This report describes all the steps performed to analyse the data of Divergent transcriptional response of dendritic cells stimulated with distinct antigen delivery systems: new insights from a comparative and reproducible computational analysis. work. The report has been automatically produced with RNASeqGUI versione 1.1.2 and then modified by hand to add paragraphs and additional comments. Moreover, it has been enriched with commands used to perform the alignment step, which RNASeqGUI software does not perform.
The alignment step has been performed with TopHat version 2.0.14 on mus musculus genome mm9 NCBI annotation version 37.67 available here.
The used shell code is the following:
tophat -o tophat_out_sample_name -p 16 -N 2 -g 10 -r 200 -a 15 -m 1 -i 100 --library-type fr-unstranded --segment-mismatches 3 --read-edit-dist 2 -G Mus_musculus.NCBIM37.67_final.gtf --transcriptome-index=transcriptome_index_Mus_musculus.NCBIM37.67_final ./RNA-Seq_Dendritic_cells/filename_R1.fastq.gz ./RNA-Seq_Dendritic_cells/filename_R2.fastq.gz
For further steps, only uniquely mapped reads have been retained using samtools.
The used shell code is the following:
samtools view -H accepted_hits.bam > header.sam
samtools view accepted_hits.bam | grep -w 'NH:i:1' | cat header.sam - | samtools view -Sb - > accepted_hits_unique.bam
In order to reproduce the report code chunks, please add these functions to your R workspace.
require(filehash)
InitDb <- function(db.name, db.path='') {
if(db.path=='') {
db.path.name <- db.name
} else {
db.path.name <- file.path(db.path, db.name)
if(!file.exists(db.path)) {
dir.create(db.path, recursive=T)
}
}
if(!file.exists(db.path.name)) {
dbCreate(db.path.name)
}
db <- dbInit(db.path.name)
return(db)
}
SaveInCache <- function(db, object, key) {
dbInsert(db, key, object)
}
LoadCachedObject <- function(db, key) {
object <- dbFetch(db, key)
return(object)
}
From now on, all the steps have been performed using RNASeqGUI v.1.1.2, available here.
This step is useful to quantify gene expression. The Feature Counts quantifier has been choosen for this aim.
Here starts the automatically generated code
/RNASeqGUI_Projects/BMDC_analysis/Results/unique_reads_FeatureCounts folder.You chose the following count file:
/BMDC_analysis/annotation/Mus_musculus.NCBIM37.67_final.gtf
, the bam folder:
/BMDC_analysis/unique_reads
, the GTF file:
/BMDC_analysis/annotation/Mus_musculus.NCBIM37.67_final.gtf
This R code has been run:
the.file ='/BMDC_analysis/annotation/Mus_musculus.NCBIM37.67_final.gtf'
Bam.FolderNew ='/BMDC_analysis/unique_reads'
Project='BMDC_analysis'
Paired='TRUE'
strand='0'
Nthread='8'
#fls <- list.files(Bam.FolderNew,pattern='bam$',full.names=TRUE)
#bamlst <- BamFileList(fls,obeyQname=TRUE)
#Vector.Bam.FolderNew = strsplit(Bam.FolderNew,'/')[[1]]
#BAM.name = Vector.Bam.FolderNew[length(Vector.Bam.FolderNew)]
#BAM.name_Counts <- paste(getwd(),'RNASeqGUI_Projects',Project,'Results/featureCounts_Report',sep='/')
#dir.create(BAM.name_Counts, showWarnings = TRUE, recursive = TRUE)
#FeatureCountsFun <- function(bamfile){
#fc_SE<-Rsubread::featureCounts(files=bamfile,annot.ext=the.file,isGTFAnnotationFile=TRUE,GTF.featureType='exon'
#GTF.attrType='gene_id',useMetaFeatures=TRUE,allowMultiOverlap=FALSE,nthreads=Nthread,strandSpecific=strand,
#countMultiMappingReads=FALSE,isPairedEnd=Paired)
#bplapply(fls, FeatureCountsFun)
This step is useful to filter out genes with low counts. This functionality has been implemented through the NoiSeq package.
Here starts the automatically generated code
BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/unique_reads_FeatureCounts/counts_FeatureCounts.txt
conditions:= c(
'DEC_1',
' DEC_2',
' E2_1',
' E2_2',
' UNTR_1',
' UNTR_2'
),
type1:
FALSE
type2:
FALSE
type3:
TRUE
cv.cutoff:
100
norm:
FALSE
cpm:
0.5
, Project:
BMDC_analysis
This R code has been run:
the.file2='counts_FeatureCounts.txt'
filtering.db <- InitDb(db.name=paste(the.file2,'filtering_db',sep=''), db.path='cache')
x <- LoadCachedObject(filtering.db, 'filtering_dataframe_key')
head(x)
## DEC_1 DEC_2 E2_1 E2_2 UNTR_1 UNTR_2
## ENSMUSG00000000702 0 0 0 0 0 0
## ENSMUSG00000078423 0 0 0 0 0 0
## ENSMUSG00000078424 0 0 0 0 0 0
## ENSMUSG00000071964 0 0 0 0 0 0
## ENSMUSG00000093774 0 0 0 0 0 0
## ENSMUSG00000093444 0 0 0 0 0 1
dim(x)[1]
## [1] 37991
the.file <- LoadCachedObject(filtering.db, 'the_file_key')
Project <- LoadCachedObject(filtering.db, 'project_key')
conditions <- LoadCachedObject(filtering.db, 'conditions_key')
type1 <- LoadCachedObject(filtering.db, 'type1_key')
type2 <- LoadCachedObject(filtering.db, 'type2_key')
type3 <- LoadCachedObject(filtering.db, 'type3_key')
cpm <- LoadCachedObject(filtering.db, 'cpm_key')
cv.cutoff <- LoadCachedObject(filtering.db, 'cvcutoff_key')
setwd('//')
#filteringfunction(x=x,the.file=the.file,conditions=conditions,type1=type1,type2=type2,type3=type3,cv.cutoff=cv.cutoff,norm=norm,cpm=cpm,Project=Project)
filtered_x <- LoadCachedObject(filtering.db, 'filteredx_key')
head(filtered_x)
## DEC_1 DEC_2 E2_1 E2_2 UNTR_1 UNTR_2
## ENSMUSG00000063889 1574 1427 1914 1748 1624 1811
## ENSMUSG00000024231 1838 1829 1808 1650 1446 1544
## ENSMUSG00000024232 164 176 185 174 181 217
## ENSMUSG00000073647 158 144 132 106 66 63
## ENSMUSG00000024235 2187 2002 1391 1282 1023 1180
## ENSMUSG00000024234 1037 947 965 898 779 903
dim(filtered_x)[1]
## [1] 13420
In order to understand how data have been transformed by filtering procedure, it is necessary to plot their distributions. Each boxplot represents the counts distribution for each experiment sample.
Here starts the automatically generated code
BMDC_analysis/Plots folder.You chose the following count file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt
, log:
TRUE
.
This R code has been run:
the.file2='Proportion_counts_FeatureCounts.txt'
countdistr.db <- InitDb(db.name=paste(the.file2,'countdistr_db',sep=''), db.path='cache')
x <- LoadCachedObject(countdistr.db, 'countdistr_dataframe_key')
the.file <- LoadCachedObject(countdistr.db, 'the_file_key')
Project <- LoadCachedObject(countdistr.db, 'project_key')
log <- LoadCachedObject(countdistr.db, 'log_key')
a=paste(getwd(),'/RNASeqGUI_Projects/',Project,'/Plots/',sep='')
the.file2 = strsplit(the.file,'/')
the.file2 = the.file2[[1]][length(the.file2[[1]])] #estract the namefile
outputName=paste(the.file2,'_countDistr.pdf',sep='')
colors=c('red','red','blue','blue','purple','purple','orange','orange','pink','orange','gold',
'darkblue','cyan','darkred')
if (log==TRUE) { boxplot(log(x+1),col=colors, main=paste(the.file2,' Log Count Distribution'),las=1) }
if (log==FALSE) { boxplot(x,col=colors, main=paste(the.file2,' Count Distribution'),las=1) }
In order to better compare and analyse the samples between them, a normalization is required. This step has been performed using the Upper Quartile normalization, present in the edgeR package.
Here starts the automatically generated code
BMDC_analysis/Plots folder.You chose the following count file: /RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt . This R code has been run:
require(edgeR)
## Loading required package: edgeR
## Loading required package: limma
##
## Attaching package: 'limma'
## The following object is masked from 'package:DEXSeq':
##
## plotMA
## The following object is masked from 'package:DESeq2':
##
## plotMA
## The following object is masked from 'package:BiocGenerics':
##
## plotMA
uqua.db <- InitDb(db.name='uqua_db', db.path='cache')
x <- LoadCachedObject(uqua.db, 'uqua_dataframe_key')
the.file <- LoadCachedObject(uqua.db, 'the_file_key')
Project <- LoadCachedObject(uqua.db, 'project_key')
print('You loaded the following count file:')
## [1] "You loaded the following count file:"
print(head(x,10))
## DEC_1 DEC_2 E2_1 E2_2 UNTR_1 UNTR_2
## ENSMUSG00000063889 1574 1427 1914 1748 1624 1811
## ENSMUSG00000024231 1838 1829 1808 1650 1446 1544
## ENSMUSG00000024232 164 176 185 174 181 217
## ENSMUSG00000073647 158 144 132 106 66 63
## ENSMUSG00000024235 2187 2002 1391 1282 1023 1180
## ENSMUSG00000024234 1037 947 965 898 779 903
## ENSMUSG00000033960 681 663 941 823 522 658
## ENSMUSG00000024236 4323 4153 3535 3485 2113 2169
## ENSMUSG00000050945 152 133 158 166 140 146
## ENSMUSG00000041225 1792 1640 1518 1397 1184 1329
#x <- edgeR::DGEList(counts = x)
#x <- edgeR::calcNormFactors(x,method='upperquartile')
#x <- edgeR::estimateCommonDisp(x, verbose=FALSE)
#x <- edgeR::estimateTagwiseDisp(x)
#myuqua <- x$pseudo.counts
myuqua <- LoadCachedObject(uqua.db, 'myuqua_key')
colors=c('red','red','blue','blue','purple','purple','orange','orange','pink','orange','gold','darkblue','cyan','darkred')
boxplot(log(myuqua+1),col=colors, main='Upper Quartile BoxPlot',las=1)
In order to understand how data have been transformed by normalization procedure, it is necessary to plot their distributions.
Here a scatter plot matrix has been plot to compare each couple of sample distributions.
Here starts the automatically generated code
BMDC_analysis/Plots folder.You chose the following count file: /RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt . This R code has been run:
library(car)
the.file2='Proportion_counts_FeatureCounts.txt_UQUA.txt'
plotspm.db<-InitDb(db.name=paste(the.file2,'plotspm_db',sep=''),db.path='cache')
x <- LoadCachedObject(plotspm.db, 'plotallcounts_dataframe_key')
the.file <- LoadCachedObject(plotspm.db, 'the_file_key')
Project <- LoadCachedObject(plotspm.db, 'project_key')
spm(log10(x+1), pch=19,cex=0.3,smoother=FALSE)
The following plot represents the Loadings of PCA, useful to undestand which of the explains the major variability.
BMDC_analysis/Plots folder.You chose the following count file: /RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt . This R code has been run:
the.file2='Proportion_counts_FeatureCounts.txt_UQUA.txt'
componenthist.db <- InitDb(db.name=paste(the.file2,'componenthist_db',sep=''), db.path='cache')
x <- LoadCachedObject(componenthist.db, 'componenthist_dataframe_key')
the.file <- LoadCachedObject(componenthist.db, 'the_file_key')
Project <- LoadCachedObject(componenthist.db, 'project_key')
a=paste(getwd(),'/RNASeqGUI_Projects/',Project,'/Plots/',sep='')
the.file2 = strsplit(the.file,'/')
the.file2 = the.file2[[1]][length(the.file2[[1]])] #estract the namefile
outputName=paste(the.file2,'_ComponentHist.pdf',sep='')
screeplot(princomp(x),main=outputName)
The PCA, useful to undestand how the samples clusterize between them.
Here starts the automatically generated code
BMDC_analysis/Plots folder.You chose the following count file: /RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt . This R code has been run:
the.file2='Proportion_counts_FeatureCounts.txt_UQUA.txt'
pcafun.db <- InitDb(db.name=paste(the.file2,'pcafun_db',sep=''), db.path='cache')
x <- LoadCachedObject(pcafun.db, 'pcafun_dataframe_key')
condition <- colnames(x)
the.file <- LoadCachedObject(pcafun.db, 'the_file_key')
Project <- LoadCachedObject(pcafun.db, 'project_key')
condition <- LoadCachedObject(pcafun.db, 'condition_key')
## Error in readSingleKey(con, map, key): unable to obtain value for key 'condition_key'
legendpos <- LoadCachedObject(pcafun.db, 'legendpos_key')
PCA <- LoadCachedObject(pcafun.db, 'pca_key')
colors <- LoadCachedObject(pcafun.db, 'colors_key')
n <- LoadCachedObject(pcafun.db, 'n_key')
PCA=prcomp(t(log(x+1)))
colors = c(rep('blue',n),rep('darkgreen',n),rep('red',n),rep('purple',n),rep('black',n),
rep('green',n),rep('brown',n),rep('pink',n),rep('gold',n))
a=paste(getwd(),'/RNASeqGUI_Projects/',Project,'/Plots/',sep='')
the.file2 = strsplit(the.file,'/')
the.file2 = the.file2[[1]][length(the.file2[[1]])] #estract the namefile
outputName=paste(the.file2,'_PCA.pdf',sep='')
plot(PCA$x,pch=unclass(as.factor(condition)),col=colors,cex=1.5, main = outputName, lwd=2)
legend(legendpos,legend=condition,pch=unclass(as.factor(condition)),col=colors,
fill='transparent',border='NA')
In order to understand the differential expressed genes for fdscaDEC (from now on just DEC) and E2, the samples have been separated in two distinct group.
The keep columns function has been used on complete count file to separate DEC and untreated samples from E2 samples.
Here starts the automatically generated code
BMDC_analysis/Results folder.You chose the following count file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt
.
This R code has been run:
dbfilename='Proportion_counts_FeatureCounts.txt_UQUA.txt_1256_keepcolumns_db'
keepcolumns.db <- InitDb(dbfilename, db.path=file.path('cache'))
Count.File <- LoadCachedObject(keepcolumns.db, 'Count_File_key')
counts <- LoadCachedObject(keepcolumns.db, 'counts_key')
print(dim(counts))
## [1] 13420 6
print(head(counts))
## DEC_1 DEC_2 E2_1 E2_2 UNTR_1
## ENSMUSG00000063889 1386.2100 1296.7846 1840.5502 1797.3179 1927.78005
## ENSMUSG00000024231 1618.9080 1662.3452 1738.6008 1696.5656 1716.66789
## ENSMUSG00000024232 144.2284 159.8542 177.8831 178.9201 214.62411
## ENSMUSG00000073647 139.4464 131.0292 126.9828 108.9937 78.76874
## ENSMUSG00000024235 1926.7159 1819.7991 1337.5621 1318.2114 1214.82938
## ENSMUSG00000024234 913.4006 860.6585 927.9543 923.3442 924.83273
## UNTR_2
## ENSMUSG00000063889 1927.03014
## ENSMUSG00000024231 1643.01010
## ENSMUSG00000024232 230.77168
## ENSMUSG00000073647 67.22854
## ENSMUSG00000024235 1255.74910
## ENSMUSG00000024234 960.87190
counts <- LoadCachedObject(keepcolumns.db, 'counts_key')
columns <- LoadCachedObject(keepcolumns.db, 'columns_key')
sub.counts <- LoadCachedObject(keepcolumns.db, 'sub_counts_key')
print(dim(sub.counts))
## [1] 13420 4
print(head(sub.counts))
## DEC_1 DEC_2 UNTR_1 UNTR_2
## ENSMUSG00000063889 1386.2100 1296.7846 1927.78005 1927.03014
## ENSMUSG00000024231 1618.9080 1662.3452 1716.66789 1643.01010
## ENSMUSG00000024232 144.2284 159.8542 214.62411 230.77168
## ENSMUSG00000073647 139.4464 131.0292 78.76874 67.22854
## ENSMUSG00000024235 1926.7159 1819.7991 1214.82938 1255.74910
## ENSMUSG00000024234 913.4006 860.6585 924.83273 960.87190
This step has been performed using the NOISeq package.
Here starts the automatically generated code
BMDC_analysis\Results folder.You chose the following count file:
Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt
, prob:
0.95
, Project:
BMDC_analysis
,
Tissue= c(
'DEC',
'DEC',
'UNTR',
'UNTR'
),
TissueRun= c(
'DEC_1',
'DEC_2',
'UNTR_1',
'UNTR_2'
).
This R code has been run:
require(NOISeq)
## Loading required package: NOISeq
## Loading required package: splines
## Loading required package: Matrix
##
## Attaching package: 'Matrix'
## The following object is masked from 'package:IRanges':
##
## expand
##
## Attaching package: 'NOISeq'
## The following object is masked from 'package:edgeR':
##
## rpkm
## The following object is masked from 'package:ShortRead':
##
## readData
require(plotrix)
the.file2='Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt'
noide2_db <- InitDb(db.name=paste(the.file2,'noide2_db',sep='_'), db.path='cache')
x <- LoadCachedObject(noide2_db, 'maindataframe_key')
the.file <- LoadCachedObject(noide2_db, 'the_file_key')
Project <- LoadCachedObject(noide2_db, 'project_key')
conditions <- LoadCachedObject(noide2_db, 'conditions_key')
TissueRuns <- LoadCachedObject(noide2_db, 'tissueruns_key')
p <- LoadCachedObject(noide2_db, 'p_key')
technical='TRUE'
print('You loaded this count file: ')
## [1] "You loaded this count file: "
print(head(as.matrix(x)))
## DEC_1 DEC_2 UNTR_1 UNTR_2
## ENSMUSG00000063889 1386.2100 1296.7846 1927.78005 1927.03014
## ENSMUSG00000024231 1618.9080 1662.3452 1716.66789 1643.01010
## ENSMUSG00000024232 144.2284 159.8542 214.62411 230.77168
## ENSMUSG00000073647 139.4464 131.0292 78.76874 67.22854
## ENSMUSG00000024235 1926.7159 1819.7991 1214.82938 1255.74910
## ENSMUSG00000024234 913.4006 860.6585 924.83273 960.87190
mynoiseq = NULL
if (technical == TRUE){ # technical replicate
print('NOISeq has been started on TECHNICAL replicates')
#myfactors = data.frame(Tissue = conditions, TissueRun = TissueRuns)
#mydata <- NOISeq::readData(data=x, factors = myfactors)
#mynoiseq = noiseq(mydata,k=0.5,norm='n',factor='Tissue',pnr = 0.2,nss = 5,
#v = 0.02,lc = 0,replicates=technical)
mynoiseq <- LoadCachedObject(noide2_db, 'mynoiseq_key')
}else{ # biological replicate
print('NOISeqBIO has been started on BIOLOGICAL replicates')
#myfactors = data.frame(Tissue = conditions, TissueRun = TissueRuns)
#mydata <- NOISeq::readData(data=x, factors=myfactors)
#mynoiseq = noiseqbio(mydata, k = 0.5, norm = 'n', factor='Tissue', lc = 0, r = 20, adj = 1.5,
#plot = FALSE, a0per = 0.9, random.seed = 12345, filter = 0)
mynoiseq <- LoadCachedObject(noide2_db, 'mynoiseq_key')
}
## [1] "NOISeq has been started on TECHNICAL replicates"
print('First five lines of the results.')
## [1] "First five lines of the results."
print( head(mynoiseq@results[[1]]) )
## DEC_mean UNTR_mean M D prob
## ENSMUSG00000063889 1341.4973 1927.40510 -0.52281569 585.90781 0.9659836
## ENSMUSG00000024231 1640.6266 1679.83900 -0.03407605 39.21240 0.2574143
## ENSMUSG00000024232 152.0413 222.69790 -0.55062467 70.65660 0.7524218
## ENSMUSG00000073647 135.2378 72.99864 0.88955713 62.23917 0.7369970
## ENSMUSG00000024235 1873.2575 1235.28924 0.60070035 637.96827 0.9744784
## ENSMUSG00000024234 887.0296 942.85231 -0.08804964 55.82276 0.4768629
## ranking
## ENSMUSG00000063889 -585.90804
## ENSMUSG00000024231 -39.21242
## ENSMUSG00000024232 -70.65874
## ENSMUSG00000073647 62.24553
## ENSMUSG00000024235 637.96855
## ENSMUSG00000024234 -55.82283
#list_DE_NOISEQ = subset(mynoiseq@results[[1]], prob > p) # select significant genes
list_DE_NOISEQ <- LoadCachedObject(noide2_db, 'listdenoiseq_key')
slices <- LoadCachedObject(noide2_db, 'slicesnoiseq_key')
lbls <- LoadCachedObject(noide2_db, 'lblsnoiseq_key')
pie3D(slices,labels=lbls,explode=0.1, main='Pie Chart of DE Genes')
To better understand the percentage of differential expressed genes, an inspection of the results has been performed with appropriate plots.
In this plot differential expressed genes are highlighted in red. Up-regulated genes are in the upper part of the plot, while down-regulated in the lower part.
Here starts the automatically generated code
BMDC_analysis/Plots folder.You chose the following count file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_results_NOISeq.txt
, prob:
0.95
, Project:
BMDC_analysis
,
the.file2='Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_results_NOISeq'
db.cache <- InitDb(db.name=paste(the.file2,'_plotfcnois_db',sep=''), db.path='cache')
results_NoiSeq <- LoadCachedObject(db.cache, 'res_key')
the.file <- LoadCachedObject(db.cache, 'thefile_key')
Project <- LoadCachedObject(db.cache, 'project_key')
p <- LoadCachedObject(db.cache, 'p_key')
name <- LoadCachedObject(db.cache, 'name_key')
print('This file has been loaded: ')
## [1] "This file has been loaded: "
print(head(results_NoiSeq))
## DEC_mean UNTR_mean M D prob
## ENSMUSG00000063889 1341.4973 1927.40510 -0.52281569 585.90781 0.9659836
## ENSMUSG00000024231 1640.6266 1679.83900 -0.03407605 39.21240 0.2574143
## ENSMUSG00000024232 152.0413 222.69790 -0.55062467 70.65660 0.7524218
## ENSMUSG00000073647 135.2378 72.99864 0.88955713 62.23917 0.7369970
## ENSMUSG00000024235 1873.2575 1235.28924 0.60070035 637.96827 0.9744784
## ENSMUSG00000024234 887.0296 942.85231 -0.08804964 55.82276 0.4768629
## ranking
## ENSMUSG00000063889 -585.90804
## ENSMUSG00000024231 -39.21242
## ENSMUSG00000024232 -70.65874
## ENSMUSG00000073647 62.24553
## ENSMUSG00000024235 637.96855
## ENSMUSG00000024234 -55.82283
print ('prob chosen: ')
## [1] "prob chosen: "
print(p)
## [1] 0.95
print ('Gene Id chosen: ')
## [1] "Gene Id chosen: "
print(name)
## [1] ""
plot(log10(results_NoiSeq[,2] * results_NoiSeq[,1]),log10(results_NoiSeq[,2]/results_NoiSeq[,1]),col='black',
main=paste('PlotFC ',the.file2,sep=''), xlab=paste('log10( ', colnames(results_NoiSeq)[2],' * ',
colnames(results_NoiSeq)[1],')',sep=''),ylab=paste('log10( ',colnames(results_NoiSeq)[2],
' / ',colnames(results_NoiSeq)[1],' )',sep=''),pch=19,cex=0.3)
DE_genes_NoiSeq = subset(results_NoiSeq, prob>p)
points(log10(DE_genes_NoiSeq[,2] * DE_genes_NoiSeq[,1]), log10(DE_genes_NoiSeq[,2]/DE_genes_NoiSeq[,1]),
pch=19, col='red', cex=0.5)
if (name!=''){ OneGene = subset(results_NoiSeq, row.names(results_NoiSeq)==name)
text(log10((OneGene[,2] * OneGene[,1])), log10(OneGene[,2]/OneGene[,1]), label=name, col='green', cex=0.6)}
In this plot differential expressed genes are highlighted in red. Up-regulated genes are in the right part of the plot, while down-regulated in the left part.
Here starts the automatically generated code
BMDC_analysis/Plots folder.You chose the following count file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_results_NOISeq.txt
, prob:
0.95
, Project:
BMDC_analysis
,
the.file2='Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_results_NOISeq'
db.cache <- InitDb(db.name=paste(the.file2,'_volcanonois_db',sep=''), db.path='cache')
results_noi <- LoadCachedObject(db.cache, 'res_key')
the.file <- LoadCachedObject(db.cache, 'thefile_key')
Project <- LoadCachedObject(db.cache, 'project_key')
name <- LoadCachedObject(db.cache, 'name_key')
p <- LoadCachedObject(db.cache, 'p_key')
print('This file has been loaded: ')
## [1] "This file has been loaded: "
print(head(results_noi))
## DEC_mean UNTR_mean M D prob
## ENSMUSG00000063889 1341.4973 1927.40510 -0.52281569 585.90781 0.9659836
## ENSMUSG00000024231 1640.6266 1679.83900 -0.03407605 39.21240 0.2574143
## ENSMUSG00000024232 152.0413 222.69790 -0.55062467 70.65660 0.7524218
## ENSMUSG00000073647 135.2378 72.99864 0.88955713 62.23917 0.7369970
## ENSMUSG00000024235 1873.2575 1235.28924 0.60070035 637.96827 0.9744784
## ENSMUSG00000024234 887.0296 942.85231 -0.08804964 55.82276 0.4768629
## ranking
## ENSMUSG00000063889 -585.90804
## ENSMUSG00000024231 -39.21242
## ENSMUSG00000024232 -70.65874
## ENSMUSG00000073647 62.24553
## ENSMUSG00000024235 637.96855
## ENSMUSG00000024234 -55.82283
p = as.numeric(p)
print ('prob chosen: ')
## [1] "prob chosen: "
print(p)
## [1] 0.95
print ('Gene Id chosen: ')
## [1] "Gene Id chosen: "
print(name)
## [1] ""
plot(log10(results_noi[,2]/results_noi[,1]), -log10(1 - results_noi$prob + 0.000001), col = 'black',
main=paste('Volcano Plot',the.file2,sep=''),xlab='log10FC',ylab='-log10(1-results_noi$prob+0.000001)',pch=19,cex=0.3)
DE_genes_NoiSeq = subset(results_noi, prob>p)
points(log10(DE_genes_NoiSeq[,2]/DE_genes_NoiSeq[,1]),-log10(1-DE_genes_NoiSeq$prob+0.000001),
pch=19,col='red',cex=0.5)
if (name!=''){ OneGene = subset(results_noi, row.names(results_noi)==name)
text(OneGene$M, OneGene$prob, label=name, col='green', cex=0.6) }
The keep columns function has been used on complete count file to separate E2 and untreated samples from DEC samples.
Here starts the automatically generated code
BMDC_analysis/Results folder.You chose the following count file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt
.
This R code has been run:
dbfilename='Proportion_counts_FeatureCounts.txt_UQUA.txt_3456_keepcolumns_db'
keepcolumns.db <- InitDb(dbfilename, db.path=file.path('cache'))
Count.File <- LoadCachedObject(keepcolumns.db, 'Count_File_key')
counts <- LoadCachedObject(keepcolumns.db, 'counts_key')
print(dim(counts))
## [1] 13420 6
print(head(counts))
## DEC_1 DEC_2 E2_1 E2_2 UNTR_1
## ENSMUSG00000063889 1386.2100 1296.7846 1840.5502 1797.3179 1927.78005
## ENSMUSG00000024231 1618.9080 1662.3452 1738.6008 1696.5656 1716.66789
## ENSMUSG00000024232 144.2284 159.8542 177.8831 178.9201 214.62411
## ENSMUSG00000073647 139.4464 131.0292 126.9828 108.9937 78.76874
## ENSMUSG00000024235 1926.7159 1819.7991 1337.5621 1318.2114 1214.82938
## ENSMUSG00000024234 913.4006 860.6585 927.9543 923.3442 924.83273
## UNTR_2
## ENSMUSG00000063889 1927.03014
## ENSMUSG00000024231 1643.01010
## ENSMUSG00000024232 230.77168
## ENSMUSG00000073647 67.22854
## ENSMUSG00000024235 1255.74910
## ENSMUSG00000024234 960.87190
counts <- LoadCachedObject(keepcolumns.db, 'counts_key')
columns <- LoadCachedObject(keepcolumns.db, 'columns_key')
sub.counts <- LoadCachedObject(keepcolumns.db, 'sub_counts_key')
print(dim(sub.counts))
## [1] 13420 4
print(head(sub.counts))
## E2_1 E2_2 UNTR_1 UNTR_2
## ENSMUSG00000063889 1840.5502 1797.3179 1927.78005 1927.03014
## ENSMUSG00000024231 1738.6008 1696.5656 1716.66789 1643.01010
## ENSMUSG00000024232 177.8831 178.9201 214.62411 230.77168
## ENSMUSG00000073647 126.9828 108.9937 78.76874 67.22854
## ENSMUSG00000024235 1337.5621 1318.2114 1214.82938 1255.74910
## ENSMUSG00000024234 927.9543 923.3442 924.83273 960.87190
This step has been performed using the NOISeq package.
Here starts the automatically generated code
BMDC_analysis\Results folder.You chose the following count file:
Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt
, prob:
0.95
, Project:
BMDC_analysis
,
Tissue= c(
'E2',
'E2',
'UNTR',
'UNTR'
),
TissueRun= c(
'E2_1',
'E2_2',
'UNTR_1',
'UNTR_2'
).
This R code has been run:
require(NOISeq)
require(plotrix)
the.file2='Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt'
noide2_db <- InitDb(db.name=paste(the.file2,'noide2_db',sep='_'), db.path='cache')
x <- LoadCachedObject(noide2_db, 'maindataframe_key')
the.file <- LoadCachedObject(noide2_db, 'the_file_key')
Project <- LoadCachedObject(noide2_db, 'project_key')
conditions <- LoadCachedObject(noide2_db, 'conditions_key')
TissueRuns <- LoadCachedObject(noide2_db, 'tissueruns_key')
p <- LoadCachedObject(noide2_db, 'p_key')
technical='TRUE'
print('You loaded this count file: ')
## [1] "You loaded this count file: "
print(head(as.matrix(x)))
## E2_1 E2_2 UNTR_1 UNTR_2
## ENSMUSG00000063889 1840.5502 1797.3179 1927.78005 1927.03014
## ENSMUSG00000024231 1738.6008 1696.5656 1716.66789 1643.01010
## ENSMUSG00000024232 177.8831 178.9201 214.62411 230.77168
## ENSMUSG00000073647 126.9828 108.9937 78.76874 67.22854
## ENSMUSG00000024235 1337.5621 1318.2114 1214.82938 1255.74910
## ENSMUSG00000024234 927.9543 923.3442 924.83273 960.87190
mynoiseq = NULL
if (technical == TRUE){ # technical replicate
print('NOISeq has been started on TECHNICAL replicates')
#myfactors = data.frame(Tissue = conditions, TissueRun = TissueRuns)
#mydata <- NOISeq::readData(data=x, factors = myfactors)
#mynoiseq = noiseq(mydata,k=0.5,norm='n',factor='Tissue',pnr = 0.2,nss = 5,
#v = 0.02,lc = 0,replicates=technical)
mynoiseq <- LoadCachedObject(noide2_db, 'mynoiseq_key')
}else{ # biological replicate
print('NOISeqBIO has been started on BIOLOGICAL replicates')
#myfactors = data.frame(Tissue = conditions, TissueRun = TissueRuns)
#mydata <- NOISeq::readData(data=x, factors=myfactors)
#mynoiseq = noiseqbio(mydata, k = 0.5, norm = 'n', factor='Tissue', lc = 0, r = 20, adj = 1.5,
#plot = FALSE, a0per = 0.9, random.seed = 12345, filter = 0)
mynoiseq <- LoadCachedObject(noide2_db, 'mynoiseq_key')
}
## [1] "NOISeq has been started on TECHNICAL replicates"
print('First five lines of the results.')
## [1] "First five lines of the results."
print( head(mynoiseq@results[[1]]) )
## E2_mean UNTR_mean M D prob
## ENSMUSG00000063889 1818.9340 1927.40510 -0.08356661 108.47107 0.5591654
## ENSMUSG00000024231 1717.5832 1679.83900 0.03205704 37.74423 0.2549925
## ENSMUSG00000024232 178.4016 222.69790 -0.31995944 44.29630 0.5848361
## ENSMUSG00000073647 117.9883 72.99864 0.69270212 44.98964 0.6417660
## ENSMUSG00000024235 1327.8867 1235.28924 0.10428320 92.59749 0.5867735
## ENSMUSG00000024234 925.6492 942.85231 -0.02656624 17.20310 0.1789121
## ranking
## ENSMUSG00000063889 -108.47111
## ENSMUSG00000024231 37.74424
## ENSMUSG00000024232 -44.29746
## ENSMUSG00000073647 44.99497
## ENSMUSG00000024235 92.59755
## ENSMUSG00000024234 -17.20312
#list_DE_NOISEQ = subset(mynoiseq@results[[1]], prob > p) # select significant genes
list_DE_NOISEQ <- LoadCachedObject(noide2_db, 'listdenoiseq_key')
slices <- LoadCachedObject(noide2_db, 'slicesnoiseq_key')
lbls <- LoadCachedObject(noide2_db, 'lblsnoiseq_key')
pie3D(slices,labels=lbls,explode=0.1, main='Pie Chart of DE Genes')
To better understand the percentage of differential expressed genes, an inspection of the results has been performed with appropriate plots.
In this plot differential expressed genes are highlighted in red. Up-regulated genes are in the upper part of the plot, while down-regulated in the lower part.
BMDC_analysis/Plots folder.You chose the following count file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_results_NOISeq.txt
, prob:
0.95
, Project:
BMDC_analysis
,
the.file2='Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_results_NOISeq'
db.cache <- InitDb(db.name=paste(the.file2,'_plotfcnois_db',sep=''), db.path='cache')
results_NoiSeq <- LoadCachedObject(db.cache, 'res_key')
the.file <- LoadCachedObject(db.cache, 'thefile_key')
Project <- LoadCachedObject(db.cache, 'project_key')
p <- LoadCachedObject(db.cache, 'p_key')
name <- LoadCachedObject(db.cache, 'name_key')
print('This file has been loaded: ')
## [1] "This file has been loaded: "
print(head(results_NoiSeq))
## E2_mean UNTR_mean M D prob
## ENSMUSG00000063889 1818.9340 1927.40510 -0.08356661 108.47107 0.5591654
## ENSMUSG00000024231 1717.5832 1679.83900 0.03205704 37.74423 0.2549925
## ENSMUSG00000024232 178.4016 222.69790 -0.31995944 44.29630 0.5848361
## ENSMUSG00000073647 117.9883 72.99864 0.69270212 44.98964 0.6417660
## ENSMUSG00000024235 1327.8867 1235.28924 0.10428320 92.59749 0.5867735
## ENSMUSG00000024234 925.6492 942.85231 -0.02656624 17.20310 0.1789121
## ranking
## ENSMUSG00000063889 -108.47111
## ENSMUSG00000024231 37.74424
## ENSMUSG00000024232 -44.29746
## ENSMUSG00000073647 44.99497
## ENSMUSG00000024235 92.59755
## ENSMUSG00000024234 -17.20312
print ('prob chosen: ')
## [1] "prob chosen: "
print(p)
## [1] 0.95
print ('Gene Id chosen: ')
## [1] "Gene Id chosen: "
print(name)
## [1] ""
plot(log10(results_NoiSeq[,2] * results_NoiSeq[,1]),log10(results_NoiSeq[,2]/results_NoiSeq[,1]),col='black',
main=paste('PlotFC ',the.file2,sep=''), xlab=paste('log10( ', colnames(results_NoiSeq)[2],' * ',
colnames(results_NoiSeq)[1],')',sep=''),ylab=paste('log10( ',colnames(results_NoiSeq)[2],
' / ',colnames(results_NoiSeq)[1],' )',sep=''),pch=19,cex=0.3)
DE_genes_NoiSeq = subset(results_NoiSeq, prob>p)
points(log10(DE_genes_NoiSeq[,2] * DE_genes_NoiSeq[,1]), log10(DE_genes_NoiSeq[,2]/DE_genes_NoiSeq[,1]),
pch=19, col='red', cex=0.5)
if (name!=''){ OneGene = subset(results_NoiSeq, row.names(results_NoiSeq)==name)
text(log10((OneGene[,2] * OneGene[,1])), log10(OneGene[,2]/OneGene[,1]), label=name, col='green', cex=0.6)}
In this plot differential expressed genes are highlighted in red. Up-regulated genes are in the right part of the plot, while down-regulated in the left part.
Here starts the automatically generated code
BMDC_analysis/Plots folder.You chose the following count file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_results_NOISeq.txt
, prob:
0.95
, Project:
BMDC_analysis
,
the.file2='Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_results_NOISeq'
db.cache <- InitDb(db.name=paste(the.file2,'_volcanonois_db',sep=''), db.path='cache')
results_noi <- LoadCachedObject(db.cache, 'res_key')
the.file <- LoadCachedObject(db.cache, 'thefile_key')
Project <- LoadCachedObject(db.cache, 'project_key')
name <- LoadCachedObject(db.cache, 'name_key')
p <- LoadCachedObject(db.cache, 'p_key')
print('This file has been loaded: ')
## [1] "This file has been loaded: "
print(head(results_noi))
## E2_mean UNTR_mean M D prob
## ENSMUSG00000063889 1818.9340 1927.40510 -0.08356661 108.47107 0.5591654
## ENSMUSG00000024231 1717.5832 1679.83900 0.03205704 37.74423 0.2549925
## ENSMUSG00000024232 178.4016 222.69790 -0.31995944 44.29630 0.5848361
## ENSMUSG00000073647 117.9883 72.99864 0.69270212 44.98964 0.6417660
## ENSMUSG00000024235 1327.8867 1235.28924 0.10428320 92.59749 0.5867735
## ENSMUSG00000024234 925.6492 942.85231 -0.02656624 17.20310 0.1789121
## ranking
## ENSMUSG00000063889 -108.47111
## ENSMUSG00000024231 37.74424
## ENSMUSG00000024232 -44.29746
## ENSMUSG00000073647 44.99497
## ENSMUSG00000024235 92.59755
## ENSMUSG00000024234 -17.20312
p = as.numeric(p)
print ('prob chosen: ')
## [1] "prob chosen: "
print(p)
## [1] 0.95
print ('Gene Id chosen: ')
## [1] "Gene Id chosen: "
print(name)
## [1] ""
plot(log10(results_noi[,2]/results_noi[,1]), -log10(1 - results_noi$prob + 0.000001), col = 'black',
main=paste('Volcano Plot',the.file2,sep=''),xlab='log10FC',ylab='-log10(1-results_noi$prob+0.000001)',pch=19,cex=0.3)
DE_genes_NoiSeq = subset(results_noi, prob>p)
points(log10(DE_genes_NoiSeq[,2]/DE_genes_NoiSeq[,1]),-log10(1-DE_genes_NoiSeq$prob+0.000001),
pch=19,col='red',cex=0.5)
if (name!=''){ OneGene = subset(results_noi, row.names(results_noi)==name)
text(OneGene$M, OneGene$prob, label=name, col='green', cex=0.6) }
In order to compare the results obtained in the differential expression step, some Venn diagrams have been produced.
The E2 genes have been intersected with DEC up-regulated and down-regulated genes.
Here starts the automatically generated code
In the Result Comparison Interface, you clicked the VennDiagram 3 sets DE button and the E2_DEC_UP_DEC_DOWN_VennDiagramDE.pdf file has been saved in the BMDC_analysis/Plots folder.
This R code has been run:
require(limma)
dbfilename <- 'E2_DEC_UP_DEC_DOWN_venn3de_db'
db <- InitDb(db.name=dbfilename, db.path='cache')
x <- LoadCachedObject(db, 'maindataframe1_key')
y <- LoadCachedObject(db, 'maindataframe2_key')
z <- LoadCachedObject(db, 'maindataframe3_key')
the.file1 <- LoadCachedObject(db, 'thefile1_key')
the.file2 <- LoadCachedObject(db, 'thefile2_key')
the.file3 <- LoadCachedObject(db, 'thefile3_key')
label1 <- LoadCachedObject(db, 'label1_key')
label2 <- LoadCachedObject(db, 'label2_key')
label3 <- LoadCachedObject(db, 'label3_key')
a = row.names(x)
b = row.names(y)
c = row.names(z)
d <- intersect(a,b) #common gene names
e <- intersect(d,c) #common gene names
Lists <- list(a, b, c) #put the word vectors into a list to supply lapply
Lists <- lapply(Lists, function(x) as.character(unlist(x)))
items <- sort(unique(unlist(Lists))) #put in alphabetical order
#MAT <- matrix(rep(0, length(items)*length(Lists)), ncol=3) #make a matrix of 0's
#names <- c(label1,label2,label3)
#colnames(MAT) <- names
#rownames(MAT) <- items
#lapply(seq_along(Lists), function(i) { #fill the matrix
# MAT[items %in% Lists[[i]], i] <<- table(Lists[[i]]) })
MAT <- LoadCachedObject(db, 'mat_key')
a=paste(getwd(),'/RNASeqGUI_Projects/',Project,'/Results/',sep='')
outputName=paste(label1,'_',label2,'_',label3,'_genes_in_intersection.txt',sep='')
b=paste(a,outputName,sep='')
#write.table(e, file = b , quote=FALSE, sep=' ', row.names=FALSE)
a=paste(getwd(),'/RNASeqGUI_Projects/',Project,'/Plots/',sep='')
outputName=paste(label1,'_',label2,'_',label3,'_VennDiagramDE.pdf',sep='')
b=paste(a,outputName,sep='')
vennDiagram(MAT,circle.col= c('red','green','yellow'),main='Venn Diagram of DE genes')
The DEC genes have been intersected with E2 up-regulated and down-regulated genes.
Here starts the automatically generated code
In the Result Comparison Interface, you clicked the VennDiagram 3 sets DE button and the DEC_E2_UP_E2_DOWN_VennDiagramDE.pdf file has been saved in the BMDC_analysis/Plots folder.
This R code has been run:
require(limma)
dbfilename <- 'DEC_E2_UP_E2_DOWN_venn3de_db'
db <- InitDb(db.name=dbfilename, db.path='cache')
x <- LoadCachedObject(db, 'maindataframe1_key')
y <- LoadCachedObject(db, 'maindataframe2_key')
z <- LoadCachedObject(db, 'maindataframe3_key')
the.file1 <- LoadCachedObject(db, 'thefile1_key')
the.file2 <- LoadCachedObject(db, 'thefile2_key')
the.file3 <- LoadCachedObject(db, 'thefile3_key')
label1 <- LoadCachedObject(db, 'label1_key')
label2 <- LoadCachedObject(db, 'label2_key')
label3 <- LoadCachedObject(db, 'label3_key')
a = row.names(x)
b = row.names(y)
c = row.names(z)
d <- intersect(a,b) #common gene names
e <- intersect(d,c) #common gene names
Lists <- list(a, b, c) #put the word vectors into a list to supply lapply
Lists <- lapply(Lists, function(x) as.character(unlist(x)))
items <- sort(unique(unlist(Lists))) #put in alphabetical order
#MAT <- matrix(rep(0, length(items)*length(Lists)), ncol=3) #make a matrix of 0's
#names <- c(label1,label2,label3)
#colnames(MAT) <- names
#rownames(MAT) <- items
#lapply(seq_along(Lists), function(i) { #fill the matrix
# MAT[items %in% Lists[[i]], i] <<- table(Lists[[i]]) })
MAT <- LoadCachedObject(db, 'mat_key')
a=paste(getwd(),'/RNASeqGUI_Projects/',Project,'/Results/',sep='')
outputName=paste(label1,'_',label2,'_',label3,'_genes_in_intersection.txt',sep='')
b=paste(a,outputName,sep='')
#write.table(e, file = b , quote=FALSE, sep=' ', row.names=FALSE)
a=paste(getwd(),'/RNASeqGUI_Projects/',Project,'/Plots/',sep='')
outputName=paste(label1,'_',label2,'_',label3,'_VennDiagramDE.pdf',sep='')
b=paste(a,outputName,sep='')
vennDiagram(MAT,circle.col= c('red','green','yellow'),main='Venn Diagram of DE genes')
The DEC up-regulated genes have been intersected with E2 up-regulated and down-regulated genes.
Here starts the automatically generated code
In the Result Comparison Interface, you clicked the VennDiagram 3 sets DE button and the DEC_UP_E2_UP_E2_DOWN_VennDiagramDE.pdf file has been saved in the BMDC_analysis/Plots folder.
This R code has been run:
require(limma)
dbfilename <- 'DEC_UP_E2_UP_E2_DOWN_venn3de_db'
db <- InitDb(db.name=dbfilename, db.path='cache')
x <- LoadCachedObject(db, 'maindataframe1_key')
y <- LoadCachedObject(db, 'maindataframe2_key')
z <- LoadCachedObject(db, 'maindataframe3_key')
the.file1 <- LoadCachedObject(db, 'thefile1_key')
the.file2 <- LoadCachedObject(db, 'thefile2_key')
the.file3 <- LoadCachedObject(db, 'thefile3_key')
label1 <- LoadCachedObject(db, 'label1_key')
label2 <- LoadCachedObject(db, 'label2_key')
label3 <- LoadCachedObject(db, 'label3_key')
a = row.names(x)
b = row.names(y)
c = row.names(z)
d <- intersect(a,b) #common gene names
e <- intersect(d,c) #common gene names
Lists <- list(a, b, c) #put the word vectors into a list to supply lapply
Lists <- lapply(Lists, function(x) as.character(unlist(x)))
items <- sort(unique(unlist(Lists))) #put in alphabetical order
#MAT <- matrix(rep(0, length(items)*length(Lists)), ncol=3) #make a matrix of 0's
#names <- c(label1,label2,label3)
#colnames(MAT) <- names
#rownames(MAT) <- items
#lapply(seq_along(Lists), function(i) { #fill the matrix
# MAT[items %in% Lists[[i]], i] <<- table(Lists[[i]]) })
MAT <- LoadCachedObject(db, 'mat_key')
a=paste(getwd(),'/RNASeqGUI_Projects/',Project,'/Results/',sep='')
outputName=paste(label1,'_',label2,'_',label3,'_genes_in_intersection.txt',sep='')
b=paste(a,outputName,sep='')
#write.table(e, file = b , quote=FALSE, sep=' ', row.names=FALSE)
a=paste(getwd(),'/RNASeqGUI_Projects/',Project,'/Plots/',sep='')
outputName=paste(label1,'_',label2,'_',label3,'_VennDiagramDE.pdf',sep='')
b=paste(a,outputName,sep='')
vennDiagram(MAT,circle.col= c('red','green','yellow'),main='Venn Diagram of DE genes')
The DEC down-regulated genes have been intersected with E2 up-regulated and down-regulated genes.
Here starts the automatically generated code
In the Result Comparison Interface, you clicked the VennDiagram 3 sets DE button and the DEC_DOWN_E2_UP_E2_DOWN_VennDiagramDE.pdf file has been saved in the BMDC_analysis/Plots folder.
This R code has been run:
require(limma)
dbfilename <- 'DEC_DOWN_E2_UP_E2_DOWN_venn3de_db'
db <- InitDb(db.name=dbfilename, db.path='cache')
x <- LoadCachedObject(db, 'maindataframe1_key')
y <- LoadCachedObject(db, 'maindataframe2_key')
z <- LoadCachedObject(db, 'maindataframe3_key')
the.file1 <- LoadCachedObject(db, 'thefile1_key')
the.file2 <- LoadCachedObject(db, 'thefile2_key')
the.file3 <- LoadCachedObject(db, 'thefile3_key')
label1 <- LoadCachedObject(db, 'label1_key')
label2 <- LoadCachedObject(db, 'label2_key')
label3 <- LoadCachedObject(db, 'label3_key')
a = row.names(x)
b = row.names(y)
c = row.names(z)
d <- intersect(a,b) #common gene names
e <- intersect(d,c) #common gene names
Lists <- list(a, b, c) #put the word vectors into a list to supply lapply
Lists <- lapply(Lists, function(x) as.character(unlist(x)))
items <- sort(unique(unlist(Lists))) #put in alphabetical order
#MAT <- matrix(rep(0, length(items)*length(Lists)), ncol=3) #make a matrix of 0's
#names <- c(label1,label2,label3)
#colnames(MAT) <- names
#rownames(MAT) <- items
#lapply(seq_along(Lists), function(i) { #fill the matrix
# MAT[items %in% Lists[[i]], i] <<- table(Lists[[i]]) })
MAT <- LoadCachedObject(db, 'mat_key')
a=paste(getwd(),'/RNASeqGUI_Projects/',Project,'/Results/',sep='')
outputName=paste(label1,'_',label2,'_',label3,'_genes_in_intersection.txt',sep='')
b=paste(a,outputName,sep='')
#write.table(e, file = b , quote=FALSE, sep=' ', row.names=FALSE)
a=paste(getwd(),'/RNASeqGUI_Projects/',Project,'/Plots/',sep='')
outputName=paste(label1,'_',label2,'_',label3,'_VennDiagramDE.pdf',sep='')
b=paste(a,outputName,sep='')
vennDiagram(MAT,circle.col= c('red','green','yellow'),main='Venn Diagram of DE genes')
In order to understand if our results regulate revelevant pathways or Gene Ontology terms, a functional analysis has been performed on them. A Gene Ontology and Pathway analysis has been performed with Gage and David packages.
To work with Gage the result file of differential expression step is necessary.
Here starts the automatically generated code
BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt
,geneSet1:
FALSE
,geneSet2:
TRUE
,Project:
BMDC_analysis
,hsa:
FALSE
,mmu:
TRUE
,dme:
FALSE
,dre:
FALSE
,conversion:
TRUE
,conversion2:
FALSE
,conversion3:
FALSE
,n:
1
,
This R code has been run:
require(biomaRt)
## Loading required package: biomaRt
require(gage)
## Loading required package: gage
require(pathview)
## Loading required package: pathview
## Loading required package: org.Hs.eg.db
##
## ##############################################################################
## Pathview is an open source software package distributed under GNU General
## Public License version 3 (GPLv3). Details of GPLv3 is available at
## http://www.gnu.org/licenses/gpl-3.0.html.
##
## The pathview downloads and uses KEGG data. Academic users may freely use the
## KEGG website at http://www.kegg.jp/ or its mirror site at GenomeNet
## http://www.genome.jp/kegg/. Academic users may also freely link to the KEGG
## website. Non-academic users may use the KEGG website as end users for
## non-commercial purposes, but any other use requires a license agreement
## (details at http://www.kegg.jp/kegg/legal.html).
## ##############################################################################
require(lattice)
geneSet1 <- FALSE
geneSet2 <- TRUE
cachedbname='Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt_FALSE_TRUE_gage_db'
db <- InitDb(db.name=cachedbname, db.path='cache')
fileName <- LoadCachedObject(db, 'filename_key')
Project <- LoadCachedObject(db, 'project_key')
geneSet1 <- LoadCachedObject(db, 'geneset1_key')
geneSet2 <- LoadCachedObject(db, 'geneset2_key')
hsa <- LoadCachedObject(db, 'hsa_key')
dme <- LoadCachedObject(db, 'dme_key')
mmu <- LoadCachedObject(db, 'mmu_key')
dre <- LoadCachedObject(db, 'dre_key')
conversion <- LoadCachedObject(db, 'conversion_key')
conversion2 <- LoadCachedObject(db, 'conversion2_key')
conversion3 <- LoadCachedObject(db, 'conversion3_key')
n <- LoadCachedObject(db, 'n_key')
res=NULL
print('Expression data selected: ')
## [1] "Expression data selected: "
print('/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt')
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt"
file.name=read.table('/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt', row.names=1, header=TRUE)
print('dimensions:')
## [1] "dimensions:"
print(dim(file.name))
## [1] 974 6
print(head(file.name))
## DEC_mean UNTR_mean M D prob
## ENSMUSG00000024235 1873.258 1235.289 0.6007003 637.9683 0.9744784
## ENSMUSG00000024236 3791.390 2408.594 0.6545356 1382.7959 0.9850969
## ENSMUSG00000006740 5218.663 3729.466 0.4847110 1489.1967 0.9697839
## ENSMUSG00000024290 3261.294 2433.127 0.4226331 828.1673 0.9561475
## ENSMUSG00000024294 4922.510 3752.394 0.3915829 1170.1164 0.9525335
## ENSMUSG00000056124 3262.128 2359.437 0.4673712 902.6919 0.9654620
## ranking
## ENSMUSG00000024235 637.9685
## ENSMUSG00000024236 1382.7960
## ENSMUSG00000006740 1489.1968
## ENSMUSG00000024290 828.1674
## ENSMUSG00000024294 1170.1164
## ENSMUSG00000056124 902.6920
kegg.gs = NULL
go.gs = NULL
if (geneSet1==TRUE){
if(hsa==TRUE){ks=kegg.gsets(species = 'hsa', id.type = 'entrez')}
if(mmu==TRUE){ks=kegg.gsets(species = 'mmu', id.type = 'entrez')}
if(dme==TRUE){ks=kegg.gsets(species = 'dme', id.type = 'entrez')}
kegg.gs=ks$kg.sets}
if (geneSet2==TRUE){ data(bods)
if(hsa==TRUE){row=subset(bods, bods[,3] == 'hsa')}
if(mmu==TRUE){row=subset(bods, bods[,3] == 'mmu')}
if(dme==TRUE){row=subset(bods, bods[,3] == 'dme')}
if(dre==TRUE){row=subset(bods, bods[,3] == 'dre')}
go=go.gsets(species = row[2], id.type = 'entrez')
go.gs=go$go.sets}
## Loading required package: org.Mm.eg.db
## Warning in library(package, lib.loc = lib.loc, character.only = TRUE,
## logical.return = TRUE, : there is no package called 'org.Mm.eg.db'
## Bioconductor version 3.2 (BiocInstaller 1.20.3), ?biocLite for help
## A new version of Bioconductor is available after installing the most
## recent version of R; see http://bioconductor.org/install
## BioC_mirror: https://bioconductor.org
## Using Bioconductor 3.2 (BiocInstaller 1.20.3), R 3.2.3 (2015-12-10).
## Installing package(s) 'org.Mm.eg.db'
##
## The downloaded source packages are in
## '/tmp/RtmpxXPIaf/downloaded_packages'
## Loading required package: org.Mm.eg.db
##
## Gene ID type for 'mouse' is: 'EG'
if(conversion==TRUE){ #ensembl gene ids to entrez genes
if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
if(mmu==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')}
if(dme==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')}
if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')}}
#if(conversion2==TRUE){ #gene names to entrez genes
#if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
# results <- getBM(attributes = c('hgnc_symbol','entrezgene'), mart=ensembl)}#to connect to a BioMart database
#if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('mgi_symbol','entrezgene') , mart=ensembl)} #to connect to a BioMart database
#if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('flybasename_gene','entrezgene'), mart=ensembl)} #to connect to a BioMart database
#if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('zfin_symbol','entrezgene'), mart=ensembl)} #to connect to a BioMart database
#file.name <- mol.sum(mol.data = file.name, id.map = results,sum.method = 'mean') }
#if(conversion3==TRUE){ # gencode names to entrez genes
#if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
#if(mmu==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')} #to connect to a BioMart database
#if(dme==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')} #to connect to a BioMartdatabase
#if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')} #to connect to a BioMart database
#newrownames = strsplit(rownames(file.name),'\.')
#nrownames = NULL
#for (i in 1:length(newrownames) ){nrownames[i] = newrownames[[i]][1]}
#rownames(file.name) = nrownames
#results <- getBM(attributes = c('ensembl_gene_id','entrezgene'), mart=ensembl)
#file.name <- mol.sum(mol.data = file.name, id.map = results,sum.method = 'mean') }
file.name <- LoadCachedObject(db, 'filenameconverted_key')
print('Expression data modified:')
## [1] "Expression data modified:"
print(dim(file.name))
## [1] 931 6
print(head(file.name))
## DEC_mean UNTR_mean M D prob ranking
## 11303 21460.367 10163.520 1.0782746 11296.8473 0.9980626 11296.8474
## 11352 1702.958 1154.060 0.5613248 548.8982 0.9687779 548.8985
## 11426 14327.668 7186.994 0.9953434 7140.6739 0.9972057 7140.6740
## 11432 8559.344 5743.498 0.5755704 2815.8454 0.9819672 2815.8454
## 11479 1593.209 1149.163 0.4713517 444.0457 0.9545082 444.0459
## 11491 9032.251 6217.521 0.5387460 2814.7293 0.9774218 2814.7294
out.suffix=NULL
fc=NULL
exp.fc <- LoadCachedObject(db, 'expfc_key')
out.suffix <- LoadCachedObject(db, 'outsuffix_key')
#if (colnames(file.name)[1] == 'log2FoldChange') {fc=file.name[,'log2FoldChange']
#names(fc)=rownames(file.name)
#sum(is.infinite(fc)) #to manage the problem of inf
#fc[fc>10]=10
#fc[fc< -10]=-10
#out.suffix='deseq' }
#if(colnames(file.name)[1] == 'logFC'){ fc=file.name[,'logFC']
#names(fc)=rownames(file.name)
#out.suffix='edger'}
#if(colnames(file.name)[3] == 'M'){ fc=file.name[,'M']
#names(fc)=rownames(file.name)
#sum(is.infinite(fc)) #to manage the problem of inf
#fc[fc>10]=10
#fc[fc< -10]=-10
#out.suffix='noiseq'}
#exp.fc=fc
#if (geneSet1==TRUE){res <- gage(exp.fc, gsets = kegg.gs, ref = NULL, samp = NULL, same.dir = FALSE, saaTest = gs.zTest, use.fold = FALSE)
#}else{res <- gage(exp.fc, gsets = go.gs , ref = NULL, samp = NULL, same.dir = FALSE, saaTest = gs.zTest, use.fold = FALSE)}
res <- LoadCachedObject(db, 'res_key')
print('First lines of results:')
## [1] "First lines of results:"
print(head(res[[1]],10))
## p.geomean
## GO:0035458 cellular response to interferon-beta 4.438578e-16
## GO:0035456 response to interferon-beta 4.122978e-15
## GO:0051607 defense response to virus 4.981495e-15
## GO:0009615 response to virus 1.215015e-13
## GO:0098542 defense response to other organism 3.649247e-13
## GO:0003690 double-stranded DNA binding 5.333721e-12
## GO:0071345 cellular response to cytokine stimulus 1.107142e-11
## GO:0001078 RNA polymerase II core promoter proximal region sequence-specific DNA binding transcription factor activity involved in negative regulation of transcription 2.478565e-11
## GO:0034097 response to cytokine 3.355081e-11
## GO:0045087 innate immune response 1.939811e-10
## stat.mean
## GO:0035458 cellular response to interferon-beta 8.041464
## GO:0035456 response to interferon-beta 7.763742
## GO:0051607 defense response to virus 7.739728
## GO:0009615 response to virus 7.322715
## GO:0098542 defense response to other organism 7.173724
## GO:0003690 double-stranded DNA binding 6.797197
## GO:0071345 cellular response to cytokine stimulus 6.691147
## GO:0001078 RNA polymerase II core promoter proximal region sequence-specific DNA binding transcription factor activity involved in negative regulation of transcription 6.572218
## GO:0034097 response to cytokine 6.526996
## GO:0045087 innate immune response 6.258796
## p.val
## GO:0035458 cellular response to interferon-beta 4.438578e-16
## GO:0035456 response to interferon-beta 4.122978e-15
## GO:0051607 defense response to virus 4.981495e-15
## GO:0009615 response to virus 1.215015e-13
## GO:0098542 defense response to other organism 3.649247e-13
## GO:0003690 double-stranded DNA binding 5.333721e-12
## GO:0071345 cellular response to cytokine stimulus 1.107142e-11
## GO:0001078 RNA polymerase II core promoter proximal region sequence-specific DNA binding transcription factor activity involved in negative regulation of transcription 2.478565e-11
## GO:0034097 response to cytokine 3.355081e-11
## GO:0045087 innate immune response 1.939811e-10
## q.val
## GO:0035458 cellular response to interferon-beta 7.385794e-13
## GO:0035456 response to interferon-beta 2.763069e-12
## GO:0051607 defense response to virus 2.763069e-12
## GO:0009615 response to virus 5.054461e-11
## GO:0098542 defense response to other organism 1.214469e-10
## GO:0003690 double-stranded DNA binding 1.479219e-09
## GO:0071345 cellular response to cytokine stimulus 2.631834e-09
## GO:0001078 RNA polymerase II core promoter proximal region sequence-specific DNA binding transcription factor activity involved in negative regulation of transcription 5.155414e-09
## GO:0034097 response to cytokine 6.203172e-09
## GO:0045087 innate immune response 3.227845e-08
## set.size
## GO:0035458 cellular response to interferon-beta 16
## GO:0035456 response to interferon-beta 19
## GO:0051607 defense response to virus 43
## GO:0009615 response to virus 48
## GO:0098542 defense response to other organism 73
## GO:0003690 double-stranded DNA binding 19
## GO:0071345 cellular response to cytokine stimulus 55
## GO:0001078 RNA polymerase II core promoter proximal region sequence-specific DNA binding transcription factor activity involved in negative regulation of transcription 15
## GO:0034097 response to cytokine 73
## GO:0045087 innate immune response 93
## exp1
## GO:0035458 cellular response to interferon-beta 4.438578e-16
## GO:0035456 response to interferon-beta 4.122978e-15
## GO:0051607 defense response to virus 4.981495e-15
## GO:0009615 response to virus 1.215015e-13
## GO:0098542 defense response to other organism 3.649247e-13
## GO:0003690 double-stranded DNA binding 5.333721e-12
## GO:0071345 cellular response to cytokine stimulus 1.107142e-11
## GO:0001078 RNA polymerase II core promoter proximal region sequence-specific DNA binding transcription factor activity involved in negative regulation of transcription 2.478565e-11
## GO:0034097 response to cytokine 3.355081e-11
## GO:0045087 innate immune response 1.939811e-10
#sel <- res$greater[, 'q.val'] < 0.01 & !is.na(res$greater[, 'q.val'])
#path.ids <- rownames(res$greater)[sel]
#sel.l <- res$less[, 'q.val'] < 0.01 & !is.na(res$less[,'q.val'])
#path.ids.l <- rownames(res$less)[sel.l]
#path.ids2 <- substr(c(path.ids, path.ids.l), 1, 8) #put greater and less together
path.ids2 <- LoadCachedObject(db, 'finalresults_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(path.ids2))
## [1] "GO:00354" "GO:00354" "GO:00516" "GO:00096" "GO:00985" "GO:00036"
#pv.out.list <- sapply(path.ids2, function(pid){ pathview( gene.data = exp.fc, pathway.id = pid, species = specie, out.suffix=out.suffix)})
Here starts the automatically generated code
BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt
,geneSet1:
FALSE
,geneSet2:
TRUE
,Project:
BMDC_analysis
,hsa:
FALSE
,mmu:
TRUE
,dme:
FALSE
,dre:
FALSE
,conversion:
TRUE
,conversion2:
FALSE
,conversion3:
FALSE
,n:
1
,
This R code has been run:
require(biomaRt)
require(gage)
require(pathview)
require(lattice)
geneSet1 <- FALSE
geneSet2 <- TRUE
cachedbname='Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt_FALSE_TRUE_gage_db'
db <- InitDb(db.name=cachedbname, db.path='cache')
fileName <- LoadCachedObject(db, 'filename_key')
Project <- LoadCachedObject(db, 'project_key')
geneSet1 <- LoadCachedObject(db, 'geneset1_key')
geneSet2 <- LoadCachedObject(db, 'geneset2_key')
hsa <- LoadCachedObject(db, 'hsa_key')
dme <- LoadCachedObject(db, 'dme_key')
mmu <- LoadCachedObject(db, 'mmu_key')
dre <- LoadCachedObject(db, 'dre_key')
conversion <- LoadCachedObject(db, 'conversion_key')
conversion2 <- LoadCachedObject(db, 'conversion2_key')
conversion3 <- LoadCachedObject(db, 'conversion3_key')
n <- LoadCachedObject(db, 'n_key')
res=NULL
print('Expression data selected: ')
## [1] "Expression data selected: "
print('/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt')
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt"
file.name=read.table('/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt', row.names=1, header=TRUE)
print('dimensions:')
## [1] "dimensions:"
print(dim(file.name))
## [1] 1044 6
print(head(file.name))
## DEC_mean UNTR_mean M D prob
## ENSMUSG00000063889 1341.497 1927.405 -0.5228157 585.9078 0.9659836
## ENSMUSG00000002477 1122.267 1572.918 -0.4870281 450.6514 0.9572653
## ENSMUSG00000024424 2829.878 4108.648 -0.5379237 1278.7698 0.9754844
## ENSMUSG00000024381 4013.433 5221.045 -0.3795020 1207.6126 0.9504844
## ENSMUSG00000090523 1423.218 2019.995 -0.5051948 596.7766 0.9650522
## ENSMUSG00000037815 20141.680 26196.586 -0.3791948 6054.9058 0.9534650
## ranking
## ENSMUSG00000063889 -585.9080
## ENSMUSG00000002477 -450.6517
## ENSMUSG00000024424 -1278.7699
## ENSMUSG00000024381 -1207.6127
## ENSMUSG00000090523 -596.7768
## ENSMUSG00000037815 -6054.9058
kegg.gs = NULL
go.gs = NULL
if (geneSet1==TRUE){
if(hsa==TRUE){ks=kegg.gsets(species = 'hsa', id.type = 'entrez')}
if(mmu==TRUE){ks=kegg.gsets(species = 'mmu', id.type = 'entrez')}
if(dme==TRUE){ks=kegg.gsets(species = 'dme', id.type = 'entrez')}
kegg.gs=ks$kg.sets}
if (geneSet2==TRUE){ data(bods)
if(hsa==TRUE){row=subset(bods, bods[,3] == 'hsa')}
if(mmu==TRUE){row=subset(bods, bods[,3] == 'mmu')}
if(dme==TRUE){row=subset(bods, bods[,3] == 'dme')}
if(dre==TRUE){row=subset(bods, bods[,3] == 'dre')}
go=go.gsets(species = row[2], id.type = 'entrez')
go.gs=go$go.sets}
## Gene ID type for 'mouse' is: 'EG'
if(conversion==TRUE){ #ensembl gene ids to entrez genes
if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
if(mmu==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')}
if(dme==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')}
if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')}}
#if(conversion2==TRUE){ #gene names to entrez genes
#if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
# results <- getBM(attributes = c('hgnc_symbol','entrezgene'), mart=ensembl)}#to connect to a BioMart database
#if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('mgi_symbol','entrezgene') , mart=ensembl)} #to connect to a BioMart database
#if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('flybasename_gene','entrezgene'), mart=ensembl)} #to connect to a BioMart database
#if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('zfin_symbol','entrezgene'), mart=ensembl)} #to connect to a BioMart database
#file.name <- mol.sum(mol.data = file.name, id.map = results,sum.method = 'mean') }
#if(conversion3==TRUE){ # gencode names to entrez genes
#if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
#if(mmu==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')} #to connect to a BioMart database
#if(dme==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')} #to connect to a BioMartdatabase
#if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')} #to connect to a BioMart database
#newrownames = strsplit(rownames(file.name),'\.')
#nrownames = NULL
#for (i in 1:length(newrownames) ){nrownames[i] = newrownames[[i]][1]}
#rownames(file.name) = nrownames
#results <- getBM(attributes = c('ensembl_gene_id','entrezgene'), mart=ensembl)
#file.name <- mol.sum(mol.data = file.name, id.map = results,sum.method = 'mean') }
file.name <- LoadCachedObject(db, 'filenameconverted_key')
print('Expression data modified:')
## [1] "Expression data modified:"
print(dim(file.name))
## [1] 995 6
print(head(file.name))
## DEC_mean UNTR_mean M D prob ranking
## 11409 1663.4981 2492.903 -0.5836063 829.4045 0.9766393 -829.4047
## 11416 1625.0272 2252.548 -0.4710940 627.5208 0.9609911 -627.5210
## 11461 252952.6590 343899.257 -0.4431186 90946.5983 0.9672504 -90946.5983
## 11465 77439.7335 101541.732 -0.3909269 24101.9988 0.9563338 -24101.9988
## 11475 952.0971 1374.974 -0.5302232 422.8764 0.9596125 -422.8768
## 11540 1389.6178 2233.098 -0.6843586 843.4805 0.9836438 -843.4808
out.suffix=NULL
fc=NULL
exp.fc <- LoadCachedObject(db, 'expfc_key')
out.suffix <- LoadCachedObject(db, 'outsuffix_key')
#if (colnames(file.name)[1] == 'log2FoldChange') {fc=file.name[,'log2FoldChange']
#names(fc)=rownames(file.name)
#sum(is.infinite(fc)) #to manage the problem of inf
#fc[fc>10]=10
#fc[fc< -10]=-10
#out.suffix='deseq' }
#if(colnames(file.name)[1] == 'logFC'){ fc=file.name[,'logFC']
#names(fc)=rownames(file.name)
#out.suffix='edger'}
#if(colnames(file.name)[3] == 'M'){ fc=file.name[,'M']
#names(fc)=rownames(file.name)
#sum(is.infinite(fc)) #to manage the problem of inf
#fc[fc>10]=10
#fc[fc< -10]=-10
#out.suffix='noiseq'}
#exp.fc=fc
#if (geneSet1==TRUE){res <- gage(exp.fc, gsets = kegg.gs, ref = NULL, samp = NULL, same.dir = FALSE, saaTest = gs.zTest, use.fold = FALSE)
#}else{res <- gage(exp.fc, gsets = go.gs , ref = NULL, samp = NULL, same.dir = FALSE, saaTest = gs.zTest, use.fold = FALSE)}
res <- LoadCachedObject(db, 'res_key')
print('First lines of results:')
## [1] "First lines of results:"
print(head(res[[1]],10))
## p.geomean stat.mean
## GO:0003735 structural constituent of ribosome 0.0002410070 3.490557
## GO:0022627 cytosolic small ribosomal subunit 0.0003205543 3.413599
## GO:0005840 ribosome 0.0005093112 3.285332
## GO:0005126 cytokine receptor binding 0.0005920397 3.242688
## GO:0022626 cytosolic ribosome 0.0010730612 3.069229
## GO:0015935 small ribosomal subunit 0.0016157705 2.944809
## GO:0005125 cytokine activity 0.0018521616 2.902301
## GO:0044391 ribosomal subunit 0.0025001536 2.807014
## GO:0005578 proteinaceous extracellular matrix 0.0044961935 2.612343
## GO:0031012 extracellular matrix 0.0047064300 2.596684
## p.val q.val
## GO:0003735 structural constituent of ribosome 0.0002410070 0.1944850
## GO:0022627 cytosolic small ribosomal subunit 0.0003205543 0.1944850
## GO:0005840 ribosome 0.0005093112 0.1944850
## GO:0005126 cytokine receptor binding 0.0005920397 0.1944850
## GO:0022626 cytosolic ribosome 0.0010730612 0.2820005
## GO:0015935 small ribosomal subunit 0.0016157705 0.3476772
## GO:0005125 cytokine activity 0.0018521616 0.3476772
## GO:0044391 ribosomal subunit 0.0025001536 0.4106502
## GO:0005578 proteinaceous extracellular matrix 0.0044961935 0.5993361
## GO:0031012 extracellular matrix 0.0047064300 0.5993361
## set.size exp1
## GO:0003735 structural constituent of ribosome 88 0.0002410070
## GO:0022627 cytosolic small ribosomal subunit 30 0.0003205543
## GO:0005840 ribosome 103 0.0005093112
## GO:0005126 cytokine receptor binding 14 0.0005920397
## GO:0022626 cytosolic ribosome 70 0.0010730612
## GO:0015935 small ribosomal subunit 43 0.0016157705
## GO:0005125 cytokine activity 13 0.0018521616
## GO:0044391 ribosomal subunit 91 0.0025001536
## GO:0005578 proteinaceous extracellular matrix 24 0.0044961935
## GO:0031012 extracellular matrix 34 0.0047064300
#sel <- res$greater[, 'q.val'] < 0.01 & !is.na(res$greater[, 'q.val'])
#path.ids <- rownames(res$greater)[sel]
#sel.l <- res$less[, 'q.val'] < 0.01 & !is.na(res$less[,'q.val'])
#path.ids.l <- rownames(res$less)[sel.l]
#path.ids2 <- substr(c(path.ids, path.ids.l), 1, 8) #put greater and less together
path.ids2 <- LoadCachedObject(db, 'finalresults_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(path.ids2))
## character(0)
#pv.out.list <- sapply(path.ids2, function(pid){ pathview( gene.data = exp.fc, pathway.id = pid, species = specie, out.suffix=out.suffix)})
Here starts the automatically generated code
BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt
,geneSet1:
TRUE
,geneSet2:
FALSE
,Project:
BMDC_analysis
,hsa:
FALSE
,mmu:
TRUE
,dme:
FALSE
,dre:
FALSE
,conversion:
TRUE
,conversion2:
FALSE
,conversion3:
FALSE
,n:
1
,
This R code has been run:
require(biomaRt)
require(gage)
require(pathview)
require(lattice)
geneSet1 <- TRUE
geneSet2 <- FALSE
cachedbname='Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt_TRUE_FALSE_gage_db'
db <- InitDb(db.name=cachedbname, db.path='cache')
fileName <- LoadCachedObject(db, 'filename_key')
Project <- LoadCachedObject(db, 'project_key')
geneSet1 <- LoadCachedObject(db, 'geneset1_key')
geneSet2 <- LoadCachedObject(db, 'geneset2_key')
hsa <- LoadCachedObject(db, 'hsa_key')
dme <- LoadCachedObject(db, 'dme_key')
mmu <- LoadCachedObject(db, 'mmu_key')
dre <- LoadCachedObject(db, 'dre_key')
conversion <- LoadCachedObject(db, 'conversion_key')
conversion2 <- LoadCachedObject(db, 'conversion2_key')
conversion3 <- LoadCachedObject(db, 'conversion3_key')
n <- LoadCachedObject(db, 'n_key')
res=NULL
print('Expression data selected: ')
## [1] "Expression data selected: "
print('/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt')
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt"
file.name=read.table('/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt', row.names=1, header=TRUE)
print('dimensions:')
## [1] "dimensions:"
print(dim(file.name))
## [1] 974 6
print(head(file.name))
## DEC_mean UNTR_mean M D prob
## ENSMUSG00000024235 1873.258 1235.289 0.6007003 637.9683 0.9744784
## ENSMUSG00000024236 3791.390 2408.594 0.6545356 1382.7959 0.9850969
## ENSMUSG00000006740 5218.663 3729.466 0.4847110 1489.1967 0.9697839
## ENSMUSG00000024290 3261.294 2433.127 0.4226331 828.1673 0.9561475
## ENSMUSG00000024294 4922.510 3752.394 0.3915829 1170.1164 0.9525335
## ENSMUSG00000056124 3262.128 2359.437 0.4673712 902.6919 0.9654620
## ranking
## ENSMUSG00000024235 637.9685
## ENSMUSG00000024236 1382.7960
## ENSMUSG00000006740 1489.1968
## ENSMUSG00000024290 828.1674
## ENSMUSG00000024294 1170.1164
## ENSMUSG00000056124 902.6920
kegg.gs = NULL
go.gs = NULL
if (geneSet1==TRUE){
if(hsa==TRUE){ks=kegg.gsets(species = 'hsa', id.type = 'entrez')}
if(mmu==TRUE){ks=kegg.gsets(species = 'mmu', id.type = 'entrez')}
if(dme==TRUE){ks=kegg.gsets(species = 'dme', id.type = 'entrez')}
kegg.gs=ks$kg.sets}
if (geneSet2==TRUE){ data(bods)
if(hsa==TRUE){row=subset(bods, bods[,3] == 'hsa')}
if(mmu==TRUE){row=subset(bods, bods[,3] == 'mmu')}
if(dme==TRUE){row=subset(bods, bods[,3] == 'dme')}
if(dre==TRUE){row=subset(bods, bods[,3] == 'dre')}
go=go.gsets(species = row[2], id.type = 'entrez')
go.gs=go$go.sets}
if(conversion==TRUE){ #ensembl gene ids to entrez genes
if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
if(mmu==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')}
if(dme==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')}
if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')}}
#if(conversion2==TRUE){ #gene names to entrez genes
#if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
# results <- getBM(attributes = c('hgnc_symbol','entrezgene'), mart=ensembl)}#to connect to a BioMart database
#if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('mgi_symbol','entrezgene') , mart=ensembl)} #to connect to a BioMart database
#if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('flybasename_gene','entrezgene'), mart=ensembl)} #to connect to a BioMart database
#if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('zfin_symbol','entrezgene'), mart=ensembl)} #to connect to a BioMart database
#file.name <- mol.sum(mol.data = file.name, id.map = results,sum.method = 'mean') }
#if(conversion3==TRUE){ # gencode names to entrez genes
#if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
#if(mmu==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')} #to connect to a BioMart database
#if(dme==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')} #to connect to a BioMartdatabase
#if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')} #to connect to a BioMart database
#newrownames = strsplit(rownames(file.name),'\.')
#nrownames = NULL
#for (i in 1:length(newrownames) ){nrownames[i] = newrownames[[i]][1]}
#rownames(file.name) = nrownames
#results <- getBM(attributes = c('ensembl_gene_id','entrezgene'), mart=ensembl)
#file.name <- mol.sum(mol.data = file.name, id.map = results,sum.method = 'mean') }
file.name <- LoadCachedObject(db, 'filenameconverted_key')
print('Expression data modified:')
## [1] "Expression data modified:"
print(dim(file.name))
## [1] 931 6
print(head(file.name))
## DEC_mean UNTR_mean M D prob ranking
## 11303 21460.367 10163.520 1.0782746 11296.8473 0.9980626 11296.8474
## 11352 1702.958 1154.060 0.5613248 548.8982 0.9687779 548.8985
## 11426 14327.668 7186.994 0.9953434 7140.6739 0.9972057 7140.6740
## 11432 8559.344 5743.498 0.5755704 2815.8454 0.9819672 2815.8454
## 11479 1593.209 1149.163 0.4713517 444.0457 0.9545082 444.0459
## 11491 9032.251 6217.521 0.5387460 2814.7293 0.9774218 2814.7294
out.suffix=NULL
fc=NULL
exp.fc <- LoadCachedObject(db, 'expfc_key')
out.suffix <- LoadCachedObject(db, 'outsuffix_key')
#if (colnames(file.name)[1] == 'log2FoldChange') {fc=file.name[,'log2FoldChange']
#names(fc)=rownames(file.name)
#sum(is.infinite(fc)) #to manage the problem of inf
#fc[fc>10]=10
#fc[fc< -10]=-10
#out.suffix='deseq' }
#if(colnames(file.name)[1] == 'logFC'){ fc=file.name[,'logFC']
#names(fc)=rownames(file.name)
#out.suffix='edger'}
#if(colnames(file.name)[3] == 'M'){ fc=file.name[,'M']
#names(fc)=rownames(file.name)
#sum(is.infinite(fc)) #to manage the problem of inf
#fc[fc>10]=10
#fc[fc< -10]=-10
#out.suffix='noiseq'}
#exp.fc=fc
#if (geneSet1==TRUE){res <- gage(exp.fc, gsets = kegg.gs, ref = NULL, samp = NULL, same.dir = FALSE, saaTest = gs.zTest, use.fold = FALSE)
#}else{res <- gage(exp.fc, gsets = go.gs , ref = NULL, samp = NULL, same.dir = FALSE, saaTest = gs.zTest, use.fold = FALSE)}
res <- LoadCachedObject(db, 'res_key')
print('First lines of results:')
## [1] "First lines of results:"
print(head(res[[1]],10))
## p.geomean stat.mean
## mmu05160 Hepatitis C 2.981657e-07 4.992401
## mmu05164 Influenza A 4.379829e-07 4.917634
## mmu05168 Herpes simplex infection 4.526240e-07 4.911191
## mmu05162 Measles 1.773026e-05 4.135226
## mmu04622 RIG-I-like receptor signaling pathway 1.299193e-03 3.011642
## mmu04623 Cytosolic DNA-sensing pathway 4.341199e-03 2.624313
## mmu04060 Cytokine-cytokine receptor interaction 2.929689e-02 1.891229
## mmu05161 Hepatitis B 3.748099e-02 1.780697
## mmu04668 TNF signaling pathway 4.778172e-02 1.666753
## mmu05203 Viral carcinogenesis 7.479971e-02 1.440948
## p.val q.val
## mmu05160 Hepatitis C 2.981657e-07 1.025948e-05
## mmu05164 Influenza A 4.379829e-07 1.025948e-05
## mmu05168 Herpes simplex infection 4.526240e-07 1.025948e-05
## mmu05162 Measles 1.773026e-05 3.014144e-04
## mmu04622 RIG-I-like receptor signaling pathway 1.299193e-03 1.766902e-02
## mmu04623 Cytosolic DNA-sensing pathway 4.341199e-03 4.920026e-02
## mmu04060 Cytokine-cytokine receptor interaction 2.929689e-02 2.845983e-01
## mmu05161 Hepatitis B 3.748099e-02 3.185884e-01
## mmu04668 TNF signaling pathway 4.778172e-02 3.610174e-01
## mmu05203 Viral carcinogenesis 7.479971e-02 5.086380e-01
## set.size exp1
## mmu05160 Hepatitis C 23 2.981657e-07
## mmu05164 Influenza A 37 4.379829e-07
## mmu05168 Herpes simplex infection 40 4.526240e-07
## mmu05162 Measles 29 1.773026e-05
## mmu04622 RIG-I-like receptor signaling pathway 13 1.299193e-03
## mmu04623 Cytosolic DNA-sensing pathway 13 4.341199e-03
## mmu04060 Cytokine-cytokine receptor interaction 23 2.929689e-02
## mmu05161 Hepatitis B 22 3.748099e-02
## mmu04668 TNF signaling pathway 19 4.778172e-02
## mmu05203 Viral carcinogenesis 21 7.479971e-02
#sel <- res$greater[, 'q.val'] < 0.01 & !is.na(res$greater[, 'q.val'])
#path.ids <- rownames(res$greater)[sel]
#sel.l <- res$less[, 'q.val'] < 0.01 & !is.na(res$less[,'q.val'])
#path.ids.l <- rownames(res$less)[sel.l]
#path.ids2 <- substr(c(path.ids, path.ids.l), 1, 8) #put greater and less together
path.ids2 <- LoadCachedObject(db, 'finalresults_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(path.ids2))
## [1] "mmu05160" "mmu05164" "mmu05168" "mmu05162" "mmu04622" "mmu04623"
#pv.out.list <- sapply(path.ids2, function(pid){ pathview( gene.data = exp.fc, pathway.id = pid, species = specie, out.suffix=out.suffix)})
Here starts the automatically generated code
BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt
,geneSet1:
TRUE
,geneSet2:
FALSE
,Project:
BMDC_analysis
,hsa:
FALSE
,mmu:
TRUE
,dme:
FALSE
,dre:
FALSE
,conversion:
TRUE
,conversion2:
FALSE
,conversion3:
FALSE
,n:
1
,
This R code has been run:
require(biomaRt)
require(gage)
require(pathview)
require(lattice)
geneSet1 <- TRUE
geneSet2 <- FALSE
cachedbname='Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt_TRUE_FALSE_gage_db'
db <- InitDb(db.name=cachedbname, db.path='cache')
fileName <- LoadCachedObject(db, 'filename_key')
Project <- LoadCachedObject(db, 'project_key')
geneSet1 <- LoadCachedObject(db, 'geneset1_key')
geneSet2 <- LoadCachedObject(db, 'geneset2_key')
hsa <- LoadCachedObject(db, 'hsa_key')
dme <- LoadCachedObject(db, 'dme_key')
mmu <- LoadCachedObject(db, 'mmu_key')
dre <- LoadCachedObject(db, 'dre_key')
conversion <- LoadCachedObject(db, 'conversion_key')
conversion2 <- LoadCachedObject(db, 'conversion2_key')
conversion3 <- LoadCachedObject(db, 'conversion3_key')
n <- LoadCachedObject(db, 'n_key')
res=NULL
print('Expression data selected: ')
## [1] "Expression data selected: "
print('/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt')
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt"
file.name=read.table('/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt', row.names=1, header=TRUE)
print('dimensions:')
## [1] "dimensions:"
print(dim(file.name))
## [1] 833 6
print(head(file.name))
## E2_mean UNTR_mean M D prob
## ENSMUSG00000024236 3491.317 2408.5939 0.5355801 1082.7228 0.9695231
## ENSMUSG00000006740 5179.638 3729.4665 0.4738820 1450.1715 0.9626677
## ENSMUSG00000024290 3519.108 2433.1265 0.5323986 1085.9818 0.9687034
## ENSMUSG00000024294 5623.267 3752.3939 0.5835973 1870.8733 0.9753353
## ENSMUSG00000033382 3250.364 2356.2755 0.4640931 894.0885 0.9585320
## ENSMUSG00000041915 1016.327 589.2449 0.7864249 427.0818 0.9752981
## ranking
## ENSMUSG00000024236 1082.7229
## ENSMUSG00000006740 1450.1715
## ENSMUSG00000024290 1085.9820
## ENSMUSG00000024294 1870.8734
## ENSMUSG00000033382 894.0886
## ENSMUSG00000041915 427.0825
kegg.gs = NULL
go.gs = NULL
if (geneSet1==TRUE){
if(hsa==TRUE){ks=kegg.gsets(species = 'hsa', id.type = 'entrez')}
if(mmu==TRUE){ks=kegg.gsets(species = 'mmu', id.type = 'entrez')}
if(dme==TRUE){ks=kegg.gsets(species = 'dme', id.type = 'entrez')}
kegg.gs=ks$kg.sets}
if (geneSet2==TRUE){ data(bods)
if(hsa==TRUE){row=subset(bods, bods[,3] == 'hsa')}
if(mmu==TRUE){row=subset(bods, bods[,3] == 'mmu')}
if(dme==TRUE){row=subset(bods, bods[,3] == 'dme')}
if(dre==TRUE){row=subset(bods, bods[,3] == 'dre')}
go=go.gsets(species = row[2], id.type = 'entrez')
go.gs=go$go.sets}
if(conversion==TRUE){ #ensembl gene ids to entrez genes
if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
if(mmu==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')}
if(dme==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')}
if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')}}
#if(conversion2==TRUE){ #gene names to entrez genes
#if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
# results <- getBM(attributes = c('hgnc_symbol','entrezgene'), mart=ensembl)}#to connect to a BioMart database
#if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('mgi_symbol','entrezgene') , mart=ensembl)} #to connect to a BioMart database
#if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('flybasename_gene','entrezgene'), mart=ensembl)} #to connect to a BioMart database
#if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('zfin_symbol','entrezgene'), mart=ensembl)} #to connect to a BioMart database
#file.name <- mol.sum(mol.data = file.name, id.map = results,sum.method = 'mean') }
#if(conversion3==TRUE){ # gencode names to entrez genes
#if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
#if(mmu==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')} #to connect to a BioMart database
#if(dme==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')} #to connect to a BioMartdatabase
#if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')} #to connect to a BioMart database
#newrownames = strsplit(rownames(file.name),'\.')
#nrownames = NULL
#for (i in 1:length(newrownames) ){nrownames[i] = newrownames[[i]][1]}
#rownames(file.name) = nrownames
#results <- getBM(attributes = c('ensembl_gene_id','entrezgene'), mart=ensembl)
#file.name <- mol.sum(mol.data = file.name, id.map = results,sum.method = 'mean') }
file.name <- LoadCachedObject(db, 'filenameconverted_key')
print('Expression data modified:')
## [1] "Expression data modified:"
print(dim(file.name))
## [1] 805 6
print(head(file.name))
## E2_mean UNTR_mean M D prob ranking
## 11305 2251.808 1587.416 0.5044036 664.3920 0.9614754 664.3922
## 11352 1756.638 1154.060 0.6060989 602.5782 0.9710134 602.5785
## 11426 13403.227 7186.994 0.8991199 6216.2327 0.9929955 6216.2327
## 11433 8977.105 5383.496 0.7377070 3593.6095 0.9877049 3593.6096
## 11479 1613.703 1149.163 0.4897913 464.5398 0.9542474 464.5400
## 11492 5231.593 3654.661 0.5175125 1576.9314 0.9691505 1576.9315
out.suffix=NULL
fc=NULL
exp.fc <- LoadCachedObject(db, 'expfc_key')
out.suffix <- LoadCachedObject(db, 'outsuffix_key')
#if (colnames(file.name)[1] == 'log2FoldChange') {fc=file.name[,'log2FoldChange']
#names(fc)=rownames(file.name)
#sum(is.infinite(fc)) #to manage the problem of inf
#fc[fc>10]=10
#fc[fc< -10]=-10
#out.suffix='deseq' }
#if(colnames(file.name)[1] == 'logFC'){ fc=file.name[,'logFC']
#names(fc)=rownames(file.name)
#out.suffix='edger'}
#if(colnames(file.name)[3] == 'M'){ fc=file.name[,'M']
#names(fc)=rownames(file.name)
#sum(is.infinite(fc)) #to manage the problem of inf
#fc[fc>10]=10
#fc[fc< -10]=-10
#out.suffix='noiseq'}
#exp.fc=fc
#if (geneSet1==TRUE){res <- gage(exp.fc, gsets = kegg.gs, ref = NULL, samp = NULL, same.dir = FALSE, saaTest = gs.zTest, use.fold = FALSE)
#}else{res <- gage(exp.fc, gsets = go.gs , ref = NULL, samp = NULL, same.dir = FALSE, saaTest = gs.zTest, use.fold = FALSE)}
res <- LoadCachedObject(db, 'res_key')
print('First lines of results:')
## [1] "First lines of results:"
print(head(res[[1]],10))
## p.geomean stat.mean
## mmu05410 Hypertrophic cardiomyopathy (HCM) 0.0001113742 3.6917135
## mmu05414 Dilated cardiomyopathy 0.0005946565 3.2414308
## mmu04810 Regulation of actin cytoskeleton 0.0066885871 2.4735669
## mmu04514 Cell adhesion molecules (CAMs) 0.0088502965 2.3718225
## mmu04145 Phagosome 0.0445257276 1.7004226
## mmu04510 Focal adhesion 0.0882811808 1.3514155
## mmu05206 MicroRNAs in cancer 0.1482244541 1.0440789
## mmu04120 Ubiquitin mediated proteolysis 0.1607398999 0.9914215
## mmu04151 PI3K-Akt signaling pathway 0.1820232294 0.9076816
## mmu00310 Lysine degradation 0.2182508717 0.7781141
## p.val q.val
## mmu05410 Hypertrophic cardiomyopathy (HCM) 0.0001113742 0.006459701
## mmu05414 Dilated cardiomyopathy 0.0005946565 0.017245038
## mmu04810 Regulation of actin cytoskeleton 0.0066885871 0.128329299
## mmu04514 Cell adhesion molecules (CAMs) 0.0088502965 0.128329299
## mmu04145 Phagosome 0.0445257276 0.516498440
## mmu04510 Focal adhesion 0.0882811808 0.853384748
## mmu05206 MicroRNAs in cancer 0.1482244541 0.932795641
## mmu04120 Ubiquitin mediated proteolysis 0.1607398999 0.932795641
## mmu04151 PI3K-Akt signaling pathway 0.1820232294 0.932795641
## mmu00310 Lysine degradation 0.2182508717 0.932795641
## set.size exp1
## mmu05410 Hypertrophic cardiomyopathy (HCM) 10 0.0001113742
## mmu05414 Dilated cardiomyopathy 11 0.0005946565
## mmu04810 Regulation of actin cytoskeleton 25 0.0066885871
## mmu04514 Cell adhesion molecules (CAMs) 11 0.0088502965
## mmu04145 Phagosome 11 0.0445257276
## mmu04510 Focal adhesion 25 0.0882811808
## mmu05206 MicroRNAs in cancer 22 0.1482244541
## mmu04120 Ubiquitin mediated proteolysis 12 0.1607398999
## mmu04151 PI3K-Akt signaling pathway 24 0.1820232294
## mmu00310 Lysine degradation 11 0.2182508717
#sel <- res$greater[, 'q.val'] < 0.01 & !is.na(res$greater[, 'q.val'])
#path.ids <- rownames(res$greater)[sel]
#sel.l <- res$less[, 'q.val'] < 0.01 & !is.na(res$less[,'q.val'])
#path.ids.l <- rownames(res$less)[sel.l]
#path.ids2 <- substr(c(path.ids, path.ids.l), 1, 8) #put greater and less together
path.ids2 <- LoadCachedObject(db, 'finalresults_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(path.ids2))
## [1] "mmu05410" "mmu05414"
#pv.out.list <- sapply(path.ids2, function(pid){ pathview( gene.data = exp.fc, pathway.id = pid, species = specie, out.suffix=out.suffix)})
Here starts the automatically generated code
BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt
,geneSet1:
TRUE
,geneSet2:
FALSE
,Project:
BMDC_analysis
,hsa:
FALSE
,mmu:
TRUE
,dme:
FALSE
,dre:
FALSE
,conversion:
TRUE
,conversion2:
FALSE
,conversion3:
FALSE
,n:
1
,
This R code has been run:
require(biomaRt)
require(gage)
require(pathview)
require(lattice)
geneSet1 <- TRUE
geneSet2 <- FALSE
cachedbname='Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt_TRUE_FALSE_gage_db'
db <- InitDb(db.name=cachedbname, db.path='cache')
fileName <- LoadCachedObject(db, 'filename_key')
Project <- LoadCachedObject(db, 'project_key')
geneSet1 <- LoadCachedObject(db, 'geneset1_key')
geneSet2 <- LoadCachedObject(db, 'geneset2_key')
hsa <- LoadCachedObject(db, 'hsa_key')
dme <- LoadCachedObject(db, 'dme_key')
mmu <- LoadCachedObject(db, 'mmu_key')
dre <- LoadCachedObject(db, 'dre_key')
conversion <- LoadCachedObject(db, 'conversion_key')
conversion2 <- LoadCachedObject(db, 'conversion2_key')
conversion3 <- LoadCachedObject(db, 'conversion3_key')
n <- LoadCachedObject(db, 'n_key')
res=NULL
print('Expression data selected: ')
## [1] "Expression data selected: "
print('/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt')
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt"
file.name=read.table('/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt', row.names=1, header=TRUE)
print('dimensions:')
## [1] "dimensions:"
print(dim(file.name))
## [1] 979 6
print(head(file.name))
## E2_mean UNTR_mean M D prob
## ENSMUSG00000002477 931.9589 1572.918 -0.7551052 640.9591 0.9811475
## ENSMUSG00000040957 312.1442 649.083 -1.0561903 336.9388 0.9732489
## ENSMUSG00000090523 1390.8650 2019.995 -0.5383691 629.1297 0.9647541
## ENSMUSG00000038418 952.2682 3287.633 -1.7876094 2335.3649 0.9967586
## ENSMUSG00000024346 904.5954 1433.102 -0.6637968 528.5067 0.9727273
## ENSMUSG00000014294 3013.9511 5375.044 -0.8346205 2361.0927 0.9904993
## ranking
## ENSMUSG00000002477 -640.9595
## ENSMUSG00000040957 -336.9404
## ENSMUSG00000090523 -629.1299
## ENSMUSG00000038418 -2335.3656
## ENSMUSG00000024346 -528.5071
## ENSMUSG00000014294 -2361.0929
kegg.gs = NULL
go.gs = NULL
if (geneSet1==TRUE){
if(hsa==TRUE){ks=kegg.gsets(species = 'hsa', id.type = 'entrez')}
if(mmu==TRUE){ks=kegg.gsets(species = 'mmu', id.type = 'entrez')}
if(dme==TRUE){ks=kegg.gsets(species = 'dme', id.type = 'entrez')}
kegg.gs=ks$kg.sets}
if (geneSet2==TRUE){ data(bods)
if(hsa==TRUE){row=subset(bods, bods[,3] == 'hsa')}
if(mmu==TRUE){row=subset(bods, bods[,3] == 'mmu')}
if(dme==TRUE){row=subset(bods, bods[,3] == 'dme')}
if(dre==TRUE){row=subset(bods, bods[,3] == 'dre')}
go=go.gsets(species = row[2], id.type = 'entrez')
go.gs=go$go.sets}
if(conversion==TRUE){ #ensembl gene ids to entrez genes
if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
if(mmu==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')}
if(dme==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')}
if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')}}
#if(conversion2==TRUE){ #gene names to entrez genes
#if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
# results <- getBM(attributes = c('hgnc_symbol','entrezgene'), mart=ensembl)}#to connect to a BioMart database
#if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('mgi_symbol','entrezgene') , mart=ensembl)} #to connect to a BioMart database
#if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('flybasename_gene','entrezgene'), mart=ensembl)} #to connect to a BioMart database
#if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('zfin_symbol','entrezgene'), mart=ensembl)} #to connect to a BioMart database
#file.name <- mol.sum(mol.data = file.name, id.map = results,sum.method = 'mean') }
#if(conversion3==TRUE){ # gencode names to entrez genes
#if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
#if(mmu==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')} #to connect to a BioMart database
#if(dme==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')} #to connect to a BioMartdatabase
#if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')} #to connect to a BioMart database
#newrownames = strsplit(rownames(file.name),'\.')
#nrownames = NULL
#for (i in 1:length(newrownames) ){nrownames[i] = newrownames[[i]][1]}
#rownames(file.name) = nrownames
#results <- getBM(attributes = c('ensembl_gene_id','entrezgene'), mart=ensembl)
#file.name <- mol.sum(mol.data = file.name, id.map = results,sum.method = 'mean') }
file.name <- LoadCachedObject(db, 'filenameconverted_key')
print('Expression data modified:')
## [1] "Expression data modified:"
print(dim(file.name))
## [1] 936 6
print(head(file.name))
## E2_mean UNTR_mean M D prob ranking
## 11409 1814.2001 2492.903 -0.4584929 678.7025 0.9561103 -678.7027
## 11475 306.2560 1374.974 -2.1665939 1068.7176 0.9949702 -1068.7197
## 11520 45375.6035 89520.067 -0.9802943 44144.4632 0.9946349 -44144.4633
## 11551 168.8537 402.214 -1.2521896 233.3603 0.9556259 -233.3637
## 11568 126.0248 1687.441 -3.7430576 1561.4163 0.9975037 -1561.4208
## 11629 1748.0061 3455.473 -0.9831731 1707.4670 0.9925112 -1707.4673
out.suffix=NULL
fc=NULL
exp.fc <- LoadCachedObject(db, 'expfc_key')
out.suffix <- LoadCachedObject(db, 'outsuffix_key')
#if (colnames(file.name)[1] == 'log2FoldChange') {fc=file.name[,'log2FoldChange']
#names(fc)=rownames(file.name)
#sum(is.infinite(fc)) #to manage the problem of inf
#fc[fc>10]=10
#fc[fc< -10]=-10
#out.suffix='deseq' }
#if(colnames(file.name)[1] == 'logFC'){ fc=file.name[,'logFC']
#names(fc)=rownames(file.name)
#out.suffix='edger'}
#if(colnames(file.name)[3] == 'M'){ fc=file.name[,'M']
#names(fc)=rownames(file.name)
#sum(is.infinite(fc)) #to manage the problem of inf
#fc[fc>10]=10
#fc[fc< -10]=-10
#out.suffix='noiseq'}
#exp.fc=fc
#if (geneSet1==TRUE){res <- gage(exp.fc, gsets = kegg.gs, ref = NULL, samp = NULL, same.dir = FALSE, saaTest = gs.zTest, use.fold = FALSE)
#}else{res <- gage(exp.fc, gsets = go.gs , ref = NULL, samp = NULL, same.dir = FALSE, saaTest = gs.zTest, use.fold = FALSE)}
res <- LoadCachedObject(db, 'res_key')
print('First lines of results:')
## [1] "First lines of results:"
print(head(res[[1]],10))
## p.geomean stat.mean
## mmu04974 Protein digestion and absorption 4.514822e-23 9.8222596
## mmu04512 ECM-receptor interaction 1.334094e-16 8.1874501
## mmu04510 Focal adhesion 1.013753e-15 7.9396512
## mmu04151 PI3K-Akt signaling pathway 1.623934e-08 5.5275213
## mmu05200 Pathways in cancer 3.881611e-03 2.6621979
## mmu04060 Cytokine-cytokine receptor interaction 1.781937e-02 2.1010253
## mmu05160 Hepatitis C 1.055064e-01 1.2507856
## mmu04066 HIF-1 signaling pathway 1.524016e-01 1.0261874
## mmu05150 Staphylococcus aureus infection 3.239795e-01 0.4565994
## mmu05164 Influenza A 3.659037e-01 0.3427223
## p.val q.val
## mmu04974 Protein digestion and absorption 4.514822e-23 1.760781e-21
## mmu04512 ECM-receptor interaction 1.334094e-16 2.601483e-15
## mmu04510 Focal adhesion 1.013753e-15 1.317879e-14
## mmu04151 PI3K-Akt signaling pathway 1.623934e-08 1.583336e-07
## mmu05200 Pathways in cancer 3.881611e-03 3.027656e-02
## mmu04060 Cytokine-cytokine receptor interaction 1.781937e-02 1.158259e-01
## mmu05160 Hepatitis C 1.055064e-01 5.878211e-01
## mmu04066 HIF-1 signaling pathway 1.524016e-01 7.429579e-01
## mmu05150 Staphylococcus aureus infection 3.239795e-01 9.998662e-01
## mmu05164 Influenza A 3.659037e-01 9.998662e-01
## set.size exp1
## mmu04974 Protein digestion and absorption 13 4.514822e-23
## mmu04512 ECM-receptor interaction 11 1.334094e-16
## mmu04510 Focal adhesion 13 1.013753e-15
## mmu04151 PI3K-Akt signaling pathway 21 1.623934e-08
## mmu05200 Pathways in cancer 20 3.881611e-03
## mmu04060 Cytokine-cytokine receptor interaction 15 1.781937e-02
## mmu05160 Hepatitis C 13 1.055064e-01
## mmu04066 HIF-1 signaling pathway 12 1.524016e-01
## mmu05150 Staphylococcus aureus infection 10 3.239795e-01
## mmu05164 Influenza A 13 3.659037e-01
#sel <- res$greater[, 'q.val'] < 0.01 & !is.na(res$greater[, 'q.val'])
#path.ids <- rownames(res$greater)[sel]
#sel.l <- res$less[, 'q.val'] < 0.01 & !is.na(res$less[,'q.val'])
#path.ids.l <- rownames(res$less)[sel.l]
#path.ids2 <- substr(c(path.ids, path.ids.l), 1, 8) #put greater and less together
path.ids2 <- LoadCachedObject(db, 'finalresults_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(path.ids2))
## [1] "mmu04974" "mmu04512" "mmu04510" "mmu04151" "mmu05200"
#pv.out.list <- sapply(path.ids2, function(pid){ pathview( gene.data = exp.fc, pathway.id = pid, species = specie, out.suffix=out.suffix)})
Here starts the automatically generated code
BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt
,geneSet1:
FALSE
,geneSet2:
TRUE
,Project:
BMDC_analysis
,hsa:
FALSE
,mmu:
TRUE
,dme:
FALSE
,dre:
FALSE
,conversion:
TRUE
,conversion2:
FALSE
,conversion3:
FALSE
,n:
1
,
This R code has been run:
require(biomaRt)
require(gage)
require(pathview)
require(lattice)
geneSet1 <- FALSE
geneSet2 <- TRUE
cachedbname='Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt_FALSE_TRUE_gage_db'
db <- InitDb(db.name=cachedbname, db.path='cache')
fileName <- LoadCachedObject(db, 'filename_key')
Project <- LoadCachedObject(db, 'project_key')
geneSet1 <- LoadCachedObject(db, 'geneset1_key')
geneSet2 <- LoadCachedObject(db, 'geneset2_key')
hsa <- LoadCachedObject(db, 'hsa_key')
dme <- LoadCachedObject(db, 'dme_key')
mmu <- LoadCachedObject(db, 'mmu_key')
dre <- LoadCachedObject(db, 'dre_key')
conversion <- LoadCachedObject(db, 'conversion_key')
conversion2 <- LoadCachedObject(db, 'conversion2_key')
conversion3 <- LoadCachedObject(db, 'conversion3_key')
n <- LoadCachedObject(db, 'n_key')
res=NULL
print('Expression data selected: ')
## [1] "Expression data selected: "
print('/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt')
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt"
file.name=read.table('/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_DOWN_genes_NOISeq.txt', row.names=1, header=TRUE)
print('dimensions:')
## [1] "dimensions:"
print(dim(file.name))
## [1] 979 6
print(head(file.name))
## E2_mean UNTR_mean M D prob
## ENSMUSG00000002477 931.9589 1572.918 -0.7551052 640.9591 0.9811475
## ENSMUSG00000040957 312.1442 649.083 -1.0561903 336.9388 0.9732489
## ENSMUSG00000090523 1390.8650 2019.995 -0.5383691 629.1297 0.9647541
## ENSMUSG00000038418 952.2682 3287.633 -1.7876094 2335.3649 0.9967586
## ENSMUSG00000024346 904.5954 1433.102 -0.6637968 528.5067 0.9727273
## ENSMUSG00000014294 3013.9511 5375.044 -0.8346205 2361.0927 0.9904993
## ranking
## ENSMUSG00000002477 -640.9595
## ENSMUSG00000040957 -336.9404
## ENSMUSG00000090523 -629.1299
## ENSMUSG00000038418 -2335.3656
## ENSMUSG00000024346 -528.5071
## ENSMUSG00000014294 -2361.0929
kegg.gs = NULL
go.gs = NULL
if (geneSet1==TRUE){
if(hsa==TRUE){ks=kegg.gsets(species = 'hsa', id.type = 'entrez')}
if(mmu==TRUE){ks=kegg.gsets(species = 'mmu', id.type = 'entrez')}
if(dme==TRUE){ks=kegg.gsets(species = 'dme', id.type = 'entrez')}
kegg.gs=ks$kg.sets}
if (geneSet2==TRUE){ data(bods)
if(hsa==TRUE){row=subset(bods, bods[,3] == 'hsa')}
if(mmu==TRUE){row=subset(bods, bods[,3] == 'mmu')}
if(dme==TRUE){row=subset(bods, bods[,3] == 'dme')}
if(dre==TRUE){row=subset(bods, bods[,3] == 'dre')}
go=go.gsets(species = row[2], id.type = 'entrez')
go.gs=go$go.sets}
## Gene ID type for 'mouse' is: 'EG'
if(conversion==TRUE){ #ensembl gene ids to entrez genes
if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
if(mmu==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')}
if(dme==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')}
if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')}}
#if(conversion2==TRUE){ #gene names to entrez genes
#if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
# results <- getBM(attributes = c('hgnc_symbol','entrezgene'), mart=ensembl)}#to connect to a BioMart database
#if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('mgi_symbol','entrezgene') , mart=ensembl)} #to connect to a BioMart database
#if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('flybasename_gene','entrezgene'), mart=ensembl)} #to connect to a BioMart database
#if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('zfin_symbol','entrezgene'), mart=ensembl)} #to connect to a BioMart database
#file.name <- mol.sum(mol.data = file.name, id.map = results,sum.method = 'mean') }
#if(conversion3==TRUE){ # gencode names to entrez genes
#if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
#if(mmu==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')} #to connect to a BioMart database
#if(dme==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')} #to connect to a BioMartdatabase
#if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')} #to connect to a BioMart database
#newrownames = strsplit(rownames(file.name),'\.')
#nrownames = NULL
#for (i in 1:length(newrownames) ){nrownames[i] = newrownames[[i]][1]}
#rownames(file.name) = nrownames
#results <- getBM(attributes = c('ensembl_gene_id','entrezgene'), mart=ensembl)
#file.name <- mol.sum(mol.data = file.name, id.map = results,sum.method = 'mean') }
file.name <- LoadCachedObject(db, 'filenameconverted_key')
print('Expression data modified:')
## [1] "Expression data modified:"
print(dim(file.name))
## [1] 936 6
print(head(file.name))
## E2_mean UNTR_mean M D prob ranking
## 11409 1814.2001 2492.903 -0.4584929 678.7025 0.9561103 -678.7027
## 11475 306.2560 1374.974 -2.1665939 1068.7176 0.9949702 -1068.7197
## 11520 45375.6035 89520.067 -0.9802943 44144.4632 0.9946349 -44144.4633
## 11551 168.8537 402.214 -1.2521896 233.3603 0.9556259 -233.3637
## 11568 126.0248 1687.441 -3.7430576 1561.4163 0.9975037 -1561.4208
## 11629 1748.0061 3455.473 -0.9831731 1707.4670 0.9925112 -1707.4673
out.suffix=NULL
fc=NULL
exp.fc <- LoadCachedObject(db, 'expfc_key')
out.suffix <- LoadCachedObject(db, 'outsuffix_key')
#if (colnames(file.name)[1] == 'log2FoldChange') {fc=file.name[,'log2FoldChange']
#names(fc)=rownames(file.name)
#sum(is.infinite(fc)) #to manage the problem of inf
#fc[fc>10]=10
#fc[fc< -10]=-10
#out.suffix='deseq' }
#if(colnames(file.name)[1] == 'logFC'){ fc=file.name[,'logFC']
#names(fc)=rownames(file.name)
#out.suffix='edger'}
#if(colnames(file.name)[3] == 'M'){ fc=file.name[,'M']
#names(fc)=rownames(file.name)
#sum(is.infinite(fc)) #to manage the problem of inf
#fc[fc>10]=10
#fc[fc< -10]=-10
#out.suffix='noiseq'}
#exp.fc=fc
#if (geneSet1==TRUE){res <- gage(exp.fc, gsets = kegg.gs, ref = NULL, samp = NULL, same.dir = FALSE, saaTest = gs.zTest, use.fold = FALSE)
#}else{res <- gage(exp.fc, gsets = go.gs , ref = NULL, samp = NULL, same.dir = FALSE, saaTest = gs.zTest, use.fold = FALSE)}
res <- LoadCachedObject(db, 'res_key')
print('First lines of results:')
## [1] "First lines of results:"
print(head(res[[1]],10))
## p.geomean stat.mean
## GO:0031012 extracellular matrix 2.106203e-53 15.338748
## GO:0005578 proteinaceous extracellular matrix 7.661242e-50 14.796973
## GO:0044420 extracellular matrix component 1.274277e-30 11.443021
## GO:0005615 extracellular space 2.232315e-30 11.394288
## GO:0030198 extracellular matrix organization 9.172815e-27 10.645268
## GO:0043062 extracellular structure organization 9.172815e-27 10.645268
## GO:0005581 collagen trimer 2.927857e-25 10.317787
## GO:0001568 blood vessel development 1.131038e-23 9.960812
## GO:0001944 vasculature development 1.203891e-23 9.954605
## GO:0005539 glycosaminoglycan binding 5.232807e-23 9.807374
## p.val q.val
## GO:0031012 extracellular matrix 2.106203e-53 2.834949e-50
## GO:0005578 proteinaceous extracellular matrix 7.661242e-50 5.156016e-47
## GO:0044420 extracellular matrix component 1.274277e-30 5.717254e-28
## GO:0005615 extracellular space 2.232315e-30 7.511739e-28
## GO:0030198 extracellular matrix organization 9.172815e-27 2.057768e-24
## GO:0043062 extracellular structure organization 9.172815e-27 2.057768e-24
## GO:0005581 collagen trimer 2.927857e-25 5.629851e-23
## GO:0001568 blood vessel development 1.131038e-23 1.800486e-21
## GO:0001944 vasculature development 1.203891e-23 1.800486e-21
## GO:0005539 glycosaminoglycan binding 5.232807e-23 7.043359e-21
## set.size exp1
## GO:0031012 extracellular matrix 64 2.106203e-53
## GO:0005578 proteinaceous extracellular matrix 46 7.661242e-50
## GO:0044420 extracellular matrix component 26 1.274277e-30
## GO:0005615 extracellular space 108 2.232315e-30
## GO:0030198 extracellular matrix organization 21 9.172815e-27
## GO:0043062 extracellular structure organization 21 9.172815e-27
## GO:0005581 collagen trimer 20 2.927857e-25
## GO:0001568 blood vessel development 38 1.131038e-23
## GO:0001944 vasculature development 40 1.203891e-23
## GO:0005539 glycosaminoglycan binding 22 5.232807e-23
#sel <- res$greater[, 'q.val'] < 0.01 & !is.na(res$greater[, 'q.val'])
#path.ids <- rownames(res$greater)[sel]
#sel.l <- res$less[, 'q.val'] < 0.01 & !is.na(res$less[,'q.val'])
#path.ids.l <- rownames(res$less)[sel.l]
#path.ids2 <- substr(c(path.ids, path.ids.l), 1, 8) #put greater and less together
path.ids2 <- LoadCachedObject(db, 'finalresults_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(path.ids2))
## [1] "GO:00310" "GO:00055" "GO:00444" "GO:00056" "GO:00301" "GO:00430"
#pv.out.list <- sapply(path.ids2, function(pid){ pathview( gene.data = exp.fc, pathway.id = pid, species = specie, out.suffix=out.suffix)})
Here starts the automatically generated code
BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt
,geneSet1:
FALSE
,geneSet2:
TRUE
,Project:
BMDC_analysis
,hsa:
FALSE
,mmu:
TRUE
,dme:
FALSE
,dre:
FALSE
,conversion:
TRUE
,conversion2:
FALSE
,conversion3:
FALSE
,n:
1
,
This R code has been run:
require(biomaRt)
require(gage)
require(pathview)
require(lattice)
geneSet1 <- FALSE
geneSet2 <- TRUE
cachedbname='Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt_FALSE_TRUE_gage_db'
db <- InitDb(db.name=cachedbname, db.path='cache')
fileName <- LoadCachedObject(db, 'filename_key')
Project <- LoadCachedObject(db, 'project_key')
geneSet1 <- LoadCachedObject(db, 'geneset1_key')
geneSet2 <- LoadCachedObject(db, 'geneset2_key')
hsa <- LoadCachedObject(db, 'hsa_key')
dme <- LoadCachedObject(db, 'dme_key')
mmu <- LoadCachedObject(db, 'mmu_key')
dre <- LoadCachedObject(db, 'dre_key')
conversion <- LoadCachedObject(db, 'conversion_key')
conversion2 <- LoadCachedObject(db, 'conversion2_key')
conversion3 <- LoadCachedObject(db, 'conversion3_key')
n <- LoadCachedObject(db, 'n_key')
res=NULL
print('Expression data selected: ')
## [1] "Expression data selected: "
print('/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt')
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt"
file.name=read.table('/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq.txt', row.names=1, header=TRUE)
print('dimensions:')
## [1] "dimensions:"
print(dim(file.name))
## [1] 833 6
print(head(file.name))
## E2_mean UNTR_mean M D prob
## ENSMUSG00000024236 3491.317 2408.5939 0.5355801 1082.7228 0.9695231
## ENSMUSG00000006740 5179.638 3729.4665 0.4738820 1450.1715 0.9626677
## ENSMUSG00000024290 3519.108 2433.1265 0.5323986 1085.9818 0.9687034
## ENSMUSG00000024294 5623.267 3752.3939 0.5835973 1870.8733 0.9753353
## ENSMUSG00000033382 3250.364 2356.2755 0.4640931 894.0885 0.9585320
## ENSMUSG00000041915 1016.327 589.2449 0.7864249 427.0818 0.9752981
## ranking
## ENSMUSG00000024236 1082.7229
## ENSMUSG00000006740 1450.1715
## ENSMUSG00000024290 1085.9820
## ENSMUSG00000024294 1870.8734
## ENSMUSG00000033382 894.0886
## ENSMUSG00000041915 427.0825
kegg.gs = NULL
go.gs = NULL
if (geneSet1==TRUE){
if(hsa==TRUE){ks=kegg.gsets(species = 'hsa', id.type = 'entrez')}
if(mmu==TRUE){ks=kegg.gsets(species = 'mmu', id.type = 'entrez')}
if(dme==TRUE){ks=kegg.gsets(species = 'dme', id.type = 'entrez')}
kegg.gs=ks$kg.sets}
if (geneSet2==TRUE){ data(bods)
if(hsa==TRUE){row=subset(bods, bods[,3] == 'hsa')}
if(mmu==TRUE){row=subset(bods, bods[,3] == 'mmu')}
if(dme==TRUE){row=subset(bods, bods[,3] == 'dme')}
if(dre==TRUE){row=subset(bods, bods[,3] == 'dre')}
go=go.gsets(species = row[2], id.type = 'entrez')
go.gs=go$go.sets}
## Gene ID type for 'mouse' is: 'EG'
if(conversion==TRUE){ #ensembl gene ids to entrez genes
if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
if(mmu==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')}
if(dme==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')}
if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')}}
#if(conversion2==TRUE){ #gene names to entrez genes
#if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
# results <- getBM(attributes = c('hgnc_symbol','entrezgene'), mart=ensembl)}#to connect to a BioMart database
#if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('mgi_symbol','entrezgene') , mart=ensembl)} #to connect to a BioMart database
#if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('flybasename_gene','entrezgene'), mart=ensembl)} #to connect to a BioMart database
#if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('zfin_symbol','entrezgene'), mart=ensembl)} #to connect to a BioMart database
#file.name <- mol.sum(mol.data = file.name, id.map = results,sum.method = 'mean') }
#if(conversion3==TRUE){ # gencode names to entrez genes
#if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')}
#if(mmu==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')} #to connect to a BioMart database
#if(dme==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')} #to connect to a BioMartdatabase
#if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')} #to connect to a BioMart database
#newrownames = strsplit(rownames(file.name),'\.')
#nrownames = NULL
#for (i in 1:length(newrownames) ){nrownames[i] = newrownames[[i]][1]}
#rownames(file.name) = nrownames
#results <- getBM(attributes = c('ensembl_gene_id','entrezgene'), mart=ensembl)
#file.name <- mol.sum(mol.data = file.name, id.map = results,sum.method = 'mean') }
file.name <- LoadCachedObject(db, 'filenameconverted_key')
print('Expression data modified:')
## [1] "Expression data modified:"
print(dim(file.name))
## [1] 805 6
print(head(file.name))
## E2_mean UNTR_mean M D prob ranking
## 11305 2251.808 1587.416 0.5044036 664.3920 0.9614754 664.3922
## 11352 1756.638 1154.060 0.6060989 602.5782 0.9710134 602.5785
## 11426 13403.227 7186.994 0.8991199 6216.2327 0.9929955 6216.2327
## 11433 8977.105 5383.496 0.7377070 3593.6095 0.9877049 3593.6096
## 11479 1613.703 1149.163 0.4897913 464.5398 0.9542474 464.5400
## 11492 5231.593 3654.661 0.5175125 1576.9314 0.9691505 1576.9315
out.suffix=NULL
fc=NULL
exp.fc <- LoadCachedObject(db, 'expfc_key')
out.suffix <- LoadCachedObject(db, 'outsuffix_key')
#if (colnames(file.name)[1] == 'log2FoldChange') {fc=file.name[,'log2FoldChange']
#names(fc)=rownames(file.name)
#sum(is.infinite(fc)) #to manage the problem of inf
#fc[fc>10]=10
#fc[fc< -10]=-10
#out.suffix='deseq' }
#if(colnames(file.name)[1] == 'logFC'){ fc=file.name[,'logFC']
#names(fc)=rownames(file.name)
#out.suffix='edger'}
#if(colnames(file.name)[3] == 'M'){ fc=file.name[,'M']
#names(fc)=rownames(file.name)
#sum(is.infinite(fc)) #to manage the problem of inf
#fc[fc>10]=10
#fc[fc< -10]=-10
#out.suffix='noiseq'}
#exp.fc=fc
#if (geneSet1==TRUE){res <- gage(exp.fc, gsets = kegg.gs, ref = NULL, samp = NULL, same.dir = FALSE, saaTest = gs.zTest, use.fold = FALSE)
#}else{res <- gage(exp.fc, gsets = go.gs , ref = NULL, samp = NULL, same.dir = FALSE, saaTest = gs.zTest, use.fold = FALSE)}
res <- LoadCachedObject(db, 'res_key')
print('First lines of results:')
## [1] "First lines of results:"
print(head(res[[1]],10))
## p.geomean stat.mean
## GO:0043025 neuronal cell body 1.485400e-05 4.175693
## GO:1901214 regulation of neuron death 2.622810e-05 4.044405
## GO:0070997 neuron death 6.217046e-05 3.837406
## GO:0044297 cell body 1.211058e-04 3.670357
## GO:0043523 regulation of neuron apoptotic process 2.489943e-04 3.481836
## GO:0043235 receptor complex 4.586850e-04 3.314714
## GO:0060326 cell chemotaxis 5.378943e-04 3.269918
## GO:0051402 neuron apoptotic process 6.272107e-04 3.226208
## GO:0030246 carbohydrate binding 1.156817e-03 3.046707
## GO:0048545 response to steroid hormone 1.177995e-03 3.041249
## p.val q.val
## GO:0043025 neuronal cell body 1.485400e-05 0.01864818
## GO:1901214 regulation of neuron death 2.622810e-05 0.01864818
## GO:0070997 neuron death 6.217046e-05 0.02946880
## GO:0044297 cell body 1.211058e-04 0.04305310
## GO:0043523 regulation of neuron apoptotic process 2.489943e-04 0.07081398
## GO:0043235 receptor complex 4.586850e-04 0.10870835
## GO:0060326 cell chemotaxis 5.378943e-04 0.10926938
## GO:0051402 neuron apoptotic process 6.272107e-04 0.11148670
## GO:0030246 carbohydrate binding 1.156817e-03 0.16751084
## GO:0048545 response to steroid hormone 1.177995e-03 0.16751084
## set.size exp1
## GO:0043025 neuronal cell body 26 1.485400e-05
## GO:1901214 regulation of neuron death 19 2.622810e-05
## GO:0070997 neuron death 21 6.217046e-05
## GO:0044297 cell body 29 1.211058e-04
## GO:0043523 regulation of neuron apoptotic process 16 2.489943e-04
## GO:0043235 receptor complex 21 4.586850e-04
## GO:0060326 cell chemotaxis 11 5.378943e-04
## GO:0051402 neuron apoptotic process 17 6.272107e-04
## GO:0030246 carbohydrate binding 13 1.156817e-03
## GO:0048545 response to steroid hormone 15 1.177995e-03
#sel <- res$greater[, 'q.val'] < 0.01 & !is.na(res$greater[, 'q.val'])
#path.ids <- rownames(res$greater)[sel]
#sel.l <- res$less[, 'q.val'] < 0.01 & !is.na(res$less[,'q.val'])
#path.ids.l <- rownames(res$less)[sel.l]
#path.ids2 <- substr(c(path.ids, path.ids.l), 1, 8) #put greater and less together
path.ids2 <- LoadCachedObject(db, 'finalresults_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(path.ids2))
## [1] "GO:00430" "GO:19012" "GO:00709" "GO:00442"
#pv.out.list <- sapply(path.ids2, function(pid){ pathview( gene.data = exp.fc, pathway.id = pid, species = specie, out.suffix=out.suffix)})
To work with DAVID, it is necessary just a gene list. The following gene lists have been automatically produced during the Result Comparison step. In order to help the lecturer, the same order described in the paper has been mainteined. The followint reported Pathway analysis has been performed on KEGG database, while the selected Gene Ontology categories are GOTERM_BP_ALL and GOTERM_MF_ALL.
Here starts the automatically generated code
2016-06-16 19:03:59 and the DAVID*_result*.csv files has been saved in the BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/DEC_UP_E2_UP_genes_in_intersection.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list_1
, db.selected:
KEGG_PATHWAY
, analysis.type:
Pathway
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
The list of called functions:
GetSpecieCode
## function (specie)
## {
## switch(specie, HUMAN = {
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## }, MOUSE = {
## dataset = "mmusculus_gene_ensembl"
## attribute = "mgi_symbol"
## }, DROSOPHILA = {
## dataset = "dmelanogaster_gene_ensembl"
## attribute = "bdgp_symbol"
## }, ZEBRAFISH = {
## dataset = "drerio_gene_ensembl"
## attribute = "zfin_symbol"
## }, {
## print("WARNING: no species detected! Using, HUMAN!")
## dialog <- MyDialog(window, "warning", message = "no species detected! Using, HUMAN!",
## title = "WARNING")
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## })
## return(list(dataset = dataset, attribute = attribute))
## }
## <environment: namespace:RNASeqGUI>
ConvertList
## function (id.list, map)
## {
## res.map <- apply(id.list, 1, function(x) {
## which(map[, 1] %in% x)
## })
## print(head(res.map))
## print(length(res.map))
## print(dim(id.list)[1])
## if (length(res.map) == dim(id.list)[1]) {
## id.list.n <- lapply(res.map, function(item) {
## if (length(item) > 0) {
## map[item[1], 2]
## }
## else {
## map[item, 2]
## }
## })
## }
## else {
## if (length(res.map) == 0) {
## print("problem res.map")
## }
## else if (length(id.list) == 0) {
## print("problem id.list")
## }
## }
## return(unlist(id.list.n))
## }
## <environment: namespace:RNASeqGUI>
DavidConnect
## function (user.mail = "rnaseqgui@na.iac.cnr.it")
## {
## if (!exists("david")) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## else {
## if (!is.connected(david)) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## }
## if (getTimeOut(david) == 30000) {
## setTimeOut(david, 5e+05)
## }
## if (is.null(getHttpProtocolVersion(david))) {
## setHttpProtocolVersion(david, "HTTP/1.0")
## }
## return(david)
## }
## <environment: namespace:RNASeqGUI>
DavidAnalysis
## function (main.window = NULL, file.name, gene.list.position,
## gene.identifier, list.type, list.name, out.file.name, db.selected,
## analysis.type, Project, specie, filter.list)
## {
## require("RDAVIDWebService")
## require("biomaRt")
## if (Sys.info()[[1]] == "Windows") {
## sys.sep = "\\"
## }
## else {
## sys.sep = "/"
## }
## sep.pos <- gregexpr(pattern = sys.sep, file.name, fixed = F)[[1]]
## out.file.name <- substring(file.name, sep.pos[length(sep.pos)] +
## 1)
## david.path <- file.path("RNASeqGUI_Projects", Project, "Results",
## "DAVID")
## david.db.path <- file.path(david.path, paste(db.selected,
## collapse = "_", sep = ""))
## dir.create(david.path, recursive = TRUE)
## if (analysis.type == "Pathway") {
## cat("Performing pathway analysis on ", db.selected, "...\n")
## this.name <- paste0(out.file.name, "_DAVID_Pathway_",
## db.selected)
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## if (length(grep("ALL", db.selected)) != 0) {
## cat("Performing ALL GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_ALL_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## cat("Performing FAT GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_FAT_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_DAVID_FAT_GO_results.txt")
## }
## }
## dbname <- paste0("david_", this.name, "_db")
## db <- InitDb(db.name = dbname, db.path = file.path("RNASeqGUI_Projects",
## Project, "Logs", "cache"))
## SaveInCache(db, file.name, "filename_key")
## SaveInCache(db, Project, "project_key")
## SaveInCache(db, gene.list.position, "genelistposition_key")
## SaveInCache(db, gene.identifier, "geneidentifier_key")
## SaveInCache(db, list.type, "listtype_key")
## SaveInCache(db, list.name, "listname_key")
## SaveInCache(db, db.selected, "dbselected_key")
## SaveInCache(db, analysis.type, "analysistype_key")
## SaveInCache(db, out.file.name, "outfilename_key")
## SaveInCache(db, specie, "specie_key")
## id.list <- read.table(file = file.name, header = TRUE, as.is = TRUE)
## id.list <- id.list[, gene.list.position, drop = TRUE]
## if (gene.identifier == "GENCODE") {
## id.list <- unlist(lapply(id.list, function(x) {
## substring(x, 0, regexpr(pattern = ".", x, fixed = T)[1] -
## 1)
## }))
## gene.identifier <- "ENSEMBL_GENE_ID"
## }
## if (gene.identifier == "GENE_SYMBOL") {
## if (specie != "") {
## print("converting gene_symbol to ensembl_gene_id ... ")
## specie.list <- GetSpecieCode(specie)
## print(specie.list$dataset)
## ensembl <- useMart("ENSEMBL_MART_ENSEMBL", host = "www.ensembl.org",
## dataset = specie.list$dataset)
## ensembl.map <- getBM(attributes = c("external_gene_name",
## "ensembl_gene_id"), mart = ensembl)
## id.list <- ConvertList(id.list, ensembl.map)
## gene.identifier <- "ENSEMBL_GENE_ID"
## print("done!")
## }
## else {
## message("ERROR: empty Specie")
## }
## }
## print("check if list is too short")
## if (length(id.list) > 3000) {
## MyDialog(parent.w = main.window, type.d = "warning",
## message = paste0("You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"),
## title = "WARNING")
## message(paste0("WARNING: You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"))
## id.list <- id.list[1:3000]
## }
## else {
## MyDialog(parent.w = main.window, type.d = "info", message = paste0("You submitted ",
## length(id.list), " genes!"), title = "INFORMATION")
## print(paste0("You submitted ", length(id.list), " genes!"))
## }
## print(head(id.list))
## SaveInCache(db, id.list, "idlist_key")
## print("Querying DAVID...")
## w.wind <- WaitingWindow(message = "Please wait while querying DAVID",
## parent.w = main.window)
## Sys.sleep(1)
## david <- DavidConnect()
## if (is.connected(david)) {
## result <- addList(david, id.list, idType = gene.identifier,
## listName = list.name, listType = list.type)
## setAnnotationCategories(david, db.selected)
## results.final <- getFunctionalAnnotationChart(david)
## w.wind$destroy()
## print("done!")
## if (dim(results.final)[1] != 0) {
## if (filter.list$flag) {
## results.final <- results.final[results.final[,
## filter.list$col.name] < filter.list$thr, ]
## }
## SaveInCache(db, filter.list, "filterlist_key")
## SaveInCache(db, results.final, "resultsfinal_key")
## write.table(results.final, file = out.file.name,
## quote = FALSE, row.names = FALSE, sep = "\t")
## cat("File ", out.file.name, " written on disk!\n")
## print(david.db.path)
## input.file.name <- substring(file.name, max(gregexpr("/",
## file.name)[[1]]) + 1)
## input.file.name <- gsub(".txt", "", input.file.name)
## input.file.name <- gsub(" ", "_", input.file.name)
## SavePathwaysList(results.final, david.db.path, just.file.name = input.file.name)
## }
## else {
## results.final <- data.frame()
## SaveInCache(db, results.final, "resultsfinal_key")
## cat("David produced no Results on ", db.selected,
## "\n")
## }
## }
## else {
## w.wind$destroy()
## message("ERROR: DAVID disconnected!")
## }
## PrintDavidReport(db, dbname)
## return(results.final)
## }
## <environment: namespace:RNASeqGUI>
This R code has been run:
print(getwd())
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Logs"
db <- InitDb(db.name='david_DEC_UP_E2_UP_genes_in_intersection.txt_DAVID_Pathway_KEGG_PATHWAY_db' , db.path='cache')
#results.data.frame <- DavidAnalysis(file.name, gene.list.position, gene.identifier, list.type, list.name, out.file.name, db.selected, analysis.type, Project)
results.data.frame <- LoadCachedObject(db, 'resultsfinal_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(results.data.frame))
## [1] Category Term Count X.
## [5] PValue Genes List.Total Pop.Hits
## [9] Pop.Total Fold.Enrichment Bonferroni Benjamini
## [13] FDR
## <0 rows> (or 0-length row.names)
Here starts the automatically generated code
2016-06-16 19:23:54 and the DAVID*_result*.csv files has been saved in the BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/DEC_UP_E2_UP_genes_in_intersection.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list_1
, db.selected:
GOTERM_MF_ALL
, analysis.type:
GO
, specie:
, filter:
FALSE
, filter.column:
No
, filter.threshold:
Inf
, Project:
BMDC_analysis
You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/DEC_UP_E2_UP_genes_in_intersection.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list_1
, db.selected:
GOTERM_BP_ALL
, analysis.type:
GO
, specie:
, filter:
FALSE
, filter.column:
No
, filter.threshold:
Inf
, Project:
BMDC_analysis
The list of called functions:
GetSpecieCode
## function (specie)
## {
## switch(specie, HUMAN = {
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## }, MOUSE = {
## dataset = "mmusculus_gene_ensembl"
## attribute = "mgi_symbol"
## }, DROSOPHILA = {
## dataset = "dmelanogaster_gene_ensembl"
## attribute = "bdgp_symbol"
## }, ZEBRAFISH = {
## dataset = "drerio_gene_ensembl"
## attribute = "zfin_symbol"
## }, {
## print("WARNING: no species detected! Using, HUMAN!")
## dialog <- MyDialog(window, "warning", message = "no species detected! Using, HUMAN!",
## title = "WARNING")
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## })
## return(list(dataset = dataset, attribute = attribute))
## }
## <environment: namespace:RNASeqGUI>
ConvertList
## function (id.list, map)
## {
## res.map <- apply(id.list, 1, function(x) {
## which(map[, 1] %in% x)
## })
## print(head(res.map))
## print(length(res.map))
## print(dim(id.list)[1])
## if (length(res.map) == dim(id.list)[1]) {
## id.list.n <- lapply(res.map, function(item) {
## if (length(item) > 0) {
## map[item[1], 2]
## }
## else {
## map[item, 2]
## }
## })
## }
## else {
## if (length(res.map) == 0) {
## print("problem res.map")
## }
## else if (length(id.list) == 0) {
## print("problem id.list")
## }
## }
## return(unlist(id.list.n))
## }
## <environment: namespace:RNASeqGUI>
DavidConnect
## function (user.mail = "rnaseqgui@na.iac.cnr.it")
## {
## if (!exists("david")) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## else {
## if (!is.connected(david)) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## }
## if (getTimeOut(david) == 30000) {
## setTimeOut(david, 5e+05)
## }
## if (is.null(getHttpProtocolVersion(david))) {
## setHttpProtocolVersion(david, "HTTP/1.0")
## }
## return(david)
## }
## <environment: namespace:RNASeqGUI>
DavidAnalysis
## function (main.window = NULL, file.name, gene.list.position,
## gene.identifier, list.type, list.name, out.file.name, db.selected,
## analysis.type, Project, specie, filter.list)
## {
## require("RDAVIDWebService")
## require("biomaRt")
## if (Sys.info()[[1]] == "Windows") {
## sys.sep = "\\"
## }
## else {
## sys.sep = "/"
## }
## sep.pos <- gregexpr(pattern = sys.sep, file.name, fixed = F)[[1]]
## out.file.name <- substring(file.name, sep.pos[length(sep.pos)] +
## 1)
## david.path <- file.path("RNASeqGUI_Projects", Project, "Results",
## "DAVID")
## david.db.path <- file.path(david.path, paste(db.selected,
## collapse = "_", sep = ""))
## dir.create(david.path, recursive = TRUE)
## if (analysis.type == "Pathway") {
## cat("Performing pathway analysis on ", db.selected, "...\n")
## this.name <- paste0(out.file.name, "_DAVID_Pathway_",
## db.selected)
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## if (length(grep("ALL", db.selected)) != 0) {
## cat("Performing ALL GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_ALL_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## cat("Performing FAT GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_FAT_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_DAVID_FAT_GO_results.txt")
## }
## }
## dbname <- paste0("david_", this.name, "_db")
## db <- InitDb(db.name = dbname, db.path = file.path("RNASeqGUI_Projects",
## Project, "Logs", "cache"))
## SaveInCache(db, file.name, "filename_key")
## SaveInCache(db, Project, "project_key")
## SaveInCache(db, gene.list.position, "genelistposition_key")
## SaveInCache(db, gene.identifier, "geneidentifier_key")
## SaveInCache(db, list.type, "listtype_key")
## SaveInCache(db, list.name, "listname_key")
## SaveInCache(db, db.selected, "dbselected_key")
## SaveInCache(db, analysis.type, "analysistype_key")
## SaveInCache(db, out.file.name, "outfilename_key")
## SaveInCache(db, specie, "specie_key")
## id.list <- read.table(file = file.name, header = TRUE, as.is = TRUE)
## id.list <- id.list[, gene.list.position, drop = TRUE]
## if (gene.identifier == "GENCODE") {
## id.list <- unlist(lapply(id.list, function(x) {
## substring(x, 0, regexpr(pattern = ".", x, fixed = T)[1] -
## 1)
## }))
## gene.identifier <- "ENSEMBL_GENE_ID"
## }
## if (gene.identifier == "GENE_SYMBOL") {
## if (specie != "") {
## print("converting gene_symbol to ensembl_gene_id ... ")
## specie.list <- GetSpecieCode(specie)
## print(specie.list$dataset)
## ensembl <- useMart("ENSEMBL_MART_ENSEMBL", host = "www.ensembl.org",
## dataset = specie.list$dataset)
## ensembl.map <- getBM(attributes = c("external_gene_name",
## "ensembl_gene_id"), mart = ensembl)
## id.list <- ConvertList(id.list, ensembl.map)
## gene.identifier <- "ENSEMBL_GENE_ID"
## print("done!")
## }
## else {
## message("ERROR: empty Specie")
## }
## }
## print("check if list is too short")
## if (length(id.list) > 3000) {
## MyDialog(parent.w = main.window, type.d = "warning",
## message = paste0("You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"),
## title = "WARNING")
## message(paste0("WARNING: You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"))
## id.list <- id.list[1:3000]
## }
## else {
## MyDialog(parent.w = main.window, type.d = "info", message = paste0("You submitted ",
## length(id.list), " genes!"), title = "INFORMATION")
## print(paste0("You submitted ", length(id.list), " genes!"))
## }
## print(head(id.list))
## SaveInCache(db, id.list, "idlist_key")
## print("Querying DAVID...")
## w.wind <- WaitingWindow(message = "Please wait while querying DAVID",
## parent.w = main.window)
## Sys.sleep(1)
## david <- DavidConnect()
## if (is.connected(david)) {
## result <- addList(david, id.list, idType = gene.identifier,
## listName = list.name, listType = list.type)
## setAnnotationCategories(david, db.selected)
## results.final <- getFunctionalAnnotationChart(david)
## w.wind$destroy()
## print("done!")
## if (dim(results.final)[1] != 0) {
## if (filter.list$flag) {
## results.final <- results.final[results.final[,
## filter.list$col.name] < filter.list$thr, ]
## }
## SaveInCache(db, filter.list, "filterlist_key")
## SaveInCache(db, results.final, "resultsfinal_key")
## write.table(results.final, file = out.file.name,
## quote = FALSE, row.names = FALSE, sep = "\t")
## cat("File ", out.file.name, " written on disk!\n")
## print(david.db.path)
## input.file.name <- substring(file.name, max(gregexpr("/",
## file.name)[[1]]) + 1)
## input.file.name <- gsub(".txt", "", input.file.name)
## input.file.name <- gsub(" ", "_", input.file.name)
## SavePathwaysList(results.final, david.db.path, just.file.name = input.file.name)
## }
## else {
## results.final <- data.frame()
## SaveInCache(db, results.final, "resultsfinal_key")
## cat("David produced no Results on ", db.selected,
## "\n")
## }
## }
## else {
## w.wind$destroy()
## message("ERROR: DAVID disconnected!")
## }
## PrintDavidReport(db, dbname)
## return(results.final)
## }
## <environment: namespace:RNASeqGUI>
This R code has been run:
print(getwd())
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Logs"
db <- InitDb(db.name='david_DEC_UP_E2_UP_genes_in_intersection.txt_DAVID_ALL_GO_GOTERM_MF_ALL_GOTERM_BP_ALL_db' , db.path='cache')
#results.data.frame <- DavidAnalysis(file.name, gene.list.position, gene.identifier, list.type, list.name, out.file.name, db.selected, analysis.type, Project)
results.data.frame <- LoadCachedObject(db, 'resultsfinal_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(results.data.frame))
## Loading required package: RDAVIDWebService
## Warning in library(package, lib.loc = lib.loc, character.only = TRUE,
## logical.return = TRUE, : there is no package called 'RDAVIDWebService'
## Error in .requirePackage(package): unable to find required package 'RDAVIDWebService'
Here starts the automatically generated code
2016-06-16 19:26:53 and the DAVID*_result*.csv files has been saved in the BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/DEC_DOWN_E2_DOWN_genes_in_intersection.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list2
, db.selected:
KEGG_PATHWAY
, analysis.type:
Pathway
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
The list of called functions:
GetSpecieCode
## function (specie)
## {
## switch(specie, HUMAN = {
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## }, MOUSE = {
## dataset = "mmusculus_gene_ensembl"
## attribute = "mgi_symbol"
## }, DROSOPHILA = {
## dataset = "dmelanogaster_gene_ensembl"
## attribute = "bdgp_symbol"
## }, ZEBRAFISH = {
## dataset = "drerio_gene_ensembl"
## attribute = "zfin_symbol"
## }, {
## print("WARNING: no species detected! Using, HUMAN!")
## dialog <- MyDialog(window, "warning", message = "no species detected! Using, HUMAN!",
## title = "WARNING")
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## })
## return(list(dataset = dataset, attribute = attribute))
## }
## <environment: namespace:RNASeqGUI>
ConvertList
## function (id.list, map)
## {
## res.map <- apply(id.list, 1, function(x) {
## which(map[, 1] %in% x)
## })
## print(head(res.map))
## print(length(res.map))
## print(dim(id.list)[1])
## if (length(res.map) == dim(id.list)[1]) {
## id.list.n <- lapply(res.map, function(item) {
## if (length(item) > 0) {
## map[item[1], 2]
## }
## else {
## map[item, 2]
## }
## })
## }
## else {
## if (length(res.map) == 0) {
## print("problem res.map")
## }
## else if (length(id.list) == 0) {
## print("problem id.list")
## }
## }
## return(unlist(id.list.n))
## }
## <environment: namespace:RNASeqGUI>
DavidConnect
## function (user.mail = "rnaseqgui@na.iac.cnr.it")
## {
## if (!exists("david")) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## else {
## if (!is.connected(david)) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## }
## if (getTimeOut(david) == 30000) {
## setTimeOut(david, 5e+05)
## }
## if (is.null(getHttpProtocolVersion(david))) {
## setHttpProtocolVersion(david, "HTTP/1.0")
## }
## return(david)
## }
## <environment: namespace:RNASeqGUI>
DavidAnalysis
## function (main.window = NULL, file.name, gene.list.position,
## gene.identifier, list.type, list.name, out.file.name, db.selected,
## analysis.type, Project, specie, filter.list)
## {
## require("RDAVIDWebService")
## require("biomaRt")
## if (Sys.info()[[1]] == "Windows") {
## sys.sep = "\\"
## }
## else {
## sys.sep = "/"
## }
## sep.pos <- gregexpr(pattern = sys.sep, file.name, fixed = F)[[1]]
## out.file.name <- substring(file.name, sep.pos[length(sep.pos)] +
## 1)
## david.path <- file.path("RNASeqGUI_Projects", Project, "Results",
## "DAVID")
## david.db.path <- file.path(david.path, paste(db.selected,
## collapse = "_", sep = ""))
## dir.create(david.path, recursive = TRUE)
## if (analysis.type == "Pathway") {
## cat("Performing pathway analysis on ", db.selected, "...\n")
## this.name <- paste0(out.file.name, "_DAVID_Pathway_",
## db.selected)
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## if (length(grep("ALL", db.selected)) != 0) {
## cat("Performing ALL GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_ALL_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## cat("Performing FAT GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_FAT_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_DAVID_FAT_GO_results.txt")
## }
## }
## dbname <- paste0("david_", this.name, "_db")
## db <- InitDb(db.name = dbname, db.path = file.path("RNASeqGUI_Projects",
## Project, "Logs", "cache"))
## SaveInCache(db, file.name, "filename_key")
## SaveInCache(db, Project, "project_key")
## SaveInCache(db, gene.list.position, "genelistposition_key")
## SaveInCache(db, gene.identifier, "geneidentifier_key")
## SaveInCache(db, list.type, "listtype_key")
## SaveInCache(db, list.name, "listname_key")
## SaveInCache(db, db.selected, "dbselected_key")
## SaveInCache(db, analysis.type, "analysistype_key")
## SaveInCache(db, out.file.name, "outfilename_key")
## SaveInCache(db, specie, "specie_key")
## id.list <- read.table(file = file.name, header = TRUE, as.is = TRUE)
## id.list <- id.list[, gene.list.position, drop = TRUE]
## if (gene.identifier == "GENCODE") {
## id.list <- unlist(lapply(id.list, function(x) {
## substring(x, 0, regexpr(pattern = ".", x, fixed = T)[1] -
## 1)
## }))
## gene.identifier <- "ENSEMBL_GENE_ID"
## }
## if (gene.identifier == "GENE_SYMBOL") {
## if (specie != "") {
## print("converting gene_symbol to ensembl_gene_id ... ")
## specie.list <- GetSpecieCode(specie)
## print(specie.list$dataset)
## ensembl <- useMart("ENSEMBL_MART_ENSEMBL", host = "www.ensembl.org",
## dataset = specie.list$dataset)
## ensembl.map <- getBM(attributes = c("external_gene_name",
## "ensembl_gene_id"), mart = ensembl)
## id.list <- ConvertList(id.list, ensembl.map)
## gene.identifier <- "ENSEMBL_GENE_ID"
## print("done!")
## }
## else {
## message("ERROR: empty Specie")
## }
## }
## print("check if list is too short")
## if (length(id.list) > 3000) {
## MyDialog(parent.w = main.window, type.d = "warning",
## message = paste0("You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"),
## title = "WARNING")
## message(paste0("WARNING: You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"))
## id.list <- id.list[1:3000]
## }
## else {
## MyDialog(parent.w = main.window, type.d = "info", message = paste0("You submitted ",
## length(id.list), " genes!"), title = "INFORMATION")
## print(paste0("You submitted ", length(id.list), " genes!"))
## }
## print(head(id.list))
## SaveInCache(db, id.list, "idlist_key")
## print("Querying DAVID...")
## w.wind <- WaitingWindow(message = "Please wait while querying DAVID",
## parent.w = main.window)
## Sys.sleep(1)
## david <- DavidConnect()
## if (is.connected(david)) {
## result <- addList(david, id.list, idType = gene.identifier,
## listName = list.name, listType = list.type)
## setAnnotationCategories(david, db.selected)
## results.final <- getFunctionalAnnotationChart(david)
## w.wind$destroy()
## print("done!")
## if (dim(results.final)[1] != 0) {
## if (filter.list$flag) {
## results.final <- results.final[results.final[,
## filter.list$col.name] < filter.list$thr, ]
## }
## SaveInCache(db, filter.list, "filterlist_key")
## SaveInCache(db, results.final, "resultsfinal_key")
## write.table(results.final, file = out.file.name,
## quote = FALSE, row.names = FALSE, sep = "\t")
## cat("File ", out.file.name, " written on disk!\n")
## print(david.db.path)
## input.file.name <- substring(file.name, max(gregexpr("/",
## file.name)[[1]]) + 1)
## input.file.name <- gsub(".txt", "", input.file.name)
## input.file.name <- gsub(" ", "_", input.file.name)
## SavePathwaysList(results.final, david.db.path, just.file.name = input.file.name)
## }
## else {
## results.final <- data.frame()
## SaveInCache(db, results.final, "resultsfinal_key")
## cat("David produced no Results on ", db.selected,
## "\n")
## }
## }
## else {
## w.wind$destroy()
## message("ERROR: DAVID disconnected!")
## }
## PrintDavidReport(db, dbname)
## return(results.final)
## }
## <environment: namespace:RNASeqGUI>
This R code has been run:
print(getwd())
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Logs"
db <- InitDb(db.name='david_DEC_DOWN_E2_DOWN_genes_in_intersection.txt_DAVID_Pathway_KEGG_PATHWAY_db' , db.path='cache')
#results.data.frame <- DavidAnalysis(file.name, gene.list.position, gene.identifier, list.type, list.name, out.file.name, db.selected, analysis.type, Project)
results.data.frame <- LoadCachedObject(db, 'resultsfinal_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(results.data.frame))
## Category Term Count X.
## 1 KEGG_PATHWAY mmu03010:Ribosome 71 13.894325
## 2 KEGG_PATHWAY mmu00190:Oxidative phosphorylation 47 9.197652
## 3 KEGG_PATHWAY mmu05012:Parkinson's disease 43 8.414873
## 4 KEGG_PATHWAY mmu05016:Huntington's disease 45 8.806262
## 5 KEGG_PATHWAY mmu05010:Alzheimer's disease 41 8.023483
## 6 KEGG_PATHWAY mmu03050:Proteasome 10 1.956947
## PValue
## 1 1.271001e-84
## 2 1.146452e-32
## 3 1.633168e-27
## 4 2.172841e-23
## 5 9.394649e-20
## 6 8.211185e-05
## Genes
## 1 ENSMUSG00000007892, ENSMUSG00000062647, ENSMUSG00000047215, ENSMUSG00000000740, ENSMUSG00000025794, ENSMUSG00000071415, ENSMUSG00000062997, ENSMUSG00000079641, ENSMUSG00000046330, ENSMUSG00000037563, ENSMUSG00000059291, ENSMUSG00000060636, ENSMUSG00000048758, ENSMUSG00000022601, ENSMUSG00000025290, ENSMUSG00000025508, ENSMUSG00000028936, ENSMUSG00000047676, ENSMUSG00000034892, ENSMUSG00000047675, ENSMUSG00000063316, ENSMUSG00000003429, ENSMUSG00000037805, ENSMUSG00000024608, ENSMUSG00000030744, ENSMUSG00000028234, ENSMUSG00000038274, ENSMUSG00000039221, ENSMUSG00000008683, ENSMUSG00000008682, ENSMUSG00000073702, ENSMUSG00000012848, ENSMUSG00000067288, ENSMUSG00000017404, ENSMUSG00000057841, ENSMUSG00000040952, ENSMUSG00000038900, ENSMUSG00000006333, ENSMUSG00000060036, ENSMUSG00000061983, ENSMUSG00000061787, ENSMUSG00000043716, ENSMUSG00000041841, ENSMUSG00000030432, ENSMUSG00000060938, ENSMUSG00000049751, ENSMUSG00000067274, ENSMUSG00000028081, ENSMUSG00000058600, ENSMUSG00000025362, ENSMUSG00000061477, ENSMUSG00000036781, ENSMUSG00000049517, ENSMUSG00000063457, ENSMUSG00000057322, ENSMUSG00000052146, ENSMUSG00000008668, ENSMUSG00000046364, ENSMUSG00000062006, ENSMUSG00000020460, ENSMUSG00000039001, ENSMUSG00000044533, ENSMUSG00000032518, ENSMUSG00000062328, ENSMUSG00000045128, ENSMUSG00000059070, ENSMUSG00000057863, ENSMUSG00000041453, ENSMUSG00000009927, ENSMUSG00000031320, ENSMUSG00000028495, ENSMUSG00000003970, ENSMUSG00000079435
## 2 ENSMUSG00000022450, ENSMUSG00000063882, ENSMUSG00000029632, ENSMUSG00000038690, ENSMUSG00000050856, ENSMUSG00000035885, ENSMUSG00000027673, ENSMUSG00000038717, ENSMUSG00000030647, ENSMUSG00000003072, ENSMUSG00000033938, ENSMUSG00000018770, ENSMUSG00000021606, ENSMUSG00000004285, ENSMUSG00000022820, ENSMUSG00000000563, ENSMUSG00000006057, ENSMUSG00000061518, ENSMUSG00000062683, ENSMUSG00000028648, ENSMUSG00000026032, ENSMUSG00000041697, ENSMUSG00000044894, ENSMUSG00000014313, ENSMUSG00000035674, ENSMUSG00000059534, ENSMUSG00000046516, ENSMUSG00000024038, ENSMUSG00000023089, ENSMUSG00000024099, ENSMUSG00000059734, ENSMUSG00000016427, ENSMUSG00000014294, ENSMUSG00000020163, ENSMUSG00000016252, ENSMUSG00000040048, ENSMUSG00000034566, ENSMUSG00000026895, ENSMUSG00000041881, ENSMUSG00000037152, ENSMUSG00000032330, ENSMUSG00000039105, ENSMUSG00000031818, ENSMUSG00000002379, ENSMUSG00000022354, ENSMUSG00000036751, ENSMUSG00000017778
## 3 ENSMUSG00000022450, ENSMUSG00000063882, ENSMUSG00000029632, ENSMUSG00000028964, ENSMUSG00000035885, ENSMUSG00000027673, ENSMUSG00000030647, ENSMUSG00000003072, ENSMUSG00000033938, ENSMUSG00000018770, ENSMUSG00000021606, ENSMUSG00000022820, ENSMUSG00000000563, ENSMUSG00000006057, ENSMUSG00000061518, ENSMUSG00000062683, ENSMUSG00000028648, ENSMUSG00000026032, ENSMUSG00000041697, ENSMUSG00000044894, ENSMUSG00000014313, ENSMUSG00000035674, ENSMUSG00000059534, ENSMUSG00000024038, ENSMUSG00000023089, ENSMUSG00000024099, ENSMUSG00000059734, ENSMUSG00000016427, ENSMUSG00000014294, ENSMUSG00000020163, ENSMUSG00000016252, ENSMUSG00000020460, ENSMUSG00000040048, ENSMUSG00000034566, ENSMUSG00000026895, ENSMUSG00000041881, ENSMUSG00000037152, ENSMUSG00000032330, ENSMUSG00000031818, ENSMUSG00000028756, ENSMUSG00000022354, ENSMUSG00000036751, ENSMUSG00000017778
## 4 ENSMUSG00000022450, ENSMUSG00000063882, ENSMUSG00000029632, ENSMUSG00000035885, ENSMUSG00000038489, ENSMUSG00000027673, ENSMUSG00000030647, ENSMUSG00000003072, ENSMUSG00000033938, ENSMUSG00000018770, ENSMUSG00000021606, ENSMUSG00000022820, ENSMUSG00000000563, ENSMUSG00000006057, ENSMUSG00000061518, ENSMUSG00000062683, ENSMUSG00000028648, ENSMUSG00000026032, ENSMUSG00000041697, ENSMUSG00000044894, ENSMUSG00000014313, ENSMUSG00000035674, ENSMUSG00000033020, ENSMUSG00000059534, ENSMUSG00000024038, ENSMUSG00000023089, ENSMUSG00000024099, ENSMUSG00000059734, ENSMUSG00000016427, ENSMUSG00000014294, ENSMUSG00000020163, ENSMUSG00000016252, ENSMUSG00000040048, ENSMUSG00000034566, ENSMUSG00000026895, ENSMUSG00000041881, ENSMUSG00000037152, ENSMUSG00000071662, ENSMUSG00000032330, ENSMUSG00000022982, ENSMUSG00000031818, ENSMUSG00000022354, ENSMUSG00000036751, ENSMUSG00000008036, ENSMUSG00000017778
## 5 ENSMUSG00000022450, ENSMUSG00000063882, ENSMUSG00000029632, ENSMUSG00000035885, ENSMUSG00000027673, ENSMUSG00000030647, ENSMUSG00000003072, ENSMUSG00000033938, ENSMUSG00000018770, ENSMUSG00000021606, ENSMUSG00000022820, ENSMUSG00000000563, ENSMUSG00000006057, ENSMUSG00000061518, ENSMUSG00000062683, ENSMUSG00000028648, ENSMUSG00000026032, ENSMUSG00000041697, ENSMUSG00000044894, ENSMUSG00000014313, ENSMUSG00000035674, ENSMUSG00000036835, ENSMUSG00000059534, ENSMUSG00000024038, ENSMUSG00000023089, ENSMUSG00000024099, ENSMUSG00000059734, ENSMUSG00000016427, ENSMUSG00000014294, ENSMUSG00000020163, ENSMUSG00000016252, ENSMUSG00000040048, ENSMUSG00000034566, ENSMUSG00000026895, ENSMUSG00000041881, ENSMUSG00000037152, ENSMUSG00000032330, ENSMUSG00000031818, ENSMUSG00000022354, ENSMUSG00000036751, ENSMUSG00000017778
## 6 ENSMUSG00000021024, ENSMUSG00000042541, ENSMUSG00000026750, ENSMUSG00000069744, ENSMUSG00000014769, ENSMUSG00000018286, ENSMUSG00000025487, ENSMUSG00000079197, ENSMUSG00000029649, ENSMUSG00000005779
## List.Total Pop.Hits Pop.Total Fold.Enrichment Bonferroni Benjamini
## 1 231 89 5738 19.816042 1.499781e-82 1.499781e-82
## 2 231 130 5738 8.980553 1.352814e-30 6.764068e-31
## 3 231 133 5738 8.030921 1.927139e-25 6.423795e-26
## 4 231 183 5738 6.108154 2.563952e-21 6.409881e-22
## 5 231 182 5738 5.595785 1.108569e-17 2.217137e-18
## 6 231 47 5738 5.285070 9.642803e-03 1.613629e-03
## FDR
## 1 1.454582e-81
## 2 1.312044e-29
## 3 1.869060e-24
## 4 2.486683e-20
## 5 1.075160e-16
## 6 9.393166e-02
Here starts the automatically generated code
2016-06-16 19:29:34 and the DAVID*_result*.csv files has been saved in the BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/DEC_DOWN_E2_DOWN_genes_in_intersection.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list2
, db.selected:
GOTERM_MF_ALL
, analysis.type:
GO
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/DEC_DOWN_E2_DOWN_genes_in_intersection.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list2
, db.selected:
GOTERM_BP_ALL
, analysis.type:
GO
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
The list of called functions:
GetSpecieCode
## function (specie)
## {
## switch(specie, HUMAN = {
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## }, MOUSE = {
## dataset = "mmusculus_gene_ensembl"
## attribute = "mgi_symbol"
## }, DROSOPHILA = {
## dataset = "dmelanogaster_gene_ensembl"
## attribute = "bdgp_symbol"
## }, ZEBRAFISH = {
## dataset = "drerio_gene_ensembl"
## attribute = "zfin_symbol"
## }, {
## print("WARNING: no species detected! Using, HUMAN!")
## dialog <- MyDialog(window, "warning", message = "no species detected! Using, HUMAN!",
## title = "WARNING")
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## })
## return(list(dataset = dataset, attribute = attribute))
## }
## <environment: namespace:RNASeqGUI>
ConvertList
## function (id.list, map)
## {
## res.map <- apply(id.list, 1, function(x) {
## which(map[, 1] %in% x)
## })
## print(head(res.map))
## print(length(res.map))
## print(dim(id.list)[1])
## if (length(res.map) == dim(id.list)[1]) {
## id.list.n <- lapply(res.map, function(item) {
## if (length(item) > 0) {
## map[item[1], 2]
## }
## else {
## map[item, 2]
## }
## })
## }
## else {
## if (length(res.map) == 0) {
## print("problem res.map")
## }
## else if (length(id.list) == 0) {
## print("problem id.list")
## }
## }
## return(unlist(id.list.n))
## }
## <environment: namespace:RNASeqGUI>
DavidConnect
## function (user.mail = "rnaseqgui@na.iac.cnr.it")
## {
## if (!exists("david")) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## else {
## if (!is.connected(david)) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## }
## if (getTimeOut(david) == 30000) {
## setTimeOut(david, 5e+05)
## }
## if (is.null(getHttpProtocolVersion(david))) {
## setHttpProtocolVersion(david, "HTTP/1.0")
## }
## return(david)
## }
## <environment: namespace:RNASeqGUI>
DavidAnalysis
## function (main.window = NULL, file.name, gene.list.position,
## gene.identifier, list.type, list.name, out.file.name, db.selected,
## analysis.type, Project, specie, filter.list)
## {
## require("RDAVIDWebService")
## require("biomaRt")
## if (Sys.info()[[1]] == "Windows") {
## sys.sep = "\\"
## }
## else {
## sys.sep = "/"
## }
## sep.pos <- gregexpr(pattern = sys.sep, file.name, fixed = F)[[1]]
## out.file.name <- substring(file.name, sep.pos[length(sep.pos)] +
## 1)
## david.path <- file.path("RNASeqGUI_Projects", Project, "Results",
## "DAVID")
## david.db.path <- file.path(david.path, paste(db.selected,
## collapse = "_", sep = ""))
## dir.create(david.path, recursive = TRUE)
## if (analysis.type == "Pathway") {
## cat("Performing pathway analysis on ", db.selected, "...\n")
## this.name <- paste0(out.file.name, "_DAVID_Pathway_",
## db.selected)
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## if (length(grep("ALL", db.selected)) != 0) {
## cat("Performing ALL GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_ALL_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## cat("Performing FAT GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_FAT_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_DAVID_FAT_GO_results.txt")
## }
## }
## dbname <- paste0("david_", this.name, "_db")
## db <- InitDb(db.name = dbname, db.path = file.path("RNASeqGUI_Projects",
## Project, "Logs", "cache"))
## SaveInCache(db, file.name, "filename_key")
## SaveInCache(db, Project, "project_key")
## SaveInCache(db, gene.list.position, "genelistposition_key")
## SaveInCache(db, gene.identifier, "geneidentifier_key")
## SaveInCache(db, list.type, "listtype_key")
## SaveInCache(db, list.name, "listname_key")
## SaveInCache(db, db.selected, "dbselected_key")
## SaveInCache(db, analysis.type, "analysistype_key")
## SaveInCache(db, out.file.name, "outfilename_key")
## SaveInCache(db, specie, "specie_key")
## id.list <- read.table(file = file.name, header = TRUE, as.is = TRUE)
## id.list <- id.list[, gene.list.position, drop = TRUE]
## if (gene.identifier == "GENCODE") {
## id.list <- unlist(lapply(id.list, function(x) {
## substring(x, 0, regexpr(pattern = ".", x, fixed = T)[1] -
## 1)
## }))
## gene.identifier <- "ENSEMBL_GENE_ID"
## }
## if (gene.identifier == "GENE_SYMBOL") {
## if (specie != "") {
## print("converting gene_symbol to ensembl_gene_id ... ")
## specie.list <- GetSpecieCode(specie)
## print(specie.list$dataset)
## ensembl <- useMart("ENSEMBL_MART_ENSEMBL", host = "www.ensembl.org",
## dataset = specie.list$dataset)
## ensembl.map <- getBM(attributes = c("external_gene_name",
## "ensembl_gene_id"), mart = ensembl)
## id.list <- ConvertList(id.list, ensembl.map)
## gene.identifier <- "ENSEMBL_GENE_ID"
## print("done!")
## }
## else {
## message("ERROR: empty Specie")
## }
## }
## print("check if list is too short")
## if (length(id.list) > 3000) {
## MyDialog(parent.w = main.window, type.d = "warning",
## message = paste0("You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"),
## title = "WARNING")
## message(paste0("WARNING: You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"))
## id.list <- id.list[1:3000]
## }
## else {
## MyDialog(parent.w = main.window, type.d = "info", message = paste0("You submitted ",
## length(id.list), " genes!"), title = "INFORMATION")
## print(paste0("You submitted ", length(id.list), " genes!"))
## }
## print(head(id.list))
## SaveInCache(db, id.list, "idlist_key")
## print("Querying DAVID...")
## w.wind <- WaitingWindow(message = "Please wait while querying DAVID",
## parent.w = main.window)
## Sys.sleep(1)
## david <- DavidConnect()
## if (is.connected(david)) {
## result <- addList(david, id.list, idType = gene.identifier,
## listName = list.name, listType = list.type)
## setAnnotationCategories(david, db.selected)
## results.final <- getFunctionalAnnotationChart(david)
## w.wind$destroy()
## print("done!")
## if (dim(results.final)[1] != 0) {
## if (filter.list$flag) {
## results.final <- results.final[results.final[,
## filter.list$col.name] < filter.list$thr, ]
## }
## SaveInCache(db, filter.list, "filterlist_key")
## SaveInCache(db, results.final, "resultsfinal_key")
## write.table(results.final, file = out.file.name,
## quote = FALSE, row.names = FALSE, sep = "\t")
## cat("File ", out.file.name, " written on disk!\n")
## print(david.db.path)
## input.file.name <- substring(file.name, max(gregexpr("/",
## file.name)[[1]]) + 1)
## input.file.name <- gsub(".txt", "", input.file.name)
## input.file.name <- gsub(" ", "_", input.file.name)
## SavePathwaysList(results.final, david.db.path, just.file.name = input.file.name)
## }
## else {
## results.final <- data.frame()
## SaveInCache(db, results.final, "resultsfinal_key")
## cat("David produced no Results on ", db.selected,
## "\n")
## }
## }
## else {
## w.wind$destroy()
## message("ERROR: DAVID disconnected!")
## }
## PrintDavidReport(db, dbname)
## return(results.final)
## }
## <environment: namespace:RNASeqGUI>
This R code has been run:
print(getwd())
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Logs"
db <- InitDb(db.name='david_DEC_DOWN_E2_DOWN_genes_in_intersection.txt_DAVID_ALL_GO_GOTERM_MF_ALL_GOTERM_BP_ALL_db' , db.path='cache')
#results.data.frame <- DavidAnalysis(file.name, gene.list.position, gene.identifier, list.type, list.name, out.file.name, db.selected, analysis.type, Project)
results.data.frame <- LoadCachedObject(db, 'resultsfinal_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(results.data.frame))
## Category Term Count
## 1 GOTERM_MF_ALL GO:0003735~structural constituent of ribosome 83
## 2 GOTERM_BP_ALL GO:0006412~translation 94
## 3 GOTERM_MF_ALL GO:0005198~structural molecule activity 88
## 4 GOTERM_BP_ALL GO:0009987~cellular process 338
## 5 GOTERM_BP_ALL GO:0044237~cellular metabolic process 253
## 6 GOTERM_BP_ALL GO:0044267~cellular protein metabolic process 135
## X. PValue
## 1 16.24266 3.032929e-93
## 2 18.39530 6.832557e-73
## 3 17.22114 1.082752e-53
## 4 66.14481 5.479370e-31
## 5 49.51076 7.433889e-26
## 6 26.41879 2.389420e-25
## Genes
## 1 ENSMUSG00000007892, ENSMUSG00000047215, ENSMUSG00000000740, ENSMUSG00000025794, ENSMUSG00000071415, ENSMUSG00000062997, ENSMUSG00000079641, ENSMUSG00000046330, ENSMUSG00000037563, ENSMUSG00000059291, ENSMUSG00000060636, ENSMUSG00000020477, ENSMUSG00000029066, ENSMUSG00000048758, ENSMUSG00000023939, ENSMUSG00000022601, ENSMUSG00000025290, ENSMUSG00000025508, ENSMUSG00000036850, ENSMUSG00000028936, ENSMUSG00000047676, ENSMUSG00000034892, ENSMUSG00000047675, ENSMUSG00000063316, ENSMUSG00000003429, ENSMUSG00000037805, ENSMUSG00000024608, ENSMUSG00000030744, ENSMUSG00000045948, ENSMUSG00000028234, ENSMUSG00000038274, ENSMUSG00000039221, ENSMUSG00000008683, ENSMUSG00000008682, ENSMUSG00000073702, ENSMUSG00000012848, ENSMUSG00000067288, ENSMUSG00000017404, ENSMUSG00000074129, ENSMUSG00000057841, ENSMUSG00000030879, ENSMUSG00000040952, ENSMUSG00000038900, ENSMUSG00000021607, ENSMUSG00000049960, ENSMUSG00000006333, ENSMUSG00000060036, ENSMUSG00000028861, ENSMUSG00000061983, ENSMUSG00000054312, ENSMUSG00000061787, ENSMUSG00000058267, ENSMUSG00000043716, ENSMUSG00000024902, ENSMUSG00000041841, ENSMUSG00000030432, ENSMUSG00000060938, ENSMUSG00000049751, ENSMUSG00000067274, ENSMUSG00000028081, ENSMUSG00000058600, ENSMUSG00000025362, ENSMUSG00000061477, ENSMUSG00000036781, ENSMUSG00000049517, ENSMUSG00000063457, ENSMUSG00000057322, ENSMUSG00000008668, ENSMUSG00000039640, ENSMUSG00000046364, ENSMUSG00000062006, ENSMUSG00000020460, ENSMUSG00000039001, ENSMUSG00000044533, ENSMUSG00000032518, ENSMUSG00000062328, ENSMUSG00000045128, ENSMUSG00000010406, ENSMUSG00000059070, ENSMUSG00000057863, ENSMUSG00000041453, ENSMUSG00000028495, ENSMUSG00000031320, ENSMUSG00000003970, ENSMUSG00000079435
## 2 ENSMUSG00000007892, ENSMUSG00000025967, ENSMUSG00000047215, ENSMUSG00000006941, ENSMUSG00000000740, ENSMUSG00000025794, ENSMUSG00000071415, ENSMUSG00000055762, ENSMUSG00000062997, ENSMUSG00000079641, ENSMUSG00000046330, ENSMUSG00000037563, ENSMUSG00000059291, ENSMUSG00000060636, ENSMUSG00000027613, ENSMUSG00000020477, ENSMUSG00000029066, ENSMUSG00000048758, ENSMUSG00000023939, ENSMUSG00000035530, ENSMUSG00000022601, ENSMUSG00000035202, ENSMUSG00000025290, ENSMUSG00000030871, ENSMUSG00000025508, ENSMUSG00000036850, ENSMUSG00000028936, ENSMUSG00000047676, ENSMUSG00000034892, ENSMUSG00000047675, ENSMUSG00000063316, ENSMUSG00000003429, ENSMUSG00000037805, ENSMUSG00000024608, ENSMUSG00000030744, ENSMUSG00000045948, ENSMUSG00000028234, ENSMUSG00000038274, ENSMUSG00000039221, ENSMUSG00000008683, ENSMUSG00000008682, ENSMUSG00000073702, ENSMUSG00000012848, ENSMUSG00000067288, ENSMUSG00000017404, ENSMUSG00000074129, ENSMUSG00000057841, ENSMUSG00000030879, ENSMUSG00000040952, ENSMUSG00000038900, ENSMUSG00000021607, ENSMUSG00000049960, ENSMUSG00000006333, ENSMUSG00000060036, ENSMUSG00000028861, ENSMUSG00000061983, ENSMUSG00000054312, ENSMUSG00000016554, ENSMUSG00000061787, ENSMUSG00000058267, ENSMUSG00000043716, ENSMUSG00000024902, ENSMUSG00000041841, ENSMUSG00000030432, ENSMUSG00000060938, ENSMUSG00000067274, ENSMUSG00000049751, ENSMUSG00000028081, ENSMUSG00000058600, ENSMUSG00000053565, ENSMUSG00000025362, ENSMUSG00000061477, ENSMUSG00000036781, ENSMUSG00000049517, ENSMUSG00000063457, ENSMUSG00000057322, ENSMUSG00000008668, ENSMUSG00000078812, ENSMUSG00000039640, ENSMUSG00000062006, ENSMUSG00000046364, ENSMUSG00000020460, ENSMUSG00000039001, ENSMUSG00000044533, ENSMUSG00000032518, ENSMUSG00000031029, ENSMUSG00000062328, ENSMUSG00000045128, ENSMUSG00000010406, ENSMUSG00000059070, ENSMUSG00000057863, ENSMUSG00000041453, ENSMUSG00000028495, ENSMUSG00000031320, ENSMUSG00000003970, ENSMUSG00000079435
## 3 ENSMUSG00000007892, ENSMUSG00000047215, ENSMUSG00000000740, ENSMUSG00000025794, ENSMUSG00000071415, ENSMUSG00000062997, ENSMUSG00000079641, ENSMUSG00000046330, ENSMUSG00000037563, ENSMUSG00000059291, ENSMUSG00000060636, ENSMUSG00000020477, ENSMUSG00000029066, ENSMUSG00000048758, ENSMUSG00000023939, ENSMUSG00000022601, ENSMUSG00000043091, ENSMUSG00000025290, ENSMUSG00000025508, ENSMUSG00000036850, ENSMUSG00000028936, ENSMUSG00000047676, ENSMUSG00000034892, ENSMUSG00000047675, ENSMUSG00000001506, ENSMUSG00000063316, ENSMUSG00000003429, ENSMUSG00000037805, ENSMUSG00000024608, ENSMUSG00000030744, ENSMUSG00000045948, ENSMUSG00000023484, ENSMUSG00000028234, ENSMUSG00000038274, ENSMUSG00000039221, ENSMUSG00000008683, ENSMUSG00000008682, ENSMUSG00000073702, ENSMUSG00000012848, ENSMUSG00000067288, ENSMUSG00000017404, ENSMUSG00000074129, ENSMUSG00000057841, ENSMUSG00000030879, ENSMUSG00000040952, ENSMUSG00000038900, ENSMUSG00000021607, ENSMUSG00000049960, ENSMUSG00000006333, ENSMUSG00000060036, ENSMUSG00000028861, ENSMUSG00000061983, ENSMUSG00000054312, ENSMUSG00000023004, ENSMUSG00000061787, ENSMUSG00000058267, ENSMUSG00000043716, ENSMUSG00000024902, ENSMUSG00000041841, ENSMUSG00000030432, ENSMUSG00000029661, ENSMUSG00000060938, ENSMUSG00000067274, ENSMUSG00000049751, ENSMUSG00000028081, ENSMUSG00000058600, ENSMUSG00000025362, ENSMUSG00000061477, ENSMUSG00000036781, ENSMUSG00000049517, ENSMUSG00000063457, ENSMUSG00000057322, ENSMUSG00000008668, ENSMUSG00000039640, ENSMUSG00000062006, ENSMUSG00000046364, ENSMUSG00000020460, ENSMUSG00000039001, ENSMUSG00000044533, ENSMUSG00000032518, ENSMUSG00000062328, ENSMUSG00000045128, ENSMUSG00000010406, ENSMUSG00000059070, ENSMUSG00000057863, ENSMUSG00000041453, ENSMUSG00000028495, ENSMUSG00000031320, ENSMUSG00000003970, ENSMUSG00000079435
## 4 ENSMUSG00000071866, ENSMUSG00000062647, ENSMUSG00000029177, ENSMUSG00000038690, ENSMUSG00000050856, ENSMUSG00000025794, ENSMUSG00000003072, ENSMUSG00000030647, ENSMUSG00000051234, ENSMUSG00000006058, ENSMUSG00000006057, ENSMUSG00000037563, ENSMUSG00000024369, ENSMUSG00000021265, ENSMUSG00000060636, ENSMUSG00000040824, ENSMUSG00000067847, ENSMUSG00000072941, ENSMUSG00000025487, ENSMUSG00000048758, ENSMUSG00000072949, ENSMUSG00000021102, ENSMUSG00000053898, ENSMUSG00000035439, ENSMUSG00000059734, ENSMUSG00000025508, ENSMUSG00000004610, ENSMUSG00000020307, ENSMUSG00000020903, ENSMUSG00000020308, ENSMUSG00000056209, ENSMUSG00000001506, ENSMUSG00000037805, ENSMUSG00000001131, ENSMUSG00000030122, ENSMUSG00000024608, ENSMUSG00000045948, ENSMUSG00000040048, ENSMUSG00000012848, ENSMUSG00000059325, ENSMUSG00000057841, ENSMUSG00000042043, ENSMUSG00000078427, ENSMUSG00000000149, ENSMUSG00000061360, ENSMUSG00000031762, ENSMUSG00000054312, ENSMUSG00000061787, ENSMUSG00000031662, ENSMUSG00000031375, ENSMUSG00000041841, ENSMUSG00000024902, ENSMUSG00000026750, ENSMUSG00000019997, ENSMUSG00000020241, ENSMUSG00000044005, ENSMUSG00000015804, ENSMUSG00000056399, ENSMUSG00000027133, ENSMUSG00000025362, ENSMUSG00000031765, ENSMUSG00000015806, ENSMUSG00000049517, ENSMUSG00000078812, ENSMUSG00000062515, ENSMUSG00000032288, ENSMUSG00000013822, ENSMUSG00000062006, ENSMUSG00000016252, ENSMUSG00000034566, ENSMUSG00000032518, ENSMUSG00000026895, ENSMUSG00000037152, ENSMUSG00000047459, ENSMUSG00000001020, ENSMUSG00000059070, ENSMUSG00000041453, ENSMUSG00000001025, ENSMUSG00000061286, ENSMUSG00000032112, ENSMUSG00000035242, ENSMUSG00000016344, ENSMUSG00000030357, ENSMUSG00000006941, ENSMUSG00000031157, ENSMUSG00000032602, ENSMUSG00000035478, ENSMUSG00000004558, ENSMUSG00000021660, ENSMUSG00000040681, ENSMUSG00000059291, ENSMUSG00000062683, ENSMUSG00000029545, ENSMUSG00000029642, ENSMUSG00000001056, ENSMUSG00000035674, ENSMUSG00000036835, ENSMUSG00000023939, ENSMUSG00000035530, ENSMUSG00000043091, ENSMUSG00000024099, ENSMUSG00000030871, ENSMUSG00000047676, ENSMUSG00000028936, ENSMUSG00000063931, ENSMUSG00000020219, ENSMUSG00000047675, ENSMUSG00000003429, ENSMUSG00000002768, ENSMUSG00000005161, ENSMUSG00000018339, ENSMUSG00000015092, ENSMUSG00000008683, ENSMUSG00000008682, ENSMUSG00000031754, ENSMUSG00000073702, ENSMUSG00000067288, ENSMUSG00000062963, ENSMUSG00000022354, ENSMUSG00000052738, ENSMUSG00000030879, ENSMUSG00000046432, ENSMUSG00000027404, ENSMUSG00000043866, ENSMUSG00000026511, ENSMUSG00000027673, ENSMUSG00000021917, ENSMUSG00000023004, ENSMUSG00000020108, ENSMUSG00000001289, ENSMUSG00000004849, ENSMUSG00000009549, ENSMUSG00000032231, ENSMUSG00000026032, ENSMUSG00000006442, ENSMUSG00000060938, ENSMUSG00000067274, ENSMUSG00000049751, ENSMUSG00000031807, ENSMUSG00000058600, ENSMUSG00000057322, ENSMUSG00000039450, ENSMUSG00000036820, ENSMUSG00000050708, ENSMUSG00000030750, ENSMUSG00000022037, ENSMUSG00000070436, ENSMUSG00000078713, ENSMUSG00000044533, ENSMUSG00000022234, ENSMUSG00000031029, ENSMUSG00000029538, ENSMUSG00000041126, ENSMUSG00000010406, ENSMUSG00000078348, ENSMUSG00000019054, ENSMUSG00000057863, ENSMUSG00000031320, ENSMUSG00000060803, ENSMUSG00000066442, ENSMUSG00000022450, ENSMUSG00000025967, ENSMUSG00000078974, ENSMUSG00000020473, ENSMUSG00000000740, ENSMUSG00000071415, ENSMUSG00000061315, ENSMUSG00000038717, ENSMUSG00000055762, ENSMUSG00000049775, ENSMUSG00000062997, ENSMUSG00000018770, ENSMUSG00000002043, ENSMUSG00000025068, ENSMUSG00000021453, ENSMUSG00000028648, ENSMUSG00000044894, ENSMUSG00000020477, ENSMUSG00000029810, ENSMUSG00000059534, ENSMUSG00000031068, ENSMUSG00000035202, ENSMUSG00000025290, ENSMUSG00000079037, ENSMUSG00000034892, ENSMUSG00000028062, ENSMUSG00000020485, ENSMUSG00000063316, ENSMUSG00000031590, ENSMUSG00000038374, ENSMUSG00000030744, ENSMUSG00000006728, ENSMUSG00000028234, ENSMUSG00000028832, ENSMUSG00000053317, ENSMUSG00000039221, ENSMUSG00000018585, ENSMUSG00000029038, ENSMUSG00000002233, ENSMUSG00000040952, ENSMUSG00000076617, ENSMUSG00000030057, ENSMUSG00000076612, ENSMUSG00000076613, ENSMUSG00000024309, ENSMUSG00000021607, ENSMUSG00000020766, ENSMUSG00000042770, ENSMUSG00000036748, ENSMUSG00000049960, ENSMUSG00000060860, ENSMUSG00000029632, ENSMUSG00000028861, ENSMUSG00000060036, ENSMUSG00000028964, ENSMUSG00000061983, ENSMUSG00000038489, ENSMUSG00000028367, ENSMUSG00000005354, ENSMUSG00000057278, ENSMUSG00000004285, ENSMUSG00000021606, ENSMUSG00000022820, ENSMUSG00000065990, ENSMUSG00000037601, ENSMUSG00000002477, ENSMUSG00000030432, ENSMUSG00000005732, ENSMUSG00000020695, ENSMUSG00000022415, ENSMUSG00000061477, ENSMUSG00000024038, ENSMUSG00000063457, ENSMUSG00000076437, ENSMUSG00000031059, ENSMUSG00000028044, ENSMUSG00000031848, ENSMUSG00000008668, ENSMUSG00000014294, ENSMUSG00000069744, ENSMUSG00000014769, ENSMUSG00000028851, ENSMUSG00000039001, ENSMUSG00000050014, ENSMUSG00000034353, ENSMUSG00000062328, ENSMUSG00000045128, ENSMUSG00000028756, ENSMUSG00000018567, ENSMUSG00000022174, ENSMUSG00000076432, ENSMUSG00000022427, ENSMUSG00000079435, ENSMUSG00000028651, ENSMUSG00000007892, ENSMUSG00000052429, ENSMUSG00000047215, ENSMUSG00000018293, ENSMUSG00000007891, ENSMUSG00000000782, ENSMUSG00000058779, ENSMUSG00000015013, ENSMUSG00000033938, ENSMUSG00000046330, ENSMUSG00000079641, ENSMUSG00000004268, ENSMUSG00000002289, ENSMUSG00000027613, ENSMUSG00000019929, ENSMUSG00000033020, ENSMUSG00000034345, ENSMUSG00000018286, ENSMUSG00000033735, ENSMUSG00000029066, ENSMUSG00000030413, ENSMUSG00000021411, ENSMUSG00000022601, ENSMUSG00000044475, ENSMUSG00000075706, ENSMUSG00000036850, ENSMUSG00000021024, ENSMUSG00000020180, ENSMUSG00000021025, ENSMUSG00000030804, ENSMUSG00000036181, ENSMUSG00000020736, ENSMUSG00000024914, ENSMUSG00000020186, ENSMUSG00000023484, ENSMUSG00000038274, ENSMUSG00000020440, ENSMUSG00000022400, ENSMUSG00000032171, ENSMUSG00000020444, ENSMUSG00000017404, ENSMUSG00000074129, ENSMUSG00000002379, ENSMUSG00000022098, ENSMUSG00000068220, ENSMUSG00000008036, ENSMUSG00000038900, ENSMUSG00000010376, ENSMUSG00000046865, ENSMUSG00000063882, ENSMUSG00000006333, ENSMUSG00000030814, ENSMUSG00000036256, ENSMUSG00000036199, ENSMUSG00000032959, ENSMUSG00000032369, ENSMUSG00000058267, ENSMUSG00000016554, ENSMUSG00000073676, ENSMUSG00000036390, ENSMUSG00000000563, ENSMUSG00000043716, ENSMUSG00000055839, ENSMUSG00000028081, ENSMUSG00000005779, ENSMUSG00000053565, ENSMUSG00000024844, ENSMUSG00000036781, ENSMUSG00000023089, ENSMUSG00000016427, ENSMUSG00000032966, ENSMUSG00000020163, ENSMUSG00000028998, ENSMUSG00000039640, ENSMUSG00000046364, ENSMUSG00000020460, ENSMUSG00000032554, ENSMUSG00000041881, ENSMUSG00000042541, ENSMUSG00000042747, ENSMUSG00000071662, ENSMUSG00000022982, ENSMUSG00000002395, ENSMUSG00000028495, ENSMUSG00000006095, ENSMUSG00000003970
## 5 ENSMUSG00000071866, ENSMUSG00000038690, ENSMUSG00000050856, ENSMUSG00000025794, ENSMUSG00000003072, ENSMUSG00000030647, ENSMUSG00000051234, ENSMUSG00000006058, ENSMUSG00000006057, ENSMUSG00000037563, ENSMUSG00000024369, ENSMUSG00000060636, ENSMUSG00000040824, ENSMUSG00000072941, ENSMUSG00000048758, ENSMUSG00000072949, ENSMUSG00000053898, ENSMUSG00000059734, ENSMUSG00000004610, ENSMUSG00000025508, ENSMUSG00000020307, ENSMUSG00000056209, ENSMUSG00000037805, ENSMUSG00000030122, ENSMUSG00000024608, ENSMUSG00000045948, ENSMUSG00000040048, ENSMUSG00000012848, ENSMUSG00000059325, ENSMUSG00000057841, ENSMUSG00000078427, ENSMUSG00000061360, ENSMUSG00000054312, ENSMUSG00000061787, ENSMUSG00000031375, ENSMUSG00000024902, ENSMUSG00000041841, ENSMUSG00000026750, ENSMUSG00000019997, ENSMUSG00000015804, ENSMUSG00000044005, ENSMUSG00000056399, ENSMUSG00000027133, ENSMUSG00000025362, ENSMUSG00000015806, ENSMUSG00000049517, ENSMUSG00000078812, ENSMUSG00000062515, ENSMUSG00000062006, ENSMUSG00000013822, ENSMUSG00000032288, ENSMUSG00000016252, ENSMUSG00000034566, ENSMUSG00000032518, ENSMUSG00000026895, ENSMUSG00000037152, ENSMUSG00000059070, ENSMUSG00000041453, ENSMUSG00000061286, ENSMUSG00000032112, ENSMUSG00000035242, ENSMUSG00000030357, ENSMUSG00000006941, ENSMUSG00000031157, ENSMUSG00000035478, ENSMUSG00000021660, ENSMUSG00000040681, ENSMUSG00000059291, ENSMUSG00000062683, ENSMUSG00000029545, ENSMUSG00000029642, ENSMUSG00000001056, ENSMUSG00000035674, ENSMUSG00000036835, ENSMUSG00000023939, ENSMUSG00000035530, ENSMUSG00000030871, ENSMUSG00000024099, ENSMUSG00000047676, ENSMUSG00000028936, ENSMUSG00000047675, ENSMUSG00000003429, ENSMUSG00000005161, ENSMUSG00000018339, ENSMUSG00000015092, ENSMUSG00000008683, ENSMUSG00000031754, ENSMUSG00000008682, ENSMUSG00000073702, ENSMUSG00000062963, ENSMUSG00000067288, ENSMUSG00000022354, ENSMUSG00000052738, ENSMUSG00000030879, ENSMUSG00000027404, ENSMUSG00000043866, ENSMUSG00000021917, ENSMUSG00000027673, ENSMUSG00000001289, ENSMUSG00000026032, ENSMUSG00000006442, ENSMUSG00000060938, ENSMUSG00000049751, ENSMUSG00000067274, ENSMUSG00000031807, ENSMUSG00000058600, ENSMUSG00000057322, ENSMUSG00000039450, ENSMUSG00000036820, ENSMUSG00000030750, ENSMUSG00000044533, ENSMUSG00000022234, ENSMUSG00000031029, ENSMUSG00000029538, ENSMUSG00000010406, ENSMUSG00000078348, ENSMUSG00000057863, ENSMUSG00000031320, ENSMUSG00000060803, ENSMUSG00000066442, ENSMUSG00000022450, ENSMUSG00000025967, ENSMUSG00000020473, ENSMUSG00000000740, ENSMUSG00000071415, ENSMUSG00000061315, ENSMUSG00000038717, ENSMUSG00000055762, ENSMUSG00000062997, ENSMUSG00000018770, ENSMUSG00000025068, ENSMUSG00000021453, ENSMUSG00000028648, ENSMUSG00000044894, ENSMUSG00000020477, ENSMUSG00000059534, ENSMUSG00000035202, ENSMUSG00000025290, ENSMUSG00000079037, ENSMUSG00000034892, ENSMUSG00000028062, ENSMUSG00000020485, ENSMUSG00000063316, ENSMUSG00000031590, ENSMUSG00000038374, ENSMUSG00000030744, ENSMUSG00000006728, ENSMUSG00000028234, ENSMUSG00000039221, ENSMUSG00000029038, ENSMUSG00000040952, ENSMUSG00000076617, ENSMUSG00000030057, ENSMUSG00000024309, ENSMUSG00000042770, ENSMUSG00000020766, ENSMUSG00000021607, ENSMUSG00000036748, ENSMUSG00000049960, ENSMUSG00000060860, ENSMUSG00000029632, ENSMUSG00000028861, ENSMUSG00000060036, ENSMUSG00000028964, ENSMUSG00000061983, ENSMUSG00000038489, ENSMUSG00000028367, ENSMUSG00000005354, ENSMUSG00000057278, ENSMUSG00000004285, ENSMUSG00000021606, ENSMUSG00000022820, ENSMUSG00000065990, ENSMUSG00000037601, ENSMUSG00000002477, ENSMUSG00000030432, ENSMUSG00000061477, ENSMUSG00000024038, ENSMUSG00000063457, ENSMUSG00000031059, ENSMUSG00000031848, ENSMUSG00000008668, ENSMUSG00000014294, ENSMUSG00000069744, ENSMUSG00000014769, ENSMUSG00000039001, ENSMUSG00000050014, ENSMUSG00000062328, ENSMUSG00000045128, ENSMUSG00000028756, ENSMUSG00000079435, ENSMUSG00000028651, ENSMUSG00000007892, ENSMUSG00000052429, ENSMUSG00000047215, ENSMUSG00000007891, ENSMUSG00000000782, ENSMUSG00000033938, ENSMUSG00000046330, ENSMUSG00000079641, ENSMUSG00000004268, ENSMUSG00000027613, ENSMUSG00000019929, ENSMUSG00000033020, ENSMUSG00000034345, ENSMUSG00000018286, ENSMUSG00000033735, ENSMUSG00000029066, ENSMUSG00000022601, ENSMUSG00000044475, ENSMUSG00000075706, ENSMUSG00000036850, ENSMUSG00000021024, ENSMUSG00000020180, ENSMUSG00000030804, ENSMUSG00000020736, ENSMUSG00000024914, ENSMUSG00000038274, ENSMUSG00000022400, ENSMUSG00000032171, ENSMUSG00000020444, ENSMUSG00000017404, ENSMUSG00000074129, ENSMUSG00000002379, ENSMUSG00000038900, ENSMUSG00000010376, ENSMUSG00000046865, ENSMUSG00000063882, ENSMUSG00000006333, ENSMUSG00000036199, ENSMUSG00000058267, ENSMUSG00000016554, ENSMUSG00000073676, ENSMUSG00000000563, ENSMUSG00000055839, ENSMUSG00000043716, ENSMUSG00000028081, ENSMUSG00000005779, ENSMUSG00000053565, ENSMUSG00000024844, ENSMUSG00000036781, ENSMUSG00000023089, ENSMUSG00000016427, ENSMUSG00000032966, ENSMUSG00000020163, ENSMUSG00000039640, ENSMUSG00000046364, ENSMUSG00000020460, ENSMUSG00000041881, ENSMUSG00000042541, ENSMUSG00000042747, ENSMUSG00000071662, ENSMUSG00000022982, ENSMUSG00000028495, ENSMUSG00000003970
## 6 ENSMUSG00000071866, ENSMUSG00000025967, ENSMUSG00000025794, ENSMUSG00000000740, ENSMUSG00000071415, ENSMUSG00000055762, ENSMUSG00000062997, ENSMUSG00000051234, ENSMUSG00000037563, ENSMUSG00000060636, ENSMUSG00000021453, ENSMUSG00000020477, ENSMUSG00000048758, ENSMUSG00000035202, ENSMUSG00000025290, ENSMUSG00000025508, ENSMUSG00000020307, ENSMUSG00000034892, ENSMUSG00000028062, ENSMUSG00000063316, ENSMUSG00000037805, ENSMUSG00000030122, ENSMUSG00000030744, ENSMUSG00000006728, ENSMUSG00000024608, ENSMUSG00000045948, ENSMUSG00000028234, ENSMUSG00000039221, ENSMUSG00000012848, ENSMUSG00000059325, ENSMUSG00000057841, ENSMUSG00000076617, ENSMUSG00000040952, ENSMUSG00000021607, ENSMUSG00000024309, ENSMUSG00000049960, ENSMUSG00000036748, ENSMUSG00000060860, ENSMUSG00000028861, ENSMUSG00000060036, ENSMUSG00000061983, ENSMUSG00000054312, ENSMUSG00000061787, ENSMUSG00000065990, ENSMUSG00000031375, ENSMUSG00000041841, ENSMUSG00000024902, ENSMUSG00000030432, ENSMUSG00000026750, ENSMUSG00000056399, ENSMUSG00000061477, ENSMUSG00000025362, ENSMUSG00000049517, ENSMUSG00000063457, ENSMUSG00000008668, ENSMUSG00000069744, ENSMUSG00000014769, ENSMUSG00000078812, ENSMUSG00000062006, ENSMUSG00000039001, ENSMUSG00000032518, ENSMUSG00000062328, ENSMUSG00000045128, ENSMUSG00000059070, ENSMUSG00000028756, ENSMUSG00000041453, ENSMUSG00000028651, ENSMUSG00000079435, ENSMUSG00000007892, ENSMUSG00000052429, ENSMUSG00000047215, ENSMUSG00000030357, ENSMUSG00000006941, ENSMUSG00000035478, ENSMUSG00000079641, ENSMUSG00000046330, ENSMUSG00000059291, ENSMUSG00000027613, ENSMUSG00000019929, ENSMUSG00000018286, ENSMUSG00000036835, ENSMUSG00000029066, ENSMUSG00000023939, ENSMUSG00000022601, ENSMUSG00000035530, ENSMUSG00000036850, ENSMUSG00000030871, ENSMUSG00000021024, ENSMUSG00000028936, ENSMUSG00000047676, ENSMUSG00000047675, ENSMUSG00000003429, ENSMUSG00000005161, ENSMUSG00000038274, ENSMUSG00000022400, ENSMUSG00000008683, ENSMUSG00000032171, ENSMUSG00000008682, ENSMUSG00000073702, ENSMUSG00000067288, ENSMUSG00000062963, ENSMUSG00000017404, ENSMUSG00000074129, ENSMUSG00000030879, ENSMUSG00000038900, ENSMUSG00000010376, ENSMUSG00000006333, ENSMUSG00000021917, ENSMUSG00000016554, ENSMUSG00000058267, ENSMUSG00000073676, ENSMUSG00000001289, ENSMUSG00000043716, ENSMUSG00000055839, ENSMUSG00000060938, ENSMUSG00000067274, ENSMUSG00000049751, ENSMUSG00000028081, ENSMUSG00000005779, ENSMUSG00000053565, ENSMUSG00000058600, ENSMUSG00000036781, ENSMUSG00000057322, ENSMUSG00000032966, ENSMUSG00000039640, ENSMUSG00000046364, ENSMUSG00000020460, ENSMUSG00000044533, ENSMUSG00000022234, ENSMUSG00000031029, ENSMUSG00000042747, ENSMUSG00000022982, ENSMUSG00000010406, ENSMUSG00000028495, ENSMUSG00000031320, ENSMUSG00000057863, ENSMUSG00000003970
## List.Total Pop.Hits Pop.Total Fold.Enrichment Bonferroni Benjamini
## 1 380 151 15404 22.281840 1.288995e-90 1.288995e-90
## 2 373 319 14219 11.233042 1.022150e-69 1.022150e-69
## 3 380 450 15404 7.927205 4.601697e-51 2.300849e-51
## 4 373 9252 14219 1.392648 8.197138e-28 4.098569e-28
## 5 373 5857 14219 1.646666 1.112110e-22 3.707033e-23
## 6 373 2088 14219 2.464697 3.574572e-22 8.936430e-23
## FDR
## 1 4.267656e-90
## 2 1.134887e-69
## 3 1.523548e-50
## 4 9.101232e-28
## 5 1.234769e-22
## 6 3.968826e-22
Here starts the automatically generated code
2016-06-16 19:31:18 and the DAVID*_result*.csv files has been saved in the BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/DEC_DOWN_E2_UP_genes_in_intersection.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list3
, db.selected:
KEGG_PATHWAY
, analysis.type:
Pathway
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
The list of called functions:
GetSpecieCode
## function (specie)
## {
## switch(specie, HUMAN = {
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## }, MOUSE = {
## dataset = "mmusculus_gene_ensembl"
## attribute = "mgi_symbol"
## }, DROSOPHILA = {
## dataset = "dmelanogaster_gene_ensembl"
## attribute = "bdgp_symbol"
## }, ZEBRAFISH = {
## dataset = "drerio_gene_ensembl"
## attribute = "zfin_symbol"
## }, {
## print("WARNING: no species detected! Using, HUMAN!")
## dialog <- MyDialog(window, "warning", message = "no species detected! Using, HUMAN!",
## title = "WARNING")
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## })
## return(list(dataset = dataset, attribute = attribute))
## }
## <environment: namespace:RNASeqGUI>
ConvertList
## function (id.list, map)
## {
## res.map <- apply(id.list, 1, function(x) {
## which(map[, 1] %in% x)
## })
## print(head(res.map))
## print(length(res.map))
## print(dim(id.list)[1])
## if (length(res.map) == dim(id.list)[1]) {
## id.list.n <- lapply(res.map, function(item) {
## if (length(item) > 0) {
## map[item[1], 2]
## }
## else {
## map[item, 2]
## }
## })
## }
## else {
## if (length(res.map) == 0) {
## print("problem res.map")
## }
## else if (length(id.list) == 0) {
## print("problem id.list")
## }
## }
## return(unlist(id.list.n))
## }
## <environment: namespace:RNASeqGUI>
DavidConnect
## function (user.mail = "rnaseqgui@na.iac.cnr.it")
## {
## if (!exists("david")) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## else {
## if (!is.connected(david)) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## }
## if (getTimeOut(david) == 30000) {
## setTimeOut(david, 5e+05)
## }
## if (is.null(getHttpProtocolVersion(david))) {
## setHttpProtocolVersion(david, "HTTP/1.0")
## }
## return(david)
## }
## <environment: namespace:RNASeqGUI>
DavidAnalysis
## function (main.window = NULL, file.name, gene.list.position,
## gene.identifier, list.type, list.name, out.file.name, db.selected,
## analysis.type, Project, specie, filter.list)
## {
## require("RDAVIDWebService")
## require("biomaRt")
## if (Sys.info()[[1]] == "Windows") {
## sys.sep = "\\"
## }
## else {
## sys.sep = "/"
## }
## sep.pos <- gregexpr(pattern = sys.sep, file.name, fixed = F)[[1]]
## out.file.name <- substring(file.name, sep.pos[length(sep.pos)] +
## 1)
## david.path <- file.path("RNASeqGUI_Projects", Project, "Results",
## "DAVID")
## david.db.path <- file.path(david.path, paste(db.selected,
## collapse = "_", sep = ""))
## dir.create(david.path, recursive = TRUE)
## if (analysis.type == "Pathway") {
## cat("Performing pathway analysis on ", db.selected, "...\n")
## this.name <- paste0(out.file.name, "_DAVID_Pathway_",
## db.selected)
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## if (length(grep("ALL", db.selected)) != 0) {
## cat("Performing ALL GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_ALL_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## cat("Performing FAT GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_FAT_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_DAVID_FAT_GO_results.txt")
## }
## }
## dbname <- paste0("david_", this.name, "_db")
## db <- InitDb(db.name = dbname, db.path = file.path("RNASeqGUI_Projects",
## Project, "Logs", "cache"))
## SaveInCache(db, file.name, "filename_key")
## SaveInCache(db, Project, "project_key")
## SaveInCache(db, gene.list.position, "genelistposition_key")
## SaveInCache(db, gene.identifier, "geneidentifier_key")
## SaveInCache(db, list.type, "listtype_key")
## SaveInCache(db, list.name, "listname_key")
## SaveInCache(db, db.selected, "dbselected_key")
## SaveInCache(db, analysis.type, "analysistype_key")
## SaveInCache(db, out.file.name, "outfilename_key")
## SaveInCache(db, specie, "specie_key")
## id.list <- read.table(file = file.name, header = TRUE, as.is = TRUE)
## id.list <- id.list[, gene.list.position, drop = TRUE]
## if (gene.identifier == "GENCODE") {
## id.list <- unlist(lapply(id.list, function(x) {
## substring(x, 0, regexpr(pattern = ".", x, fixed = T)[1] -
## 1)
## }))
## gene.identifier <- "ENSEMBL_GENE_ID"
## }
## if (gene.identifier == "GENE_SYMBOL") {
## if (specie != "") {
## print("converting gene_symbol to ensembl_gene_id ... ")
## specie.list <- GetSpecieCode(specie)
## print(specie.list$dataset)
## ensembl <- useMart("ENSEMBL_MART_ENSEMBL", host = "www.ensembl.org",
## dataset = specie.list$dataset)
## ensembl.map <- getBM(attributes = c("external_gene_name",
## "ensembl_gene_id"), mart = ensembl)
## id.list <- ConvertList(id.list, ensembl.map)
## gene.identifier <- "ENSEMBL_GENE_ID"
## print("done!")
## }
## else {
## message("ERROR: empty Specie")
## }
## }
## print("check if list is too short")
## if (length(id.list) > 3000) {
## MyDialog(parent.w = main.window, type.d = "warning",
## message = paste0("You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"),
## title = "WARNING")
## message(paste0("WARNING: You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"))
## id.list <- id.list[1:3000]
## }
## else {
## MyDialog(parent.w = main.window, type.d = "info", message = paste0("You submitted ",
## length(id.list), " genes!"), title = "INFORMATION")
## print(paste0("You submitted ", length(id.list), " genes!"))
## }
## print(head(id.list))
## SaveInCache(db, id.list, "idlist_key")
## print("Querying DAVID...")
## w.wind <- WaitingWindow(message = "Please wait while querying DAVID",
## parent.w = main.window)
## Sys.sleep(1)
## david <- DavidConnect()
## if (is.connected(david)) {
## result <- addList(david, id.list, idType = gene.identifier,
## listName = list.name, listType = list.type)
## setAnnotationCategories(david, db.selected)
## results.final <- getFunctionalAnnotationChart(david)
## w.wind$destroy()
## print("done!")
## if (dim(results.final)[1] != 0) {
## if (filter.list$flag) {
## results.final <- results.final[results.final[,
## filter.list$col.name] < filter.list$thr, ]
## }
## SaveInCache(db, filter.list, "filterlist_key")
## SaveInCache(db, results.final, "resultsfinal_key")
## write.table(results.final, file = out.file.name,
## quote = FALSE, row.names = FALSE, sep = "\t")
## cat("File ", out.file.name, " written on disk!\n")
## print(david.db.path)
## input.file.name <- substring(file.name, max(gregexpr("/",
## file.name)[[1]]) + 1)
## input.file.name <- gsub(".txt", "", input.file.name)
## input.file.name <- gsub(" ", "_", input.file.name)
## SavePathwaysList(results.final, david.db.path, just.file.name = input.file.name)
## }
## else {
## results.final <- data.frame()
## SaveInCache(db, results.final, "resultsfinal_key")
## cat("David produced no Results on ", db.selected,
## "\n")
## }
## }
## else {
## w.wind$destroy()
## message("ERROR: DAVID disconnected!")
## }
## PrintDavidReport(db, dbname)
## return(results.final)
## }
## <environment: namespace:RNASeqGUI>
This R code has been run:
print(getwd())
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Logs"
db <- InitDb(db.name='david_DEC_DOWN_E2_UP_genes_in_intersection.txt_DAVID_Pathway_KEGG_PATHWAY_db' , db.path='cache')
#results.data.frame <- DavidAnalysis(file.name, gene.list.position, gene.identifier, list.type, list.name, out.file.name, db.selected, analysis.type, Project)
results.data.frame <- LoadCachedObject(db, 'resultsfinal_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(results.data.frame))
## Category Term Count X.
## 1 KEGG_PATHWAY mmu04060:Cytokine-cytokine receptor interaction 4 40
## PValue
## 1 0.0007128032
## Genes
## 1 ENSMUSG00000026070, ENSMUSG00000004296, ENSMUSG00000018752, ENSMUSG00000017652
## List.Total Pop.Hits Pop.Total Fold.Enrichment Bonferroni Benjamini
## 1 6 244 5738 15.6776 0.01063886 0.01063886
## FDR
## 1 0.494533
Here starts the automatically generated code
2016-06-16 19:31:59 and the DAVID*_result*.csv files has been saved in the BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/DEC_DOWN_E2_UP_genes_in_intersection.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list3
, db.selected:
GOTERM_MF_ALL
, analysis.type:
GO
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/DEC_DOWN_E2_UP_genes_in_intersection.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list3
, db.selected:
GOTERM_BP_ALL
, analysis.type:
GO
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
The list of called functions:
GetSpecieCode
## function (specie)
## {
## switch(specie, HUMAN = {
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## }, MOUSE = {
## dataset = "mmusculus_gene_ensembl"
## attribute = "mgi_symbol"
## }, DROSOPHILA = {
## dataset = "dmelanogaster_gene_ensembl"
## attribute = "bdgp_symbol"
## }, ZEBRAFISH = {
## dataset = "drerio_gene_ensembl"
## attribute = "zfin_symbol"
## }, {
## print("WARNING: no species detected! Using, HUMAN!")
## dialog <- MyDialog(window, "warning", message = "no species detected! Using, HUMAN!",
## title = "WARNING")
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## })
## return(list(dataset = dataset, attribute = attribute))
## }
## <environment: namespace:RNASeqGUI>
ConvertList
## function (id.list, map)
## {
## res.map <- apply(id.list, 1, function(x) {
## which(map[, 1] %in% x)
## })
## print(head(res.map))
## print(length(res.map))
## print(dim(id.list)[1])
## if (length(res.map) == dim(id.list)[1]) {
## id.list.n <- lapply(res.map, function(item) {
## if (length(item) > 0) {
## map[item[1], 2]
## }
## else {
## map[item, 2]
## }
## })
## }
## else {
## if (length(res.map) == 0) {
## print("problem res.map")
## }
## else if (length(id.list) == 0) {
## print("problem id.list")
## }
## }
## return(unlist(id.list.n))
## }
## <environment: namespace:RNASeqGUI>
DavidConnect
## function (user.mail = "rnaseqgui@na.iac.cnr.it")
## {
## if (!exists("david")) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## else {
## if (!is.connected(david)) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## }
## if (getTimeOut(david) == 30000) {
## setTimeOut(david, 5e+05)
## }
## if (is.null(getHttpProtocolVersion(david))) {
## setHttpProtocolVersion(david, "HTTP/1.0")
## }
## return(david)
## }
## <environment: namespace:RNASeqGUI>
DavidAnalysis
## function (main.window = NULL, file.name, gene.list.position,
## gene.identifier, list.type, list.name, out.file.name, db.selected,
## analysis.type, Project, specie, filter.list)
## {
## require("RDAVIDWebService")
## require("biomaRt")
## if (Sys.info()[[1]] == "Windows") {
## sys.sep = "\\"
## }
## else {
## sys.sep = "/"
## }
## sep.pos <- gregexpr(pattern = sys.sep, file.name, fixed = F)[[1]]
## out.file.name <- substring(file.name, sep.pos[length(sep.pos)] +
## 1)
## david.path <- file.path("RNASeqGUI_Projects", Project, "Results",
## "DAVID")
## david.db.path <- file.path(david.path, paste(db.selected,
## collapse = "_", sep = ""))
## dir.create(david.path, recursive = TRUE)
## if (analysis.type == "Pathway") {
## cat("Performing pathway analysis on ", db.selected, "...\n")
## this.name <- paste0(out.file.name, "_DAVID_Pathway_",
## db.selected)
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## if (length(grep("ALL", db.selected)) != 0) {
## cat("Performing ALL GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_ALL_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## cat("Performing FAT GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_FAT_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_DAVID_FAT_GO_results.txt")
## }
## }
## dbname <- paste0("david_", this.name, "_db")
## db <- InitDb(db.name = dbname, db.path = file.path("RNASeqGUI_Projects",
## Project, "Logs", "cache"))
## SaveInCache(db, file.name, "filename_key")
## SaveInCache(db, Project, "project_key")
## SaveInCache(db, gene.list.position, "genelistposition_key")
## SaveInCache(db, gene.identifier, "geneidentifier_key")
## SaveInCache(db, list.type, "listtype_key")
## SaveInCache(db, list.name, "listname_key")
## SaveInCache(db, db.selected, "dbselected_key")
## SaveInCache(db, analysis.type, "analysistype_key")
## SaveInCache(db, out.file.name, "outfilename_key")
## SaveInCache(db, specie, "specie_key")
## id.list <- read.table(file = file.name, header = TRUE, as.is = TRUE)
## id.list <- id.list[, gene.list.position, drop = TRUE]
## if (gene.identifier == "GENCODE") {
## id.list <- unlist(lapply(id.list, function(x) {
## substring(x, 0, regexpr(pattern = ".", x, fixed = T)[1] -
## 1)
## }))
## gene.identifier <- "ENSEMBL_GENE_ID"
## }
## if (gene.identifier == "GENE_SYMBOL") {
## if (specie != "") {
## print("converting gene_symbol to ensembl_gene_id ... ")
## specie.list <- GetSpecieCode(specie)
## print(specie.list$dataset)
## ensembl <- useMart("ENSEMBL_MART_ENSEMBL", host = "www.ensembl.org",
## dataset = specie.list$dataset)
## ensembl.map <- getBM(attributes = c("external_gene_name",
## "ensembl_gene_id"), mart = ensembl)
## id.list <- ConvertList(id.list, ensembl.map)
## gene.identifier <- "ENSEMBL_GENE_ID"
## print("done!")
## }
## else {
## message("ERROR: empty Specie")
## }
## }
## print("check if list is too short")
## if (length(id.list) > 3000) {
## MyDialog(parent.w = main.window, type.d = "warning",
## message = paste0("You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"),
## title = "WARNING")
## message(paste0("WARNING: You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"))
## id.list <- id.list[1:3000]
## }
## else {
## MyDialog(parent.w = main.window, type.d = "info", message = paste0("You submitted ",
## length(id.list), " genes!"), title = "INFORMATION")
## print(paste0("You submitted ", length(id.list), " genes!"))
## }
## print(head(id.list))
## SaveInCache(db, id.list, "idlist_key")
## print("Querying DAVID...")
## w.wind <- WaitingWindow(message = "Please wait while querying DAVID",
## parent.w = main.window)
## Sys.sleep(1)
## david <- DavidConnect()
## if (is.connected(david)) {
## result <- addList(david, id.list, idType = gene.identifier,
## listName = list.name, listType = list.type)
## setAnnotationCategories(david, db.selected)
## results.final <- getFunctionalAnnotationChart(david)
## w.wind$destroy()
## print("done!")
## if (dim(results.final)[1] != 0) {
## if (filter.list$flag) {
## results.final <- results.final[results.final[,
## filter.list$col.name] < filter.list$thr, ]
## }
## SaveInCache(db, filter.list, "filterlist_key")
## SaveInCache(db, results.final, "resultsfinal_key")
## write.table(results.final, file = out.file.name,
## quote = FALSE, row.names = FALSE, sep = "\t")
## cat("File ", out.file.name, " written on disk!\n")
## print(david.db.path)
## input.file.name <- substring(file.name, max(gregexpr("/",
## file.name)[[1]]) + 1)
## input.file.name <- gsub(".txt", "", input.file.name)
## input.file.name <- gsub(" ", "_", input.file.name)
## SavePathwaysList(results.final, david.db.path, just.file.name = input.file.name)
## }
## else {
## results.final <- data.frame()
## SaveInCache(db, results.final, "resultsfinal_key")
## cat("David produced no Results on ", db.selected,
## "\n")
## }
## }
## else {
## w.wind$destroy()
## message("ERROR: DAVID disconnected!")
## }
## PrintDavidReport(db, dbname)
## return(results.final)
## }
## <environment: namespace:RNASeqGUI>
This R code has been run:
print(getwd())
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Logs"
db <- InitDb(db.name='david_DEC_DOWN_E2_UP_genes_in_intersection.txt_DAVID_ALL_GO_GOTERM_MF_ALL_GOTERM_BP_ALL_db' , db.path='cache')
#results.data.frame <- DavidAnalysis(file.name, gene.list.position, gene.identifier, list.type, list.name, out.file.name, db.selected, analysis.type, Project)
results.data.frame <- LoadCachedObject(db, 'resultsfinal_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(results.data.frame))
## [1] Category Term Count X.
## [5] PValue Genes List.Total Pop.Hits
## [9] Pop.Total Fold.Enrichment Bonferroni Benjamini
## [13] FDR
## <0 rows> (or 0-length row.names)
Here starts the automatically generated code
2016-06-16 19:32:58 and the DAVID*_result*.csv files has been saved in the BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/DEC_UP_E2_DOWN_genes_in_intersection.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list4
, db.selected:
KEGG_PATHWAY
, analysis.type:
Pathway
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
The list of called functions:
GetSpecieCode
## function (specie)
## {
## switch(specie, HUMAN = {
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## }, MOUSE = {
## dataset = "mmusculus_gene_ensembl"
## attribute = "mgi_symbol"
## }, DROSOPHILA = {
## dataset = "dmelanogaster_gene_ensembl"
## attribute = "bdgp_symbol"
## }, ZEBRAFISH = {
## dataset = "drerio_gene_ensembl"
## attribute = "zfin_symbol"
## }, {
## print("WARNING: no species detected! Using, HUMAN!")
## dialog <- MyDialog(window, "warning", message = "no species detected! Using, HUMAN!",
## title = "WARNING")
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## })
## return(list(dataset = dataset, attribute = attribute))
## }
## <environment: namespace:RNASeqGUI>
ConvertList
## function (id.list, map)
## {
## res.map <- apply(id.list, 1, function(x) {
## which(map[, 1] %in% x)
## })
## print(head(res.map))
## print(length(res.map))
## print(dim(id.list)[1])
## if (length(res.map) == dim(id.list)[1]) {
## id.list.n <- lapply(res.map, function(item) {
## if (length(item) > 0) {
## map[item[1], 2]
## }
## else {
## map[item, 2]
## }
## })
## }
## else {
## if (length(res.map) == 0) {
## print("problem res.map")
## }
## else if (length(id.list) == 0) {
## print("problem id.list")
## }
## }
## return(unlist(id.list.n))
## }
## <environment: namespace:RNASeqGUI>
DavidConnect
## function (user.mail = "rnaseqgui@na.iac.cnr.it")
## {
## if (!exists("david")) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## else {
## if (!is.connected(david)) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## }
## if (getTimeOut(david) == 30000) {
## setTimeOut(david, 5e+05)
## }
## if (is.null(getHttpProtocolVersion(david))) {
## setHttpProtocolVersion(david, "HTTP/1.0")
## }
## return(david)
## }
## <environment: namespace:RNASeqGUI>
DavidAnalysis
## function (main.window = NULL, file.name, gene.list.position,
## gene.identifier, list.type, list.name, out.file.name, db.selected,
## analysis.type, Project, specie, filter.list)
## {
## require("RDAVIDWebService")
## require("biomaRt")
## if (Sys.info()[[1]] == "Windows") {
## sys.sep = "\\"
## }
## else {
## sys.sep = "/"
## }
## sep.pos <- gregexpr(pattern = sys.sep, file.name, fixed = F)[[1]]
## out.file.name <- substring(file.name, sep.pos[length(sep.pos)] +
## 1)
## david.path <- file.path("RNASeqGUI_Projects", Project, "Results",
## "DAVID")
## david.db.path <- file.path(david.path, paste(db.selected,
## collapse = "_", sep = ""))
## dir.create(david.path, recursive = TRUE)
## if (analysis.type == "Pathway") {
## cat("Performing pathway analysis on ", db.selected, "...\n")
## this.name <- paste0(out.file.name, "_DAVID_Pathway_",
## db.selected)
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## if (length(grep("ALL", db.selected)) != 0) {
## cat("Performing ALL GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_ALL_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## cat("Performing FAT GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_FAT_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_DAVID_FAT_GO_results.txt")
## }
## }
## dbname <- paste0("david_", this.name, "_db")
## db <- InitDb(db.name = dbname, db.path = file.path("RNASeqGUI_Projects",
## Project, "Logs", "cache"))
## SaveInCache(db, file.name, "filename_key")
## SaveInCache(db, Project, "project_key")
## SaveInCache(db, gene.list.position, "genelistposition_key")
## SaveInCache(db, gene.identifier, "geneidentifier_key")
## SaveInCache(db, list.type, "listtype_key")
## SaveInCache(db, list.name, "listname_key")
## SaveInCache(db, db.selected, "dbselected_key")
## SaveInCache(db, analysis.type, "analysistype_key")
## SaveInCache(db, out.file.name, "outfilename_key")
## SaveInCache(db, specie, "specie_key")
## id.list <- read.table(file = file.name, header = TRUE, as.is = TRUE)
## id.list <- id.list[, gene.list.position, drop = TRUE]
## if (gene.identifier == "GENCODE") {
## id.list <- unlist(lapply(id.list, function(x) {
## substring(x, 0, regexpr(pattern = ".", x, fixed = T)[1] -
## 1)
## }))
## gene.identifier <- "ENSEMBL_GENE_ID"
## }
## if (gene.identifier == "GENE_SYMBOL") {
## if (specie != "") {
## print("converting gene_symbol to ensembl_gene_id ... ")
## specie.list <- GetSpecieCode(specie)
## print(specie.list$dataset)
## ensembl <- useMart("ENSEMBL_MART_ENSEMBL", host = "www.ensembl.org",
## dataset = specie.list$dataset)
## ensembl.map <- getBM(attributes = c("external_gene_name",
## "ensembl_gene_id"), mart = ensembl)
## id.list <- ConvertList(id.list, ensembl.map)
## gene.identifier <- "ENSEMBL_GENE_ID"
## print("done!")
## }
## else {
## message("ERROR: empty Specie")
## }
## }
## print("check if list is too short")
## if (length(id.list) > 3000) {
## MyDialog(parent.w = main.window, type.d = "warning",
## message = paste0("You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"),
## title = "WARNING")
## message(paste0("WARNING: You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"))
## id.list <- id.list[1:3000]
## }
## else {
## MyDialog(parent.w = main.window, type.d = "info", message = paste0("You submitted ",
## length(id.list), " genes!"), title = "INFORMATION")
## print(paste0("You submitted ", length(id.list), " genes!"))
## }
## print(head(id.list))
## SaveInCache(db, id.list, "idlist_key")
## print("Querying DAVID...")
## w.wind <- WaitingWindow(message = "Please wait while querying DAVID",
## parent.w = main.window)
## Sys.sleep(1)
## david <- DavidConnect()
## if (is.connected(david)) {
## result <- addList(david, id.list, idType = gene.identifier,
## listName = list.name, listType = list.type)
## setAnnotationCategories(david, db.selected)
## results.final <- getFunctionalAnnotationChart(david)
## w.wind$destroy()
## print("done!")
## if (dim(results.final)[1] != 0) {
## if (filter.list$flag) {
## results.final <- results.final[results.final[,
## filter.list$col.name] < filter.list$thr, ]
## }
## SaveInCache(db, filter.list, "filterlist_key")
## SaveInCache(db, results.final, "resultsfinal_key")
## write.table(results.final, file = out.file.name,
## quote = FALSE, row.names = FALSE, sep = "\t")
## cat("File ", out.file.name, " written on disk!\n")
## print(david.db.path)
## input.file.name <- substring(file.name, max(gregexpr("/",
## file.name)[[1]]) + 1)
## input.file.name <- gsub(".txt", "", input.file.name)
## input.file.name <- gsub(" ", "_", input.file.name)
## SavePathwaysList(results.final, david.db.path, just.file.name = input.file.name)
## }
## else {
## results.final <- data.frame()
## SaveInCache(db, results.final, "resultsfinal_key")
## cat("David produced no Results on ", db.selected,
## "\n")
## }
## }
## else {
## w.wind$destroy()
## message("ERROR: DAVID disconnected!")
## }
## PrintDavidReport(db, dbname)
## return(results.final)
## }
## <environment: namespace:RNASeqGUI>
This R code has been run:
print(getwd())
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Logs"
db <- InitDb(db.name='david_DEC_UP_E2_DOWN_genes_in_intersection.txt_DAVID_Pathway_KEGG_PATHWAY_db' , db.path='cache')
#results.data.frame <- DavidAnalysis(file.name, gene.list.position, gene.identifier, list.type, list.name, out.file.name, db.selected, analysis.type, Project)
results.data.frame <- LoadCachedObject(db, 'resultsfinal_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(results.data.frame))
## [1] Category Term Count X.
## [5] PValue Genes List.Total Pop.Hits
## [9] Pop.Total Fold.Enrichment Bonferroni Benjamini
## [13] FDR
## <0 rows> (or 0-length row.names)
Here starts the automatically generated code
2016-06-16 19:33:39 and the DAVID*_result*.csv files has been saved in the BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/DEC_UP_E2_DOWN_genes_in_intersection.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list4
, db.selected:
GOTERM_MF_ALL
, analysis.type:
GO
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/DEC_UP_E2_DOWN_genes_in_intersection.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list4
, db.selected:
GOTERM_BP_ALL
, analysis.type:
GO
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
The list of called functions:
GetSpecieCode
## function (specie)
## {
## switch(specie, HUMAN = {
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## }, MOUSE = {
## dataset = "mmusculus_gene_ensembl"
## attribute = "mgi_symbol"
## }, DROSOPHILA = {
## dataset = "dmelanogaster_gene_ensembl"
## attribute = "bdgp_symbol"
## }, ZEBRAFISH = {
## dataset = "drerio_gene_ensembl"
## attribute = "zfin_symbol"
## }, {
## print("WARNING: no species detected! Using, HUMAN!")
## dialog <- MyDialog(window, "warning", message = "no species detected! Using, HUMAN!",
## title = "WARNING")
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## })
## return(list(dataset = dataset, attribute = attribute))
## }
## <environment: namespace:RNASeqGUI>
ConvertList
## function (id.list, map)
## {
## res.map <- apply(id.list, 1, function(x) {
## which(map[, 1] %in% x)
## })
## print(head(res.map))
## print(length(res.map))
## print(dim(id.list)[1])
## if (length(res.map) == dim(id.list)[1]) {
## id.list.n <- lapply(res.map, function(item) {
## if (length(item) > 0) {
## map[item[1], 2]
## }
## else {
## map[item, 2]
## }
## })
## }
## else {
## if (length(res.map) == 0) {
## print("problem res.map")
## }
## else if (length(id.list) == 0) {
## print("problem id.list")
## }
## }
## return(unlist(id.list.n))
## }
## <environment: namespace:RNASeqGUI>
DavidConnect
## function (user.mail = "rnaseqgui@na.iac.cnr.it")
## {
## if (!exists("david")) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## else {
## if (!is.connected(david)) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## }
## if (getTimeOut(david) == 30000) {
## setTimeOut(david, 5e+05)
## }
## if (is.null(getHttpProtocolVersion(david))) {
## setHttpProtocolVersion(david, "HTTP/1.0")
## }
## return(david)
## }
## <environment: namespace:RNASeqGUI>
DavidAnalysis
## function (main.window = NULL, file.name, gene.list.position,
## gene.identifier, list.type, list.name, out.file.name, db.selected,
## analysis.type, Project, specie, filter.list)
## {
## require("RDAVIDWebService")
## require("biomaRt")
## if (Sys.info()[[1]] == "Windows") {
## sys.sep = "\\"
## }
## else {
## sys.sep = "/"
## }
## sep.pos <- gregexpr(pattern = sys.sep, file.name, fixed = F)[[1]]
## out.file.name <- substring(file.name, sep.pos[length(sep.pos)] +
## 1)
## david.path <- file.path("RNASeqGUI_Projects", Project, "Results",
## "DAVID")
## david.db.path <- file.path(david.path, paste(db.selected,
## collapse = "_", sep = ""))
## dir.create(david.path, recursive = TRUE)
## if (analysis.type == "Pathway") {
## cat("Performing pathway analysis on ", db.selected, "...\n")
## this.name <- paste0(out.file.name, "_DAVID_Pathway_",
## db.selected)
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## if (length(grep("ALL", db.selected)) != 0) {
## cat("Performing ALL GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_ALL_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## cat("Performing FAT GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_FAT_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_DAVID_FAT_GO_results.txt")
## }
## }
## dbname <- paste0("david_", this.name, "_db")
## db <- InitDb(db.name = dbname, db.path = file.path("RNASeqGUI_Projects",
## Project, "Logs", "cache"))
## SaveInCache(db, file.name, "filename_key")
## SaveInCache(db, Project, "project_key")
## SaveInCache(db, gene.list.position, "genelistposition_key")
## SaveInCache(db, gene.identifier, "geneidentifier_key")
## SaveInCache(db, list.type, "listtype_key")
## SaveInCache(db, list.name, "listname_key")
## SaveInCache(db, db.selected, "dbselected_key")
## SaveInCache(db, analysis.type, "analysistype_key")
## SaveInCache(db, out.file.name, "outfilename_key")
## SaveInCache(db, specie, "specie_key")
## id.list <- read.table(file = file.name, header = TRUE, as.is = TRUE)
## id.list <- id.list[, gene.list.position, drop = TRUE]
## if (gene.identifier == "GENCODE") {
## id.list <- unlist(lapply(id.list, function(x) {
## substring(x, 0, regexpr(pattern = ".", x, fixed = T)[1] -
## 1)
## }))
## gene.identifier <- "ENSEMBL_GENE_ID"
## }
## if (gene.identifier == "GENE_SYMBOL") {
## if (specie != "") {
## print("converting gene_symbol to ensembl_gene_id ... ")
## specie.list <- GetSpecieCode(specie)
## print(specie.list$dataset)
## ensembl <- useMart("ENSEMBL_MART_ENSEMBL", host = "www.ensembl.org",
## dataset = specie.list$dataset)
## ensembl.map <- getBM(attributes = c("external_gene_name",
## "ensembl_gene_id"), mart = ensembl)
## id.list <- ConvertList(id.list, ensembl.map)
## gene.identifier <- "ENSEMBL_GENE_ID"
## print("done!")
## }
## else {
## message("ERROR: empty Specie")
## }
## }
## print("check if list is too short")
## if (length(id.list) > 3000) {
## MyDialog(parent.w = main.window, type.d = "warning",
## message = paste0("You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"),
## title = "WARNING")
## message(paste0("WARNING: You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"))
## id.list <- id.list[1:3000]
## }
## else {
## MyDialog(parent.w = main.window, type.d = "info", message = paste0("You submitted ",
## length(id.list), " genes!"), title = "INFORMATION")
## print(paste0("You submitted ", length(id.list), " genes!"))
## }
## print(head(id.list))
## SaveInCache(db, id.list, "idlist_key")
## print("Querying DAVID...")
## w.wind <- WaitingWindow(message = "Please wait while querying DAVID",
## parent.w = main.window)
## Sys.sleep(1)
## david <- DavidConnect()
## if (is.connected(david)) {
## result <- addList(david, id.list, idType = gene.identifier,
## listName = list.name, listType = list.type)
## setAnnotationCategories(david, db.selected)
## results.final <- getFunctionalAnnotationChart(david)
## w.wind$destroy()
## print("done!")
## if (dim(results.final)[1] != 0) {
## if (filter.list$flag) {
## results.final <- results.final[results.final[,
## filter.list$col.name] < filter.list$thr, ]
## }
## SaveInCache(db, filter.list, "filterlist_key")
## SaveInCache(db, results.final, "resultsfinal_key")
## write.table(results.final, file = out.file.name,
## quote = FALSE, row.names = FALSE, sep = "\t")
## cat("File ", out.file.name, " written on disk!\n")
## print(david.db.path)
## input.file.name <- substring(file.name, max(gregexpr("/",
## file.name)[[1]]) + 1)
## input.file.name <- gsub(".txt", "", input.file.name)
## input.file.name <- gsub(" ", "_", input.file.name)
## SavePathwaysList(results.final, david.db.path, just.file.name = input.file.name)
## }
## else {
## results.final <- data.frame()
## SaveInCache(db, results.final, "resultsfinal_key")
## cat("David produced no Results on ", db.selected,
## "\n")
## }
## }
## else {
## w.wind$destroy()
## message("ERROR: DAVID disconnected!")
## }
## PrintDavidReport(db, dbname)
## return(results.final)
## }
## <environment: namespace:RNASeqGUI>
This R code has been run:
print(getwd())
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Logs"
db <- InitDb(db.name='david_DEC_UP_E2_DOWN_genes_in_intersection.txt_DAVID_ALL_GO_GOTERM_MF_ALL_GOTERM_BP_ALL_db' , db.path='cache')
#results.data.frame <- DavidAnalysis(file.name, gene.list.position, gene.identifier, list.type, list.name, out.file.name, db.selected, analysis.type, Project)
results.data.frame <- LoadCachedObject(db, 'resultsfinal_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(results.data.frame))
## Category Term Count X.
## 1 GOTERM_BP_ALL GO:0006955~immune response 18 21.428571
## 2 GOTERM_BP_ALL GO:0002376~immune system process 19 22.619048
## 3 GOTERM_BP_ALL GO:0050896~response to stimulus 29 34.523810
## 4 GOTERM_BP_ALL GO:0009615~response to virus 6 7.142857
## 5 GOTERM_MF_ALL GO:0032555~purine ribonucleotide binding 22 26.190476
## 6 GOTERM_MF_ALL GO:0032553~ribonucleotide binding 22 26.190476
## PValue
## 1 3.939597e-13
## 2 1.531680e-10
## 3 1.836444e-09
## 4 8.156406e-06
## 5 1.412989e-05
## 6 1.412989e-05
## Genes
## 1 ENSMUSG00000032661, ENSMUSG00000046879, ENSMUSG00000056116, ENSMUSG00000015947, ENSMUSG00000040296, ENSMUSG00000070427, ENSMUSG00000026656, ENSMUSG00000020641, ENSMUSG00000052776, ENSMUSG00000032690, ENSMUSG00000028270, ENSMUSG00000035373, ENSMUSG00000055172, ENSMUSG00000029561, ENSMUSG00000025498, ENSMUSG00000066861, ENSMUSG00000035385, ENSMUSG00000017830
## 2 ENSMUSG00000032661, ENSMUSG00000046879, ENSMUSG00000056116, ENSMUSG00000015947, ENSMUSG00000040296, ENSMUSG00000070427, ENSMUSG00000026656, ENSMUSG00000020641, ENSMUSG00000052776, ENSMUSG00000038418, ENSMUSG00000032690, ENSMUSG00000028270, ENSMUSG00000035373, ENSMUSG00000055172, ENSMUSG00000029561, ENSMUSG00000025498, ENSMUSG00000066861, ENSMUSG00000035385, ENSMUSG00000017830
## 3 ENSMUSG00000032661, ENSMUSG00000046879, ENSMUSG00000015947, ENSMUSG00000040296, ENSMUSG00000070427, ENSMUSG00000026656, ENSMUSG00000052776, ENSMUSG00000006782, ENSMUSG00000038418, ENSMUSG00000026104, ENSMUSG00000028270, ENSMUSG00000035373, ENSMUSG00000029561, ENSMUSG00000035692, ENSMUSG00000021871, ENSMUSG00000073489, ENSMUSG00000056116, ENSMUSG00000079017, ENSMUSG00000020641, ENSMUSG00000032690, ENSMUSG00000021250, ENSMUSG00000055172, ENSMUSG00000025492, ENSMUSG00000078920, ENSMUSG00000019987, ENSMUSG00000025498, ENSMUSG00000066861, ENSMUSG00000017830, ENSMUSG00000035385
## 4 ENSMUSG00000079017, ENSMUSG00000040296, ENSMUSG00000020641, ENSMUSG00000035692, ENSMUSG00000025498, ENSMUSG00000052776
## 5 ENSMUSG00000032661, ENSMUSG00000035208, ENSMUSG00000082292, ENSMUSG00000046879, ENSMUSG00000037820, ENSMUSG00000040296, ENSMUSG00000078763, ENSMUSG00000000204, ENSMUSG00000052776, ENSMUSG00000032690, ENSMUSG00000072620, ENSMUSG00000028270, ENSMUSG00000027078, ENSMUSG00000078920, ENSMUSG00000029561, ENSMUSG00000020638, ENSMUSG00000066861, ENSMUSG00000027293, ENSMUSG00000060519, ENSMUSG00000078853, ENSMUSG00000017830, ENSMUSG00000069874
## 6 ENSMUSG00000032661, ENSMUSG00000035208, ENSMUSG00000082292, ENSMUSG00000046879, ENSMUSG00000037820, ENSMUSG00000040296, ENSMUSG00000078763, ENSMUSG00000000204, ENSMUSG00000052776, ENSMUSG00000032690, ENSMUSG00000072620, ENSMUSG00000028270, ENSMUSG00000027078, ENSMUSG00000078920, ENSMUSG00000029561, ENSMUSG00000020638, ENSMUSG00000066861, ENSMUSG00000027293, ENSMUSG00000060519, ENSMUSG00000078853, ENSMUSG00000017830, ENSMUSG00000069874
## List.Total Pop.Hits Pop.Total Fold.Enrichment Bonferroni Benjamini
## 1 53 471 14219 10.252854 2.702203e-10 2.702203e-10
## 2 53 791 14219 6.444219 1.050732e-07 5.253660e-08
## 3 53 2437 14219 3.192535 1.259800e-06 4.199334e-07
## 4 53 76 14219 21.180238 5.579692e-03 1.397851e-03
## 5 68 1796 15404 2.774859 2.032649e-03 2.032649e-03
## 6 68 1796 15404 2.774859 2.032649e-03 2.032649e-03
## FDR
## 1 5.924261e-10
## 2 2.303620e-07
## 3 2.761980e-06
## 4 1.226639e-02
## 5 1.675292e-02
## 6 1.675292e-02
Here starts the automatically generated code
2016-06-16 19:34:51 and the DAVID*_result*.csv files has been saved in the BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/genes_in_E2_UP_not_in_DEC.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list5
, db.selected:
KEGG_PATHWAY
, analysis.type:
Pathway
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
The list of called functions:
GetSpecieCode
## function (specie)
## {
## switch(specie, HUMAN = {
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## }, MOUSE = {
## dataset = "mmusculus_gene_ensembl"
## attribute = "mgi_symbol"
## }, DROSOPHILA = {
## dataset = "dmelanogaster_gene_ensembl"
## attribute = "bdgp_symbol"
## }, ZEBRAFISH = {
## dataset = "drerio_gene_ensembl"
## attribute = "zfin_symbol"
## }, {
## print("WARNING: no species detected! Using, HUMAN!")
## dialog <- MyDialog(window, "warning", message = "no species detected! Using, HUMAN!",
## title = "WARNING")
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## })
## return(list(dataset = dataset, attribute = attribute))
## }
## <environment: namespace:RNASeqGUI>
ConvertList
## function (id.list, map)
## {
## res.map <- apply(id.list, 1, function(x) {
## which(map[, 1] %in% x)
## })
## print(head(res.map))
## print(length(res.map))
## print(dim(id.list)[1])
## if (length(res.map) == dim(id.list)[1]) {
## id.list.n <- lapply(res.map, function(item) {
## if (length(item) > 0) {
## map[item[1], 2]
## }
## else {
## map[item, 2]
## }
## })
## }
## else {
## if (length(res.map) == 0) {
## print("problem res.map")
## }
## else if (length(id.list) == 0) {
## print("problem id.list")
## }
## }
## return(unlist(id.list.n))
## }
## <environment: namespace:RNASeqGUI>
DavidConnect
## function (user.mail = "rnaseqgui@na.iac.cnr.it")
## {
## if (!exists("david")) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## else {
## if (!is.connected(david)) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## }
## if (getTimeOut(david) == 30000) {
## setTimeOut(david, 5e+05)
## }
## if (is.null(getHttpProtocolVersion(david))) {
## setHttpProtocolVersion(david, "HTTP/1.0")
## }
## return(david)
## }
## <environment: namespace:RNASeqGUI>
DavidAnalysis
## function (main.window = NULL, file.name, gene.list.position,
## gene.identifier, list.type, list.name, out.file.name, db.selected,
## analysis.type, Project, specie, filter.list)
## {
## require("RDAVIDWebService")
## require("biomaRt")
## if (Sys.info()[[1]] == "Windows") {
## sys.sep = "\\"
## }
## else {
## sys.sep = "/"
## }
## sep.pos <- gregexpr(pattern = sys.sep, file.name, fixed = F)[[1]]
## out.file.name <- substring(file.name, sep.pos[length(sep.pos)] +
## 1)
## david.path <- file.path("RNASeqGUI_Projects", Project, "Results",
## "DAVID")
## david.db.path <- file.path(david.path, paste(db.selected,
## collapse = "_", sep = ""))
## dir.create(david.path, recursive = TRUE)
## if (analysis.type == "Pathway") {
## cat("Performing pathway analysis on ", db.selected, "...\n")
## this.name <- paste0(out.file.name, "_DAVID_Pathway_",
## db.selected)
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## if (length(grep("ALL", db.selected)) != 0) {
## cat("Performing ALL GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_ALL_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## cat("Performing FAT GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_FAT_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_DAVID_FAT_GO_results.txt")
## }
## }
## dbname <- paste0("david_", this.name, "_db")
## db <- InitDb(db.name = dbname, db.path = file.path("RNASeqGUI_Projects",
## Project, "Logs", "cache"))
## SaveInCache(db, file.name, "filename_key")
## SaveInCache(db, Project, "project_key")
## SaveInCache(db, gene.list.position, "genelistposition_key")
## SaveInCache(db, gene.identifier, "geneidentifier_key")
## SaveInCache(db, list.type, "listtype_key")
## SaveInCache(db, list.name, "listname_key")
## SaveInCache(db, db.selected, "dbselected_key")
## SaveInCache(db, analysis.type, "analysistype_key")
## SaveInCache(db, out.file.name, "outfilename_key")
## SaveInCache(db, specie, "specie_key")
## id.list <- read.table(file = file.name, header = TRUE, as.is = TRUE)
## id.list <- id.list[, gene.list.position, drop = TRUE]
## if (gene.identifier == "GENCODE") {
## id.list <- unlist(lapply(id.list, function(x) {
## substring(x, 0, regexpr(pattern = ".", x, fixed = T)[1] -
## 1)
## }))
## gene.identifier <- "ENSEMBL_GENE_ID"
## }
## if (gene.identifier == "GENE_SYMBOL") {
## if (specie != "") {
## print("converting gene_symbol to ensembl_gene_id ... ")
## specie.list <- GetSpecieCode(specie)
## print(specie.list$dataset)
## ensembl <- useMart("ENSEMBL_MART_ENSEMBL", host = "www.ensembl.org",
## dataset = specie.list$dataset)
## ensembl.map <- getBM(attributes = c("external_gene_name",
## "ensembl_gene_id"), mart = ensembl)
## id.list <- ConvertList(id.list, ensembl.map)
## gene.identifier <- "ENSEMBL_GENE_ID"
## print("done!")
## }
## else {
## message("ERROR: empty Specie")
## }
## }
## print("check if list is too short")
## if (length(id.list) > 3000) {
## MyDialog(parent.w = main.window, type.d = "warning",
## message = paste0("You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"),
## title = "WARNING")
## message(paste0("WARNING: You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"))
## id.list <- id.list[1:3000]
## }
## else {
## MyDialog(parent.w = main.window, type.d = "info", message = paste0("You submitted ",
## length(id.list), " genes!"), title = "INFORMATION")
## print(paste0("You submitted ", length(id.list), " genes!"))
## }
## print(head(id.list))
## SaveInCache(db, id.list, "idlist_key")
## print("Querying DAVID...")
## w.wind <- WaitingWindow(message = "Please wait while querying DAVID",
## parent.w = main.window)
## Sys.sleep(1)
## david <- DavidConnect()
## if (is.connected(david)) {
## result <- addList(david, id.list, idType = gene.identifier,
## listName = list.name, listType = list.type)
## setAnnotationCategories(david, db.selected)
## results.final <- getFunctionalAnnotationChart(david)
## w.wind$destroy()
## print("done!")
## if (dim(results.final)[1] != 0) {
## if (filter.list$flag) {
## results.final <- results.final[results.final[,
## filter.list$col.name] < filter.list$thr, ]
## }
## SaveInCache(db, filter.list, "filterlist_key")
## SaveInCache(db, results.final, "resultsfinal_key")
## write.table(results.final, file = out.file.name,
## quote = FALSE, row.names = FALSE, sep = "\t")
## cat("File ", out.file.name, " written on disk!\n")
## print(david.db.path)
## input.file.name <- substring(file.name, max(gregexpr("/",
## file.name)[[1]]) + 1)
## input.file.name <- gsub(".txt", "", input.file.name)
## input.file.name <- gsub(" ", "_", input.file.name)
## SavePathwaysList(results.final, david.db.path, just.file.name = input.file.name)
## }
## else {
## results.final <- data.frame()
## SaveInCache(db, results.final, "resultsfinal_key")
## cat("David produced no Results on ", db.selected,
## "\n")
## }
## }
## else {
## w.wind$destroy()
## message("ERROR: DAVID disconnected!")
## }
## PrintDavidReport(db, dbname)
## return(results.final)
## }
## <environment: namespace:RNASeqGUI>
This R code has been run:
print(getwd())
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Logs"
db <- InitDb(db.name='david_genes_in_E2_UP_not_in_DEC.txt_DAVID_Pathway_KEGG_PATHWAY_db' , db.path='cache')
#results.data.frame <- DavidAnalysis(file.name, gene.list.position, gene.identifier, list.type, list.name, out.file.name, db.selected, analysis.type, Project)
results.data.frame <- LoadCachedObject(db, 'resultsfinal_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(results.data.frame))
## Category Term Count
## 1 KEGG_PATHWAY mmu04510:Focal adhesion 14
## 2 KEGG_PATHWAY mmu04630:Jak-STAT signaling pathway 11
## 3 KEGG_PATHWAY mmu04810:Regulation of actin cytoskeleton 13
## 4 KEGG_PATHWAY mmu04960:Aldosterone-regulated sodium reabsorption 6
## X. PValue
## 1 3.349282 0.0001113010
## 2 2.631579 0.0007063283
## 3 3.110048 0.0009870693
## 4 1.435407 0.0012390469
## Genes
## 1 ENSMUSG00000020689, ENSMUSG00000001281, ENSMUSG00000024456, ENSMUSG00000019699, ENSMUSG00000009376, ENSMUSG00000000555, ENSMUSG00000020573, ENSMUSG00000001930, ENSMUSG00000021823, ENSMUSG00000020580, ENSMUSG00000052889, ENSMUSG00000024122, ENSMUSG00000025321, ENSMUSG00000032000
## 2 ENSMUSG00000020573, ENSMUSG00000059326, ENSMUSG00000024789, ENSMUSG00000040663, ENSMUSG00000022637, ENSMUSG00000021756, ENSMUSG00000071714, ENSMUSG00000019699, ENSMUSG00000030745, ENSMUSG00000071713, ENSMUSG00000003882
## 3 ENSMUSG00000020689, ENSMUSG00000031133, ENSMUSG00000020573, ENSMUSG00000037946, ENSMUSG00000021823, ENSMUSG00000030789, ENSMUSG00000020580, ENSMUSG00000001281, ENSMUSG00000024456, ENSMUSG00000059495, ENSMUSG00000025321, ENSMUSG00000000555, ENSMUSG00000000157
## 4 ENSMUSG00000020573, ENSMUSG00000040907, ENSMUSG00000052889, ENSMUSG00000024122, ENSMUSG00000005534, ENSMUSG00000019970
## List.Total Pop.Hits Pop.Total Fold.Enrichment Bonferroni Benjamini
## 1 113 198 5738 3.590417 0.01238902 0.01238902
## 2 113 152 5738 3.674779 0.07608640 0.03879576
## 3 113 217 5738 3.042046 0.10470889 0.03619741
## 4 113 42 5738 7.254109 0.12964952 0.03411918
## FDR
## 1 0.1260958
## 2 0.7977624
## 3 1.1132303
## 4 1.3955978
Here starts the automatically generated code
2016-06-16 19:35:36 and the DAVID*_result*.csv files has been saved in the BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/genes_in_E2_UP_not_in_DEC.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list5
, db.selected:
GOTERM_MF_ALL
, analysis.type:
GO
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/genes_in_E2_UP_not_in_DEC.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list5
, db.selected:
GOTERM_BP_ALL
, analysis.type:
GO
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
The list of called functions:
GetSpecieCode
## function (specie)
## {
## switch(specie, HUMAN = {
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## }, MOUSE = {
## dataset = "mmusculus_gene_ensembl"
## attribute = "mgi_symbol"
## }, DROSOPHILA = {
## dataset = "dmelanogaster_gene_ensembl"
## attribute = "bdgp_symbol"
## }, ZEBRAFISH = {
## dataset = "drerio_gene_ensembl"
## attribute = "zfin_symbol"
## }, {
## print("WARNING: no species detected! Using, HUMAN!")
## dialog <- MyDialog(window, "warning", message = "no species detected! Using, HUMAN!",
## title = "WARNING")
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## })
## return(list(dataset = dataset, attribute = attribute))
## }
## <environment: namespace:RNASeqGUI>
ConvertList
## function (id.list, map)
## {
## res.map <- apply(id.list, 1, function(x) {
## which(map[, 1] %in% x)
## })
## print(head(res.map))
## print(length(res.map))
## print(dim(id.list)[1])
## if (length(res.map) == dim(id.list)[1]) {
## id.list.n <- lapply(res.map, function(item) {
## if (length(item) > 0) {
## map[item[1], 2]
## }
## else {
## map[item, 2]
## }
## })
## }
## else {
## if (length(res.map) == 0) {
## print("problem res.map")
## }
## else if (length(id.list) == 0) {
## print("problem id.list")
## }
## }
## return(unlist(id.list.n))
## }
## <environment: namespace:RNASeqGUI>
DavidConnect
## function (user.mail = "rnaseqgui@na.iac.cnr.it")
## {
## if (!exists("david")) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## else {
## if (!is.connected(david)) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## }
## if (getTimeOut(david) == 30000) {
## setTimeOut(david, 5e+05)
## }
## if (is.null(getHttpProtocolVersion(david))) {
## setHttpProtocolVersion(david, "HTTP/1.0")
## }
## return(david)
## }
## <environment: namespace:RNASeqGUI>
DavidAnalysis
## function (main.window = NULL, file.name, gene.list.position,
## gene.identifier, list.type, list.name, out.file.name, db.selected,
## analysis.type, Project, specie, filter.list)
## {
## require("RDAVIDWebService")
## require("biomaRt")
## if (Sys.info()[[1]] == "Windows") {
## sys.sep = "\\"
## }
## else {
## sys.sep = "/"
## }
## sep.pos <- gregexpr(pattern = sys.sep, file.name, fixed = F)[[1]]
## out.file.name <- substring(file.name, sep.pos[length(sep.pos)] +
## 1)
## david.path <- file.path("RNASeqGUI_Projects", Project, "Results",
## "DAVID")
## david.db.path <- file.path(david.path, paste(db.selected,
## collapse = "_", sep = ""))
## dir.create(david.path, recursive = TRUE)
## if (analysis.type == "Pathway") {
## cat("Performing pathway analysis on ", db.selected, "...\n")
## this.name <- paste0(out.file.name, "_DAVID_Pathway_",
## db.selected)
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## if (length(grep("ALL", db.selected)) != 0) {
## cat("Performing ALL GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_ALL_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## cat("Performing FAT GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_FAT_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_DAVID_FAT_GO_results.txt")
## }
## }
## dbname <- paste0("david_", this.name, "_db")
## db <- InitDb(db.name = dbname, db.path = file.path("RNASeqGUI_Projects",
## Project, "Logs", "cache"))
## SaveInCache(db, file.name, "filename_key")
## SaveInCache(db, Project, "project_key")
## SaveInCache(db, gene.list.position, "genelistposition_key")
## SaveInCache(db, gene.identifier, "geneidentifier_key")
## SaveInCache(db, list.type, "listtype_key")
## SaveInCache(db, list.name, "listname_key")
## SaveInCache(db, db.selected, "dbselected_key")
## SaveInCache(db, analysis.type, "analysistype_key")
## SaveInCache(db, out.file.name, "outfilename_key")
## SaveInCache(db, specie, "specie_key")
## id.list <- read.table(file = file.name, header = TRUE, as.is = TRUE)
## id.list <- id.list[, gene.list.position, drop = TRUE]
## if (gene.identifier == "GENCODE") {
## id.list <- unlist(lapply(id.list, function(x) {
## substring(x, 0, regexpr(pattern = ".", x, fixed = T)[1] -
## 1)
## }))
## gene.identifier <- "ENSEMBL_GENE_ID"
## }
## if (gene.identifier == "GENE_SYMBOL") {
## if (specie != "") {
## print("converting gene_symbol to ensembl_gene_id ... ")
## specie.list <- GetSpecieCode(specie)
## print(specie.list$dataset)
## ensembl <- useMart("ENSEMBL_MART_ENSEMBL", host = "www.ensembl.org",
## dataset = specie.list$dataset)
## ensembl.map <- getBM(attributes = c("external_gene_name",
## "ensembl_gene_id"), mart = ensembl)
## id.list <- ConvertList(id.list, ensembl.map)
## gene.identifier <- "ENSEMBL_GENE_ID"
## print("done!")
## }
## else {
## message("ERROR: empty Specie")
## }
## }
## print("check if list is too short")
## if (length(id.list) > 3000) {
## MyDialog(parent.w = main.window, type.d = "warning",
## message = paste0("You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"),
## title = "WARNING")
## message(paste0("WARNING: You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"))
## id.list <- id.list[1:3000]
## }
## else {
## MyDialog(parent.w = main.window, type.d = "info", message = paste0("You submitted ",
## length(id.list), " genes!"), title = "INFORMATION")
## print(paste0("You submitted ", length(id.list), " genes!"))
## }
## print(head(id.list))
## SaveInCache(db, id.list, "idlist_key")
## print("Querying DAVID...")
## w.wind <- WaitingWindow(message = "Please wait while querying DAVID",
## parent.w = main.window)
## Sys.sleep(1)
## david <- DavidConnect()
## if (is.connected(david)) {
## result <- addList(david, id.list, idType = gene.identifier,
## listName = list.name, listType = list.type)
## setAnnotationCategories(david, db.selected)
## results.final <- getFunctionalAnnotationChart(david)
## w.wind$destroy()
## print("done!")
## if (dim(results.final)[1] != 0) {
## if (filter.list$flag) {
## results.final <- results.final[results.final[,
## filter.list$col.name] < filter.list$thr, ]
## }
## SaveInCache(db, filter.list, "filterlist_key")
## SaveInCache(db, results.final, "resultsfinal_key")
## write.table(results.final, file = out.file.name,
## quote = FALSE, row.names = FALSE, sep = "\t")
## cat("File ", out.file.name, " written on disk!\n")
## print(david.db.path)
## input.file.name <- substring(file.name, max(gregexpr("/",
## file.name)[[1]]) + 1)
## input.file.name <- gsub(".txt", "", input.file.name)
## input.file.name <- gsub(" ", "_", input.file.name)
## SavePathwaysList(results.final, david.db.path, just.file.name = input.file.name)
## }
## else {
## results.final <- data.frame()
## SaveInCache(db, results.final, "resultsfinal_key")
## cat("David produced no Results on ", db.selected,
## "\n")
## }
## }
## else {
## w.wind$destroy()
## message("ERROR: DAVID disconnected!")
## }
## PrintDavidReport(db, dbname)
## return(results.final)
## }
## <environment: namespace:RNASeqGUI>
This R code has been run:
print(getwd())
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Logs"
db <- InitDb(db.name='david_genes_in_E2_UP_not_in_DEC.txt_DAVID_ALL_GO_GOTERM_MF_ALL_GOTERM_BP_ALL_db' , db.path='cache')
#results.data.frame <- DavidAnalysis(file.name, gene.list.position, gene.identifier, list.type, list.name, out.file.name, db.selected, analysis.type, Project)
results.data.frame <- LoadCachedObject(db, 'resultsfinal_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(results.data.frame))
## Category Term Count
## 1 GOTERM_BP_ALL GO:0009966~regulation of signal transduction 42
## 2 GOTERM_BP_ALL GO:0010646~regulation of cell communication 45
## 3 GOTERM_MF_ALL GO:0005524~ATP binding 67
## 4 GOTERM_MF_ALL GO:0032559~adenyl ribonucleotide binding 67
## 5 GOTERM_MF_ALL GO:0030554~adenyl nucleotide binding 68
## 6 GOTERM_MF_ALL GO:0001883~purine nucleoside binding 68
## X. PValue
## 1 10.04785 1.227286e-09
## 2 10.76555 3.760833e-09
## 3 16.02871 4.511255e-09
## 4 16.02871 7.131723e-09
## 5 16.26794 2.160112e-08
## 6 16.26794 3.007909e-08
## Genes
## 1 ENSMUSG00000053754, ENSMUSG00000031133, ENSMUSG00000034593, ENSMUSG00000028030, ENSMUSG00000029094, ENSMUSG00000019852, ENSMUSG00000027652, ENSMUSG00000022508, ENSMUSG00000037706, ENSMUSG00000021948, ENSMUSG00000036473, ENSMUSG00000025199, ENSMUSG00000059495, ENSMUSG00000022749, ENSMUSG00000074272, ENSMUSG00000027276, ENSMUSG00000031391, ENSMUSG00000028991, ENSMUSG00000031709, ENSMUSG00000037946, ENSMUSG00000020716, ENSMUSG00000054051, ENSMUSG00000024789, ENSMUSG00000022637, ENSMUSG00000021756, ENSMUSG00000018909, ENSMUSG00000027660, ENSMUSG00000037552, ENSMUSG00000024451, ENSMUSG00000021670, ENSMUSG00000032413, ENSMUSG00000009376, ENSMUSG00000020859, ENSMUSG00000001588, ENSMUSG00000057530, ENSMUSG00000037533, ENSMUSG00000035236, ENSMUSG00000070565, ENSMUSG00000038520, ENSMUSG00000021027, ENSMUSG00000034610, ENSMUSG00000024163
## 2 ENSMUSG00000053754, ENSMUSG00000031133, ENSMUSG00000034593, ENSMUSG00000036098, ENSMUSG00000028030, ENSMUSG00000029094, ENSMUSG00000019852, ENSMUSG00000027652, ENSMUSG00000022508, ENSMUSG00000031393, ENSMUSG00000037868, ENSMUSG00000037706, ENSMUSG00000021948, ENSMUSG00000036473, ENSMUSG00000025199, ENSMUSG00000059495, ENSMUSG00000022749, ENSMUSG00000074272, ENSMUSG00000027276, ENSMUSG00000031391, ENSMUSG00000028991, ENSMUSG00000020716, ENSMUSG00000031709, ENSMUSG00000037946, ENSMUSG00000054051, ENSMUSG00000024789, ENSMUSG00000022637, ENSMUSG00000021756, ENSMUSG00000018909, ENSMUSG00000027660, ENSMUSG00000037552, ENSMUSG00000024451, ENSMUSG00000021670, ENSMUSG00000032413, ENSMUSG00000009376, ENSMUSG00000020859, ENSMUSG00000001588, ENSMUSG00000057530, ENSMUSG00000037533, ENSMUSG00000035236, ENSMUSG00000070565, ENSMUSG00000038520, ENSMUSG00000021027, ENSMUSG00000034610, ENSMUSG00000024163
## 3 ENSMUSG00000053754, ENSMUSG00000007613, ENSMUSG00000060671, ENSMUSG00000020788, ENSMUSG00000048279, ENSMUSG00000021559, ENSMUSG00000026944, ENSMUSG00000022504, ENSMUSG00000022360, ENSMUSG00000020573, ENSMUSG00000026437, ENSMUSG00000022994, ENSMUSG00000021820, ENSMUSG00000025757, ENSMUSG00000052889, ENSMUSG00000031314, ENSMUSG00000025199, ENSMUSG00000042249, ENSMUSG00000020334, ENSMUSG00000019970, ENSMUSG00000004815, ENSMUSG00000054051, ENSMUSG00000058997, ENSMUSG00000024789, ENSMUSG00000021375, ENSMUSG00000036086, ENSMUSG00000022672, ENSMUSG00000026409, ENSMUSG00000020580, ENSMUSG00000024122, ENSMUSG00000031303, ENSMUSG00000042046, ENSMUSG00000024843, ENSMUSG00000034593, ENSMUSG00000028030, ENSMUSG00000040907, ENSMUSG00000025574, ENSMUSG00000030761, ENSMUSG00000024943, ENSMUSG00000000823, ENSMUSG00000035722, ENSMUSG00000038844, ENSMUSG00000005534, ENSMUSG00000024948, ENSMUSG00000024130, ENSMUSG00000033526, ENSMUSG00000009418, ENSMUSG00000021948, ENSMUSG00000039585, ENSMUSG00000023088, ENSMUSG00000028991, ENSMUSG00000029186, ENSMUSG00000036875, ENSMUSG00000001630, ENSMUSG00000041415, ENSMUSG00000038970, ENSMUSG00000019699, ENSMUSG00000040661, ENSMUSG00000040021, ENSMUSG00000024070, ENSMUSG00000009376, ENSMUSG00000023809, ENSMUSG00000001588, ENSMUSG00000020273, ENSMUSG00000005102, ENSMUSG00000037795, ENSMUSG00000041642
## 4 ENSMUSG00000053754, ENSMUSG00000007613, ENSMUSG00000060671, ENSMUSG00000020788, ENSMUSG00000048279, ENSMUSG00000021559, ENSMUSG00000026944, ENSMUSG00000022504, ENSMUSG00000022360, ENSMUSG00000020573, ENSMUSG00000026437, ENSMUSG00000022994, ENSMUSG00000021820, ENSMUSG00000025757, ENSMUSG00000052889, ENSMUSG00000031314, ENSMUSG00000025199, ENSMUSG00000042249, ENSMUSG00000020334, ENSMUSG00000019970, ENSMUSG00000004815, ENSMUSG00000054051, ENSMUSG00000058997, ENSMUSG00000024789, ENSMUSG00000021375, ENSMUSG00000036086, ENSMUSG00000022672, ENSMUSG00000026409, ENSMUSG00000020580, ENSMUSG00000024122, ENSMUSG00000031303, ENSMUSG00000042046, ENSMUSG00000024843, ENSMUSG00000034593, ENSMUSG00000028030, ENSMUSG00000040907, ENSMUSG00000025574, ENSMUSG00000030761, ENSMUSG00000024943, ENSMUSG00000000823, ENSMUSG00000035722, ENSMUSG00000038844, ENSMUSG00000005534, ENSMUSG00000024948, ENSMUSG00000024130, ENSMUSG00000033526, ENSMUSG00000009418, ENSMUSG00000021948, ENSMUSG00000039585, ENSMUSG00000023088, ENSMUSG00000028991, ENSMUSG00000029186, ENSMUSG00000036875, ENSMUSG00000001630, ENSMUSG00000041415, ENSMUSG00000038970, ENSMUSG00000019699, ENSMUSG00000040661, ENSMUSG00000040021, ENSMUSG00000024070, ENSMUSG00000009376, ENSMUSG00000023809, ENSMUSG00000001588, ENSMUSG00000020273, ENSMUSG00000005102, ENSMUSG00000037795, ENSMUSG00000041642
## 5 ENSMUSG00000053754, ENSMUSG00000007613, ENSMUSG00000060671, ENSMUSG00000020788, ENSMUSG00000048279, ENSMUSG00000021559, ENSMUSG00000026944, ENSMUSG00000022504, ENSMUSG00000022360, ENSMUSG00000020573, ENSMUSG00000026437, ENSMUSG00000022994, ENSMUSG00000021820, ENSMUSG00000025757, ENSMUSG00000052889, ENSMUSG00000031314, ENSMUSG00000025199, ENSMUSG00000042249, ENSMUSG00000020334, ENSMUSG00000019970, ENSMUSG00000004815, ENSMUSG00000054051, ENSMUSG00000058997, ENSMUSG00000024789, ENSMUSG00000021375, ENSMUSG00000036086, ENSMUSG00000022672, ENSMUSG00000020250, ENSMUSG00000026409, ENSMUSG00000020580, ENSMUSG00000024122, ENSMUSG00000031303, ENSMUSG00000042046, ENSMUSG00000024843, ENSMUSG00000034593, ENSMUSG00000028030, ENSMUSG00000040907, ENSMUSG00000025574, ENSMUSG00000030761, ENSMUSG00000024943, ENSMUSG00000000823, ENSMUSG00000035722, ENSMUSG00000038844, ENSMUSG00000005534, ENSMUSG00000024948, ENSMUSG00000024130, ENSMUSG00000033526, ENSMUSG00000009418, ENSMUSG00000021948, ENSMUSG00000039585, ENSMUSG00000023088, ENSMUSG00000028991, ENSMUSG00000029186, ENSMUSG00000036875, ENSMUSG00000001630, ENSMUSG00000041415, ENSMUSG00000038970, ENSMUSG00000019699, ENSMUSG00000040661, ENSMUSG00000040021, ENSMUSG00000024070, ENSMUSG00000009376, ENSMUSG00000023809, ENSMUSG00000001588, ENSMUSG00000020273, ENSMUSG00000005102, ENSMUSG00000037795, ENSMUSG00000041642
## 6 ENSMUSG00000053754, ENSMUSG00000007613, ENSMUSG00000060671, ENSMUSG00000020788, ENSMUSG00000048279, ENSMUSG00000021559, ENSMUSG00000026944, ENSMUSG00000022504, ENSMUSG00000022360, ENSMUSG00000020573, ENSMUSG00000026437, ENSMUSG00000022994, ENSMUSG00000021820, ENSMUSG00000025757, ENSMUSG00000052889, ENSMUSG00000031314, ENSMUSG00000025199, ENSMUSG00000042249, ENSMUSG00000020334, ENSMUSG00000019970, ENSMUSG00000004815, ENSMUSG00000054051, ENSMUSG00000058997, ENSMUSG00000024789, ENSMUSG00000021375, ENSMUSG00000036086, ENSMUSG00000022672, ENSMUSG00000020250, ENSMUSG00000026409, ENSMUSG00000020580, ENSMUSG00000024122, ENSMUSG00000031303, ENSMUSG00000042046, ENSMUSG00000024843, ENSMUSG00000034593, ENSMUSG00000028030, ENSMUSG00000040907, ENSMUSG00000025574, ENSMUSG00000030761, ENSMUSG00000024943, ENSMUSG00000000823, ENSMUSG00000035722, ENSMUSG00000038844, ENSMUSG00000005534, ENSMUSG00000024948, ENSMUSG00000024130, ENSMUSG00000033526, ENSMUSG00000009418, ENSMUSG00000021948, ENSMUSG00000039585, ENSMUSG00000023088, ENSMUSG00000028991, ENSMUSG00000029186, ENSMUSG00000036875, ENSMUSG00000001630, ENSMUSG00000041415, ENSMUSG00000038970, ENSMUSG00000019699, ENSMUSG00000040661, ENSMUSG00000040021, ENSMUSG00000024070, ENSMUSG00000009376, ENSMUSG00000023809, ENSMUSG00000001588, ENSMUSG00000020273, ENSMUSG00000005102, ENSMUSG00000037795, ENSMUSG00000041642
## List.Total Pop.Hits Pop.Total Fold.Enrichment Bonferroni Benjamini
## 1 310 661 14219 2.914440 2.385842e-06 2.385842e-06
## 2 310 771 14219 2.677106 7.311032e-06 3.655523e-06
## 3 337 1443 15404 2.122326 2.530811e-06 2.530811e-06
## 4 337 1460 15404 2.097614 4.000888e-06 2.000446e-06
## 5 337 1535 15404 2.024903 1.211815e-05 4.039401e-06
## 6 337 1548 15404 2.007898 1.687423e-05 4.218584e-06
## FDR
## 1 2.103102e-06
## 2 6.444635e-06
## 3 6.601481e-06
## 4 1.043610e-05
## 5 3.160968e-05
## 6 4.401580e-05
Here starts the automatically generated code
BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/genes_in_DEC_UP_not_in_E2.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list6
, db.selected:
KEGG_PATHWAY
, analysis.type:
Pathway
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
The list of called functions:
GetSpecieCode
## function (specie)
## {
## switch(specie, HUMAN = {
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## }, MOUSE = {
## dataset = "mmusculus_gene_ensembl"
## attribute = "mgi_symbol"
## }, DROSOPHILA = {
## dataset = "dmelanogaster_gene_ensembl"
## attribute = "bdgp_symbol"
## }, ZEBRAFISH = {
## dataset = "drerio_gene_ensembl"
## attribute = "zfin_symbol"
## }, {
## print("WARNING: no species detected! Using, HUMAN!")
## dialog <- MyDialog(window, "warning", message = "no species detected! Using, HUMAN!",
## title = "WARNING")
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## })
## return(list(dataset = dataset, attribute = attribute))
## }
## <environment: namespace:RNASeqGUI>
ConvertList
## function (id.list, map)
## {
## res.map <- apply(id.list, 1, function(x) {
## which(map[, 1] %in% x)
## })
## print(head(res.map))
## print(length(res.map))
## print(dim(id.list)[1])
## if (length(res.map) == dim(id.list)[1]) {
## id.list.n <- lapply(res.map, function(item) {
## if (length(item) > 0) {
## map[item[1], 2]
## }
## else {
## map[item, 2]
## }
## })
## }
## else {
## if (length(res.map) == 0) {
## print("problem res.map")
## }
## else if (length(id.list) == 0) {
## print("problem id.list")
## }
## }
## return(unlist(id.list.n))
## }
## <environment: namespace:RNASeqGUI>
DavidConnect
## function (user.mail = "rnaseqgui@na.iac.cnr.it")
## {
## if (!exists("david")) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## else {
## if (!is.connected(david)) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## }
## if (getTimeOut(david) == 30000) {
## setTimeOut(david, 5e+05)
## }
## if (is.null(getHttpProtocolVersion(david))) {
## setHttpProtocolVersion(david, "HTTP/1.0")
## }
## return(david)
## }
## <environment: namespace:RNASeqGUI>
DavidAnalysis
## function (main.window = NULL, file.name, gene.list.position,
## gene.identifier, list.type, list.name, out.file.name, db.selected,
## analysis.type, Project, specie, filter.list)
## {
## require("RDAVIDWebService")
## require("biomaRt")
## if (Sys.info()[[1]] == "Windows") {
## sys.sep = "\\"
## }
## else {
## sys.sep = "/"
## }
## sep.pos <- gregexpr(pattern = sys.sep, file.name, fixed = F)[[1]]
## out.file.name <- substring(file.name, sep.pos[length(sep.pos)] +
## 1)
## david.path <- file.path("RNASeqGUI_Projects", Project, "Results",
## "DAVID")
## david.db.path <- file.path(david.path, paste(db.selected,
## collapse = "_", sep = ""))
## dir.create(david.path, recursive = TRUE)
## if (analysis.type == "Pathway") {
## cat("Performing pathway analysis on ", db.selected, "...\n")
## this.name <- paste0(out.file.name, "_DAVID_Pathway_",
## db.selected)
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## if (length(grep("ALL", db.selected)) != 0) {
## cat("Performing ALL GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_ALL_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## cat("Performing FAT GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_FAT_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_DAVID_FAT_GO_results.txt")
## }
## }
## dbname <- paste0("david_", this.name, "_db")
## db <- InitDb(db.name = dbname, db.path = file.path("RNASeqGUI_Projects",
## Project, "Logs", "cache"))
## SaveInCache(db, file.name, "filename_key")
## SaveInCache(db, Project, "project_key")
## SaveInCache(db, gene.list.position, "genelistposition_key")
## SaveInCache(db, gene.identifier, "geneidentifier_key")
## SaveInCache(db, list.type, "listtype_key")
## SaveInCache(db, list.name, "listname_key")
## SaveInCache(db, db.selected, "dbselected_key")
## SaveInCache(db, analysis.type, "analysistype_key")
## SaveInCache(db, out.file.name, "outfilename_key")
## SaveInCache(db, specie, "specie_key")
## id.list <- read.table(file = file.name, header = TRUE, as.is = TRUE)
## id.list <- id.list[, gene.list.position, drop = TRUE]
## if (gene.identifier == "GENCODE") {
## id.list <- unlist(lapply(id.list, function(x) {
## substring(x, 0, regexpr(pattern = ".", x, fixed = T)[1] -
## 1)
## }))
## gene.identifier <- "ENSEMBL_GENE_ID"
## }
## if (gene.identifier == "GENE_SYMBOL") {
## if (specie != "") {
## print("converting gene_symbol to ensembl_gene_id ... ")
## specie.list <- GetSpecieCode(specie)
## print(specie.list$dataset)
## ensembl <- useMart("ENSEMBL_MART_ENSEMBL", host = "www.ensembl.org",
## dataset = specie.list$dataset)
## ensembl.map <- getBM(attributes = c("external_gene_name",
## "ensembl_gene_id"), mart = ensembl)
## id.list <- ConvertList(id.list, ensembl.map)
## gene.identifier <- "ENSEMBL_GENE_ID"
## print("done!")
## }
## else {
## message("ERROR: empty Specie")
## }
## }
## print("check if list is too short")
## if (length(id.list) > 3000) {
## MyDialog(parent.w = main.window, type.d = "warning",
## message = paste0("You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"),
## title = "WARNING")
## message(paste0("WARNING: You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"))
## id.list <- id.list[1:3000]
## }
## else {
## MyDialog(parent.w = main.window, type.d = "info", message = paste0("You submitted ",
## length(id.list), " genes!"), title = "INFORMATION")
## print(paste0("You submitted ", length(id.list), " genes!"))
## }
## print(head(id.list))
## SaveInCache(db, id.list, "idlist_key")
## print("Querying DAVID...")
## w.wind <- WaitingWindow(message = "Please wait while querying DAVID",
## parent.w = main.window)
## Sys.sleep(1)
## david <- DavidConnect()
## if (is.connected(david)) {
## result <- addList(david, id.list, idType = gene.identifier,
## listName = list.name, listType = list.type)
## setAnnotationCategories(david, db.selected)
## results.final <- getFunctionalAnnotationChart(david)
## w.wind$destroy()
## print("done!")
## if (dim(results.final)[1] != 0) {
## if (filter.list$flag) {
## results.final <- results.final[results.final[,
## filter.list$col.name] < filter.list$thr, ]
## }
## SaveInCache(db, filter.list, "filterlist_key")
## SaveInCache(db, results.final, "resultsfinal_key")
## write.table(results.final, file = out.file.name,
## quote = FALSE, row.names = FALSE, sep = "\t")
## cat("File ", out.file.name, " written on disk!\n")
## print(david.db.path)
## input.file.name <- substring(file.name, max(gregexpr("/",
## file.name)[[1]]) + 1)
## input.file.name <- gsub(".txt", "", input.file.name)
## input.file.name <- gsub(" ", "_", input.file.name)
## SavePathwaysList(results.final, david.db.path, just.file.name = input.file.name)
## }
## else {
## results.final <- data.frame()
## SaveInCache(db, results.final, "resultsfinal_key")
## cat("David produced no Results on ", db.selected,
## "\n")
## }
## }
## else {
## w.wind$destroy()
## message("ERROR: DAVID disconnected!")
## }
## PrintDavidReport(db, dbname)
## return(results.final)
## }
## <environment: namespace:RNASeqGUI>
This R code has been run:
print(getwd())
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Logs"
db <- InitDb(db.name='david_genes_in_DEC_UP_not_in_E2.txt_DAVID_Pathway_KEGG_PATHWAY_db' , db.path='cache')
#results.data.frame <- DavidAnalysis(file.name, gene.list.position, gene.identifier, list.type, list.name, out.file.name, db.selected, analysis.type, Project)
results.data.frame <- LoadCachedObject(db, 'resultsfinal_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(results.data.frame))
## Category Term Count
## 1 KEGG_PATHWAY mmu04620:Toll-like receptor signaling pathway 18
## 2 KEGG_PATHWAY mmu04621:NOD-like receptor signaling pathway 11
## 3 KEGG_PATHWAY mmu04622:RIG-I-like receptor signaling pathway 9
## 4 KEGG_PATHWAY mmu04623:Cytosolic DNA-sensing pathway 8
## 5 KEGG_PATHWAY mmu04060:Cytokine-cytokine receptor interaction 17
## X. PValue
## 1 3.742204 2.617753e-09
## 2 2.286902 1.021687e-05
## 3 1.871102 7.561990e-04
## 4 1.663202 1.010135e-03
## 5 3.534304 1.956391e-03
## Genes
## 1 ENSMUSG00000021408, ENSMUSG00000039005, ENSMUSG00000042349, ENSMUSG00000044583, ENSMUSG00000018930, ENSMUSG00000032508, ENSMUSG00000020115, ENSMUSG00000024401, ENSMUSG00000024235, ENSMUSG00000039936, ENSMUSG00000027995, ENSMUSG00000034855, ENSMUSG00000045322, ENSMUSG00000031639, ENSMUSG00000051439, ENSMUSG00000032041, ENSMUSG00000026029, ENSMUSG00000044827
## 2 ENSMUSG00000039193, ENSMUSG00000078945, ENSMUSG00000058427, ENSMUSG00000025860, ENSMUSG00000024401, ENSMUSG00000022534, ENSMUSG00000038058, ENSMUSG00000026029, ENSMUSG00000071203, ENSMUSG00000032691, ENSMUSG00000025888
## 3 ENSMUSG00000039285, ENSMUSG00000034855, ENSMUSG00000042349, ENSMUSG00000026896, ENSMUSG00000000275, ENSMUSG00000021408, ENSMUSG00000024401, ENSMUSG00000020115, ENSMUSG00000026029
## 4 ENSMUSG00000034855, ENSMUSG00000027951, ENSMUSG00000042349, ENSMUSG00000021408, ENSMUSG00000018930, ENSMUSG00000020115, ENSMUSG00000037860, ENSMUSG00000025888
## 5 ENSMUSG00000028362, ENSMUSG00000018930, ENSMUSG00000024401, ENSMUSG00000028864, ENSMUSG00000027947, ENSMUSG00000026180, ENSMUSG00000057722, ENSMUSG00000034855, ENSMUSG00000028859, ENSMUSG00000023951, ENSMUSG00000032440, ENSMUSG00000058427, ENSMUSG00000024621, ENSMUSG00000062960, ENSMUSG00000049103, ENSMUSG00000039304, ENSMUSG00000079227
## List.Total Pop.Hits Pop.Total Fold.Enrichment Bonferroni Benjamini
## 1 169 99 5738 6.173211 3.376900e-07 3.376900e-07
## 2 169 62 5738 6.023860 1.317114e-03 6.587742e-04
## 3 169 68 5738 4.493735 9.297618e-02 3.200548e-02
## 4 169 55 5738 4.938569 1.222322e-01 3.206787e-02
## 5 169 244 5738 2.365554 2.232383e-01 4.926921e-02
## FDR
## 1 3.044309e-06
## 2 1.188103e-02
## 3 8.758938e-01
## 4 1.168447e+00
## 5 2.251671e+00
Here starts the automatically generated code
BMDC_analysis/Results folder.You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/genes_in_DEC_UP_not_in_E2.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list6
, db.selected:
GOTERM_MF_ALL
, analysis.type:
GO
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
You chose the following file:
/RNASeqGUI_Projects/BMDC_analysis/Results/genes_in_DEC_UP_not_in_E2.txt
, gene.list.position:
1
, gene.identifier:
ENSEMBL_GENE_ID
, list.type:
Gene
, list.name:
list6
, db.selected:
GOTERM_BP_ALL
, analysis.type:
GO
, specie:
, filter:
TRUE
, filter.column:
Benjamini
, filter.threshold:
0.05
, Project:
BMDC_analysis
The list of called functions:
GetSpecieCode
## function (specie)
## {
## switch(specie, HUMAN = {
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## }, MOUSE = {
## dataset = "mmusculus_gene_ensembl"
## attribute = "mgi_symbol"
## }, DROSOPHILA = {
## dataset = "dmelanogaster_gene_ensembl"
## attribute = "bdgp_symbol"
## }, ZEBRAFISH = {
## dataset = "drerio_gene_ensembl"
## attribute = "zfin_symbol"
## }, {
## print("WARNING: no species detected! Using, HUMAN!")
## dialog <- MyDialog(window, "warning", message = "no species detected! Using, HUMAN!",
## title = "WARNING")
## dataset = "hsapiens_gene_ensembl"
## attribute = "hgnc_symbol"
## })
## return(list(dataset = dataset, attribute = attribute))
## }
## <environment: namespace:RNASeqGUI>
ConvertList
## function (id.list, map)
## {
## res.map <- apply(id.list, 1, function(x) {
## which(map[, 1] %in% x)
## })
## print(head(res.map))
## print(length(res.map))
## print(dim(id.list)[1])
## if (length(res.map) == dim(id.list)[1]) {
## id.list.n <- lapply(res.map, function(item) {
## if (length(item) > 0) {
## map[item[1], 2]
## }
## else {
## map[item, 2]
## }
## })
## }
## else {
## if (length(res.map) == 0) {
## print("problem res.map")
## }
## else if (length(id.list) == 0) {
## print("problem id.list")
## }
## }
## return(unlist(id.list.n))
## }
## <environment: namespace:RNASeqGUI>
DavidConnect
## function (user.mail = "rnaseqgui@na.iac.cnr.it")
## {
## if (!exists("david")) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## else {
## if (!is.connected(david)) {
## david <- DAVIDWebService$new(email = user.mail, url = "https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/")
## }
## }
## if (getTimeOut(david) == 30000) {
## setTimeOut(david, 5e+05)
## }
## if (is.null(getHttpProtocolVersion(david))) {
## setHttpProtocolVersion(david, "HTTP/1.0")
## }
## return(david)
## }
## <environment: namespace:RNASeqGUI>
DavidAnalysis
## function (main.window = NULL, file.name, gene.list.position,
## gene.identifier, list.type, list.name, out.file.name, db.selected,
## analysis.type, Project, specie, filter.list)
## {
## require("RDAVIDWebService")
## require("biomaRt")
## if (Sys.info()[[1]] == "Windows") {
## sys.sep = "\\"
## }
## else {
## sys.sep = "/"
## }
## sep.pos <- gregexpr(pattern = sys.sep, file.name, fixed = F)[[1]]
## out.file.name <- substring(file.name, sep.pos[length(sep.pos)] +
## 1)
## david.path <- file.path("RNASeqGUI_Projects", Project, "Results",
## "DAVID")
## david.db.path <- file.path(david.path, paste(db.selected,
## collapse = "_", sep = ""))
## dir.create(david.path, recursive = TRUE)
## if (analysis.type == "Pathway") {
## cat("Performing pathway analysis on ", db.selected, "...\n")
## this.name <- paste0(out.file.name, "_DAVID_Pathway_",
## db.selected)
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## if (length(grep("ALL", db.selected)) != 0) {
## cat("Performing ALL GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_ALL_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_results.txt")
## }
## else {
## cat("Performing FAT GO analysis on ", db.selected,
## "...\n")
## this.name <- paste0(out.file.name, "_DAVID_FAT_GO_",
## paste(db.selected, collapse = "_", sep = ""))
## out.file.name <- paste0(david.path, sys.sep, this.name,
## "_DAVID_FAT_GO_results.txt")
## }
## }
## dbname <- paste0("david_", this.name, "_db")
## db <- InitDb(db.name = dbname, db.path = file.path("RNASeqGUI_Projects",
## Project, "Logs", "cache"))
## SaveInCache(db, file.name, "filename_key")
## SaveInCache(db, Project, "project_key")
## SaveInCache(db, gene.list.position, "genelistposition_key")
## SaveInCache(db, gene.identifier, "geneidentifier_key")
## SaveInCache(db, list.type, "listtype_key")
## SaveInCache(db, list.name, "listname_key")
## SaveInCache(db, db.selected, "dbselected_key")
## SaveInCache(db, analysis.type, "analysistype_key")
## SaveInCache(db, out.file.name, "outfilename_key")
## SaveInCache(db, specie, "specie_key")
## id.list <- read.table(file = file.name, header = TRUE, as.is = TRUE)
## id.list <- id.list[, gene.list.position, drop = TRUE]
## if (gene.identifier == "GENCODE") {
## id.list <- unlist(lapply(id.list, function(x) {
## substring(x, 0, regexpr(pattern = ".", x, fixed = T)[1] -
## 1)
## }))
## gene.identifier <- "ENSEMBL_GENE_ID"
## }
## if (gene.identifier == "GENE_SYMBOL") {
## if (specie != "") {
## print("converting gene_symbol to ensembl_gene_id ... ")
## specie.list <- GetSpecieCode(specie)
## print(specie.list$dataset)
## ensembl <- useMart("ENSEMBL_MART_ENSEMBL", host = "www.ensembl.org",
## dataset = specie.list$dataset)
## ensembl.map <- getBM(attributes = c("external_gene_name",
## "ensembl_gene_id"), mart = ensembl)
## id.list <- ConvertList(id.list, ensembl.map)
## gene.identifier <- "ENSEMBL_GENE_ID"
## print("done!")
## }
## else {
## message("ERROR: empty Specie")
## }
## }
## print("check if list is too short")
## if (length(id.list) > 3000) {
## MyDialog(parent.w = main.window, type.d = "warning",
## message = paste0("You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"),
## title = "WARNING")
## message(paste0("WARNING: You submitted ", length(id.list),
## " genes!\nBecause of DAVID limitations, the gene list length has been cut to 3000 genes"))
## id.list <- id.list[1:3000]
## }
## else {
## MyDialog(parent.w = main.window, type.d = "info", message = paste0("You submitted ",
## length(id.list), " genes!"), title = "INFORMATION")
## print(paste0("You submitted ", length(id.list), " genes!"))
## }
## print(head(id.list))
## SaveInCache(db, id.list, "idlist_key")
## print("Querying DAVID...")
## w.wind <- WaitingWindow(message = "Please wait while querying DAVID",
## parent.w = main.window)
## Sys.sleep(1)
## david <- DavidConnect()
## if (is.connected(david)) {
## result <- addList(david, id.list, idType = gene.identifier,
## listName = list.name, listType = list.type)
## setAnnotationCategories(david, db.selected)
## results.final <- getFunctionalAnnotationChart(david)
## w.wind$destroy()
## print("done!")
## if (dim(results.final)[1] != 0) {
## if (filter.list$flag) {
## results.final <- results.final[results.final[,
## filter.list$col.name] < filter.list$thr, ]
## }
## SaveInCache(db, filter.list, "filterlist_key")
## SaveInCache(db, results.final, "resultsfinal_key")
## write.table(results.final, file = out.file.name,
## quote = FALSE, row.names = FALSE, sep = "\t")
## cat("File ", out.file.name, " written on disk!\n")
## print(david.db.path)
## input.file.name <- substring(file.name, max(gregexpr("/",
## file.name)[[1]]) + 1)
## input.file.name <- gsub(".txt", "", input.file.name)
## input.file.name <- gsub(" ", "_", input.file.name)
## SavePathwaysList(results.final, david.db.path, just.file.name = input.file.name)
## }
## else {
## results.final <- data.frame()
## SaveInCache(db, results.final, "resultsfinal_key")
## cat("David produced no Results on ", db.selected,
## "\n")
## }
## }
## else {
## w.wind$destroy()
## message("ERROR: DAVID disconnected!")
## }
## PrintDavidReport(db, dbname)
## return(results.final)
## }
## <environment: namespace:RNASeqGUI>
This R code has been run:
print(getwd())
## [1] "/RNASeqGUI_Projects/BMDC_analysis/Logs"
db <- InitDb(db.name='david_genes_in_DEC_UP_not_in_E2.txt_DAVID_ALL_GO_GOTERM_MF_ALL_GOTERM_BP_ALL_db' , db.path='cache')
#results.data.frame <- DavidAnalysis(file.name, gene.list.position, gene.identifier, list.type, list.name, out.file.name, db.selected, analysis.type, Project)
results.data.frame <- LoadCachedObject(db, 'resultsfinal_key')
print('First lines of the results:')
## [1] "First lines of the results:"
print(head(results.data.frame))
## Category Term Count X.
## 1 GOTERM_BP_ALL GO:0002376~immune system process 69 14.345114
## 2 GOTERM_BP_ALL GO:0006955~immune response 49 10.187110
## 3 GOTERM_BP_ALL GO:0006954~inflammatory response 29 6.029106
## 4 GOTERM_BP_ALL GO:0051707~response to other organism 29 6.029106
## 5 GOTERM_BP_ALL GO:0006952~defense response 39 8.108108
## 6 GOTERM_BP_ALL GO:0009607~response to biotic stimulus 31 6.444906
## PValue
## 1 2.860003e-21
## 2 4.784466e-18
## 3 5.383090e-13
## 4 1.959847e-12
## 5 6.822472e-12
## 6 7.103107e-11
## Genes
## 1 ENSMUSG00000001166, ENSMUSG00000038518, ENSMUSG00000040274, ENSMUSG00000039361, ENSMUSG00000030830, ENSMUSG00000002699, ENSMUSG00000032508, ENSMUSG00000021109, ENSMUSG00000021624, ENSMUSG00000032440, ENSMUSG00000041827, ENSMUSG00000029379, ENSMUSG00000032041, ENSMUSG00000079227, ENSMUSG00000032737, ENSMUSG00000027111, ENSMUSG00000052593, ENSMUSG00000023341, ENSMUSG00000029468, ENSMUSG00000029605, ENSMUSG00000079362, ENSMUSG00000020115, ENSMUSG00000008496, ENSMUSG00000079363, ENSMUSG00000036381, ENSMUSG00000031596, ENSMUSG00000034855, ENSMUSG00000031103, ENSMUSG00000062960, ENSMUSG00000058818, ENSMUSG00000021583, ENSMUSG00000038527, ENSMUSG00000026029, ENSMUSG00000037321, ENSMUSG00000024164, ENSMUSG00000034330, ENSMUSG00000044827, ENSMUSG00000044583, ENSMUSG00000028362, ENSMUSG00000018930, ENSMUSG00000028268, ENSMUSG00000022148, ENSMUSG00000024401, ENSMUSG00000029298, ENSMUSG00000036986, ENSMUSG00000018654, ENSMUSG00000023951, ENSMUSG00000070034, ENSMUSG00000051439, ENSMUSG00000049103, ENSMUSG00000027639, ENSMUSG00000042228, ENSMUSG00000047798, ENSMUSG00000040253, ENSMUSG00000039005, ENSMUSG00000053835, ENSMUSG00000039936, ENSMUSG00000027995, ENSMUSG00000030142, ENSMUSG00000032691, ENSMUSG00000045322, ENSMUSG00000028859, ENSMUSG00000026896, ENSMUSG00000058427, ENSMUSG00000031639, ENSMUSG00000078921, ENSMUSG00000006818, ENSMUSG00000039304, ENSMUSG00000040264
## 2 ENSMUSG00000001166, ENSMUSG00000032508, ENSMUSG00000021624, ENSMUSG00000041827, ENSMUSG00000029379, ENSMUSG00000032041, ENSMUSG00000079227, ENSMUSG00000032737, ENSMUSG00000052593, ENSMUSG00000023341, ENSMUSG00000029605, ENSMUSG00000020115, ENSMUSG00000079362, ENSMUSG00000008496, ENSMUSG00000079363, ENSMUSG00000036381, ENSMUSG00000034855, ENSMUSG00000021583, ENSMUSG00000058818, ENSMUSG00000038527, ENSMUSG00000034330, ENSMUSG00000024164, ENSMUSG00000037321, ENSMUSG00000044827, ENSMUSG00000044583, ENSMUSG00000018930, ENSMUSG00000028362, ENSMUSG00000028268, ENSMUSG00000024401, ENSMUSG00000029298, ENSMUSG00000023951, ENSMUSG00000070034, ENSMUSG00000049103, ENSMUSG00000051439, ENSMUSG00000027639, ENSMUSG00000047798, ENSMUSG00000040253, ENSMUSG00000039005, ENSMUSG00000053835, ENSMUSG00000027995, ENSMUSG00000030142, ENSMUSG00000032691, ENSMUSG00000045322, ENSMUSG00000026896, ENSMUSG00000031639, ENSMUSG00000058427, ENSMUSG00000078921, ENSMUSG00000039304, ENSMUSG00000040264
## 3 ENSMUSG00000035356, ENSMUSG00000044583, ENSMUSG00000018930, ENSMUSG00000032508, ENSMUSG00000024401, ENSMUSG00000021109, ENSMUSG00000042286, ENSMUSG00000021624, ENSMUSG00000051439, ENSMUSG00000049103, ENSMUSG00000026193, ENSMUSG00000029379, ENSMUSG00000032041, ENSMUSG00000079227, ENSMUSG00000039005, ENSMUSG00000029468, ENSMUSG00000022534, ENSMUSG00000027995, ENSMUSG00000032691, ENSMUSG00000031596, ENSMUSG00000034855, ENSMUSG00000045322, ENSMUSG00000039193, ENSMUSG00000040026, ENSMUSG00000058427, ENSMUSG00000031639, ENSMUSG00000038527, ENSMUSG00000024164, ENSMUSG00000044827
## 4 ENSMUSG00000044583, ENSMUSG00000020227, ENSMUSG00000032508, ENSMUSG00000024401, ENSMUSG00000042286, ENSMUSG00000070034, ENSMUSG00000027639, ENSMUSG00000051439, ENSMUSG00000032041, ENSMUSG00000079227, ENSMUSG00000039005, ENSMUSG00000023341, ENSMUSG00000029468, ENSMUSG00000028874, ENSMUSG00000029605, ENSMUSG00000024079, ENSMUSG00000020115, ENSMUSG00000027995, ENSMUSG00000032691, ENSMUSG00000045322, ENSMUSG00000026896, ENSMUSG00000039193, ENSMUSG00000003283, ENSMUSG00000031639, ENSMUSG00000078921, ENSMUSG00000038058, ENSMUSG00000029826, ENSMUSG00000034330, ENSMUSG00000044827
## 5 ENSMUSG00000035356, ENSMUSG00000044583, ENSMUSG00000018930, ENSMUSG00000024401, ENSMUSG00000032508, ENSMUSG00000021109, ENSMUSG00000042286, ENSMUSG00000021624, ENSMUSG00000070034, ENSMUSG00000027639, ENSMUSG00000051439, ENSMUSG00000049103, ENSMUSG00000019979, ENSMUSG00000029379, ENSMUSG00000026193, ENSMUSG00000032041, ENSMUSG00000079227, ENSMUSG00000039005, ENSMUSG00000023341, ENSMUSG00000029468, ENSMUSG00000028874, ENSMUSG00000022534, ENSMUSG00000020115, ENSMUSG00000027995, ENSMUSG00000031596, ENSMUSG00000032691, ENSMUSG00000034855, ENSMUSG00000045322, ENSMUSG00000039193, ENSMUSG00000026896, ENSMUSG00000040026, ENSMUSG00000003283, ENSMUSG00000058427, ENSMUSG00000031639, ENSMUSG00000038058, ENSMUSG00000038527, ENSMUSG00000037321, ENSMUSG00000024164, ENSMUSG00000044827
## 6 ENSMUSG00000044583, ENSMUSG00000020227, ENSMUSG00000070348, ENSMUSG00000032508, ENSMUSG00000024401, ENSMUSG00000059108, ENSMUSG00000042286, ENSMUSG00000070034, ENSMUSG00000027639, ENSMUSG00000051439, ENSMUSG00000032041, ENSMUSG00000079227, ENSMUSG00000039005, ENSMUSG00000023341, ENSMUSG00000029468, ENSMUSG00000028874, ENSMUSG00000029605, ENSMUSG00000024079, ENSMUSG00000020115, ENSMUSG00000027995, ENSMUSG00000032691, ENSMUSG00000045322, ENSMUSG00000026896, ENSMUSG00000039193, ENSMUSG00000003283, ENSMUSG00000031639, ENSMUSG00000078921, ENSMUSG00000038058, ENSMUSG00000029826, ENSMUSG00000034330, ENSMUSG00000044827
## List.Total Pop.Hits Pop.Total Fold.Enrichment Bonferroni Benjamini
## 1 336 791 14219 3.691496 5.702845e-18 5.702845e-18
## 2 336 471 14219 4.402557 9.540225e-15 4.770113e-15
## 3 336 225 14219 5.454378 1.073464e-09 3.578214e-10
## 4 336 237 14219 5.178207 3.907994e-09 9.769985e-10
## 5 336 448 14219 3.683972 1.360393e-08 2.720786e-09
## 6 336 314 14219 4.177936 1.416359e-07 2.360599e-08
## FDR
## 1 4.915537e-18
## 2 8.223146e-15
## 3 9.252710e-10
## 4 3.368472e-09
## 5 1.172583e-08
## 6 1.220824e-07
After functional analysis results inspection, heatmaps for most relevant pathways has been produced using the suited Gage functionality.
Here starts the automatically generated code
2016-06-16 20:01:20 and the GAGE_result.txt file has been saved in the BMDC_analysis/Results folder.You chose the following Pathway/GO file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_results_NOISeq_Gage_Analysis/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_results_NOISeq_Pathway_result.txt
,geneSet1:
TRUE
,geneSet2:
FALSE
,Project:
BMDC_analysis
,hsa:
FALSE
,mmu:
TRUE
,dme:
FALSE
,dre:
FALSE
,conversion:
TRUE
, num_of_path:
4
,countFile:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt
This R code has been run:
geneSet1 <- TRUE
geneSet2 <- FALSE
db <- InitDb(db.name = paste(geneSet1,geneSet2,'kegggoheatmap_db',sep='_'), db.path=file.path('cache'))
res <- LoadCachedObject(db, 'res_key')
Project <- LoadCachedObject(db, 'project_key')
hsa <- LoadCachedObject(db, 'hsa_key')
mmu <- LoadCachedObject(db, 'mmu_key')
dme <- LoadCachedObject(db, 'dme_key')
dre <- LoadCachedObject(db, 'dre_key')
conversion <- LoadCachedObject(db, 'conversion_key')
num_of_path <- LoadCachedObject(db, 'num_of_path_key')
countFile <- LoadCachedObject(db, 'countFile_key')
control <- LoadCachedObject(db, 'control_key')
treated <- LoadCachedObject(db, 'treated_key')
res=read.table(res, row.names=1, header=TRUE, sep='')
## Warning in file(file, "rt"): cannot open file '/
## media/dario/dati/RNASeqGUI_Projects/CADS_FC/Results/
## Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Gage_Analysis/
## Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Pathway_result.txt':
## File o directory non esistente
## Error in file(file, "rt"): non posso aprire questa connessione
counts=read.table(countFile, row.names=1, header=TRUE)
print('Pathway list selected:')
## [1] "Pathway list selected:"
print(head(res,10))
## [1] "/media/dario/dati/RNASeqGUI_Projects/CADS_FC/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Gage_Analysis/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Pathway_result.txt"
print('Count file selected:')
## [1] "Count file selected:"
print(head(counts))
## DEC_1 DEC_2 E2_1 E2_2 UNTR_1
## ENSMUSG00000063889 1386.2100 1296.7846 1840.5502 1797.3179 1927.78005
## ENSMUSG00000024231 1618.9080 1662.3452 1738.6008 1696.5656 1716.66789
## ENSMUSG00000024232 144.2284 159.8542 177.8831 178.9201 214.62411
## ENSMUSG00000073647 139.4464 131.0292 126.9828 108.9937 78.76874
## ENSMUSG00000024235 1926.7159 1819.7991 1337.5621 1318.2114 1214.82938
## ENSMUSG00000024234 913.4006 860.6585 927.9543 923.3442 924.83273
## UNTR_2
## ENSMUSG00000063889 1927.03014
## ENSMUSG00000024231 1643.01010
## ENSMUSG00000024232 230.77168
## ENSMUSG00000073647 67.22854
## ENSMUSG00000024235 1255.74910
## ENSMUSG00000024234 960.87190
#if(conversion==TRUE){
# if(hsa==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','hgnc_symbol'), mart=ensembl)}
# if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','mgi_symbol'), mart=ensembl)}
# if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','bdgp_symbol'), mart=ensembl)}
# if(dre==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','zfin_symbol'), mart=ensembl)}
#counts <- mol.sum(mol.data = counts, id.map = results,sum.method = 'mean') }
#if(conversion3==TRUE){newrownames = strsplit(rownames(counts),'\.')
# nrownames = NULL
# for (i in 1:length(newrownames) ){ nrownames[i] = newrownames[[i]][1]}
# rownames(counts) = nrownames
# if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','hgnc_symbol'), mart=ensembl)}
# if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','mgi_symbol'), mart=ensembl)}
# if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','bdgp_symbol'), mart=ensembl) }
# if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','zfin_symbol'), mart=ensembl)}
#counts <- mol.sum(mol.data = counts, id.map = results,sum.method = 'mean')}
counts <- LoadCachedObject(db, 'counts_key')
if (geneSet1 == TRUE){ #kegg
if(hsa==TRUE){ks=kegg.gsets(species = 'hsa', id.type = 'entrez')}
if(mmu==TRUE){ks=kegg.gsets(species = 'mmu', id.type = 'entrez')}
if(dme==TRUE){ks=kegg.gsets(species = 'dme', id.type = 'entrez')}
if(dre==TRUE){ks=kegg.gsets(species = 'dre', id.type = 'entrez')}
kegg.gs=ks$kg.sets
gs = rownames(res)[num_of_path]
print('Path selected:')
print(gs)
outname = gsub(' |:|/', '_', substr(gs, 0, 100))
if(hsa==TRUE){results1 <- getBM(attributes = c('entrezgene','hgnc_symbol'), mart=ensembl)}
if(mmu==TRUE){results1 <- getBM(attributes = c('entrezgene','mgi_symbol') , mart=ensembl)}
if(dme==TRUE){results1 <- getBM(attributes = c('entrezgene','bdgp_symbol'), mart=ensembl)}
if(dre==TRUE){results1 <- getBM(attributes = c('entrezgene','zfin_symbol'), mart=ensembl)}
kegg.gs[[gs]] <- mol.sum(mol.data = kegg.gs[[gs]], id.map = results1, sum.method = 'mean')
#gage::geneData(genes=rownames(kegg.gs[[gs]]),exprs=log(counts+1),ref=control,samp=treated,
#outname=outname,txt=T,heatmap=T,limit=3,scatterplot=T)
}
## [1] "Path selected:"
## NULL
## Error in kegg.gs[[gs]]: tentativo di selezione meno di un elemento
if (geneSet2 == TRUE){ #GO
data(bods)
if(hsa==TRUE){row=subset(bods, bods[,3] == 'hsa')}
if(mmu==TRUE){row=subset(bods, bods[,3] == 'mmu')}
if(dme==TRUE){row=subset(bods, bods[,3] == 'dme')}
if(dre==TRUE){row=subset(bods, bods[,3] == 'dre')}
go=go.gsets(species = row[2], id.type = 'entrez')
go.gs=go$go.sets
gs = rownames(res)[num_of_path]
outname = gsub(' |:|/', '_', substr(gs, 12, 100))
if(hsa==TRUE){results1 <- getBM(attributes = c('entrezgene','hgnc_symbol'), mart=ensembl)}
if(mmu==TRUE){results1 <- getBM(attributes = c('entrezgene','mgi_symbol') , mart=ensembl)}
if(dme==TRUE){results1 <- getBM(attributes = c('entrezgene','bdgp_symbol'), mart=ensembl)}
if(dre==TRUE){results1 <- getBM(attributes = c('entrezgene','zfin_symbol'), mart=ensembl)}
go.gs[[gs]] <- mol.sum(mol.data = go.gs[[gs]], id.map = results1, sum.method = 'mean')
#gage::geneData(genes=rownames(go.gs[[gs]]),exprs=log(counts+1),ref=control,samp=treated,
#outname=outname,txt=T,heatmap=T,limit=3,scatterplot=T)
}
Here starts the automatically generated code
2016-06-16 20:02:30 and the GAGE_result.txt file has been saved in the BMDC_analysis/Results folder.You chose the following Pathway/GO file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_results_NOISeq_Gage_Analysis/Proportion_counts_FeatureCounts.txt_UQUA.txt_E2_vs_UNTR.txt_results_NOISeq_Pathway_result.txt
,geneSet1:
TRUE
,geneSet2:
FALSE
,Project:
BMDC_analysis
,hsa:
FALSE
,mmu:
TRUE
,dme:
FALSE
,dre:
FALSE
,conversion:
TRUE
, num_of_path:
2
,countFile:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt
This R code has been run:
geneSet1 <- TRUE
geneSet2 <- FALSE
db <- InitDb(db.name = paste(geneSet1,geneSet2,'kegggoheatmap_db',sep='_'), db.path=file.path('cache'))
res <- LoadCachedObject(db, 'res_key')
Project <- LoadCachedObject(db, 'project_key')
hsa <- LoadCachedObject(db, 'hsa_key')
mmu <- LoadCachedObject(db, 'mmu_key')
dme <- LoadCachedObject(db, 'dme_key')
dre <- LoadCachedObject(db, 'dre_key')
conversion <- LoadCachedObject(db, 'conversion_key')
num_of_path <- LoadCachedObject(db, 'num_of_path_key')
countFile <- LoadCachedObject(db, 'countFile_key')
control <- LoadCachedObject(db, 'control_key')
treated <- LoadCachedObject(db, 'treated_key')
res=read.table(res, row.names=1, header=TRUE, sep='')
## Warning in file(file, "rt"): cannot open file '/
## media/dario/dati/RNASeqGUI_Projects/CADS_FC/Results/
## Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Gage_Analysis/
## Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Pathway_result.txt':
## File o directory non esistente
## Error in file(file, "rt"): non posso aprire questa connessione
counts=read.table(countFile, row.names=1, header=TRUE)
print('Pathway list selected:')
## [1] "Pathway list selected:"
print(head(res,10))
## [1] "/media/dario/dati/RNASeqGUI_Projects/CADS_FC/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Gage_Analysis/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Pathway_result.txt"
print('Count file selected:')
## [1] "Count file selected:"
print(head(counts))
## DEC_1 DEC_2 E2_1 E2_2 UNTR_1
## ENSMUSG00000063889 1386.2100 1296.7846 1840.5502 1797.3179 1927.78005
## ENSMUSG00000024231 1618.9080 1662.3452 1738.6008 1696.5656 1716.66789
## ENSMUSG00000024232 144.2284 159.8542 177.8831 178.9201 214.62411
## ENSMUSG00000073647 139.4464 131.0292 126.9828 108.9937 78.76874
## ENSMUSG00000024235 1926.7159 1819.7991 1337.5621 1318.2114 1214.82938
## ENSMUSG00000024234 913.4006 860.6585 927.9543 923.3442 924.83273
## UNTR_2
## ENSMUSG00000063889 1927.03014
## ENSMUSG00000024231 1643.01010
## ENSMUSG00000024232 230.77168
## ENSMUSG00000073647 67.22854
## ENSMUSG00000024235 1255.74910
## ENSMUSG00000024234 960.87190
#if(conversion==TRUE){
# if(hsa==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','hgnc_symbol'), mart=ensembl)}
# if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','mgi_symbol'), mart=ensembl)}
# if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','bdgp_symbol'), mart=ensembl)}
# if(dre==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','zfin_symbol'), mart=ensembl)}
#counts <- mol.sum(mol.data = counts, id.map = results,sum.method = 'mean') }
#if(conversion3==TRUE){newrownames = strsplit(rownames(counts),'\.')
# nrownames = NULL
# for (i in 1:length(newrownames) ){ nrownames[i] = newrownames[[i]][1]}
# rownames(counts) = nrownames
# if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','hgnc_symbol'), mart=ensembl)}
# if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','mgi_symbol'), mart=ensembl)}
# if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','bdgp_symbol'), mart=ensembl) }
# if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','zfin_symbol'), mart=ensembl)}
#counts <- mol.sum(mol.data = counts, id.map = results,sum.method = 'mean')}
counts <- LoadCachedObject(db, 'counts_key')
if (geneSet1 == TRUE){ #kegg
if(hsa==TRUE){ks=kegg.gsets(species = 'hsa', id.type = 'entrez')}
if(mmu==TRUE){ks=kegg.gsets(species = 'mmu', id.type = 'entrez')}
if(dme==TRUE){ks=kegg.gsets(species = 'dme', id.type = 'entrez')}
if(dre==TRUE){ks=kegg.gsets(species = 'dre', id.type = 'entrez')}
kegg.gs=ks$kg.sets
gs = rownames(res)[num_of_path]
print('Path selected:')
print(gs)
outname = gsub(' |:|/', '_', substr(gs, 0, 100))
if(hsa==TRUE){results1 <- getBM(attributes = c('entrezgene','hgnc_symbol'), mart=ensembl)}
if(mmu==TRUE){results1 <- getBM(attributes = c('entrezgene','mgi_symbol') , mart=ensembl)}
if(dme==TRUE){results1 <- getBM(attributes = c('entrezgene','bdgp_symbol'), mart=ensembl)}
if(dre==TRUE){results1 <- getBM(attributes = c('entrezgene','zfin_symbol'), mart=ensembl)}
kegg.gs[[gs]] <- mol.sum(mol.data = kegg.gs[[gs]], id.map = results1, sum.method = 'mean')
#gage::geneData(genes=rownames(kegg.gs[[gs]]),exprs=log(counts+1),ref=control,samp=treated,
#outname=outname,txt=T,heatmap=T,limit=3,scatterplot=T)
}
## [1] "Path selected:"
## NULL
## Error in kegg.gs[[gs]]: tentativo di selezione meno di un elemento
if (geneSet2 == TRUE){ #GO
data(bods)
if(hsa==TRUE){row=subset(bods, bods[,3] == 'hsa')}
if(mmu==TRUE){row=subset(bods, bods[,3] == 'mmu')}
if(dme==TRUE){row=subset(bods, bods[,3] == 'dme')}
if(dre==TRUE){row=subset(bods, bods[,3] == 'dre')}
go=go.gsets(species = row[2], id.type = 'entrez')
go.gs=go$go.sets
gs = rownames(res)[num_of_path]
outname = gsub(' |:|/', '_', substr(gs, 12, 100))
if(hsa==TRUE){results1 <- getBM(attributes = c('entrezgene','hgnc_symbol'), mart=ensembl)}
if(mmu==TRUE){results1 <- getBM(attributes = c('entrezgene','mgi_symbol') , mart=ensembl)}
if(dme==TRUE){results1 <- getBM(attributes = c('entrezgene','bdgp_symbol'), mart=ensembl)}
if(dre==TRUE){results1 <- getBM(attributes = c('entrezgene','zfin_symbol'), mart=ensembl)}
go.gs[[gs]] <- mol.sum(mol.data = go.gs[[gs]], id.map = results1, sum.method = 'mean')
#gage::geneData(genes=rownames(go.gs[[gs]]),exprs=log(counts+1),ref=control,samp=treated,
#outname=outname,txt=T,heatmap=T,limit=3,scatterplot=T)
}
Here starts the automatically generated code
2016-06-16 20:21:04 and the GAGE_result.txt file has been saved in the BMDC_analysis/Results folder.You chose the following Pathway/GO file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Gage_Analysis/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Pathway_result.txt
,geneSet1:
TRUE
,geneSet2:
FALSE
,Project:
BMDC_analysis
,hsa:
FALSE
,mmu:
TRUE
,dme:
FALSE
,dre:
FALSE
,conversion:
TRUE
, num_of_path:
5
,countFile:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt
This R code has been run:
geneSet1 <- TRUE
geneSet2 <- FALSE
db <- InitDb(db.name = paste(geneSet1,geneSet2,'kegggoheatmap_db',sep='_'), db.path=file.path('cache'))
res <- LoadCachedObject(db, 'res_key')
Project <- LoadCachedObject(db, 'project_key')
hsa <- LoadCachedObject(db, 'hsa_key')
mmu <- LoadCachedObject(db, 'mmu_key')
dme <- LoadCachedObject(db, 'dme_key')
dre <- LoadCachedObject(db, 'dre_key')
conversion <- LoadCachedObject(db, 'conversion_key')
num_of_path <- LoadCachedObject(db, 'num_of_path_key')
countFile <- LoadCachedObject(db, 'countFile_key')
control <- LoadCachedObject(db, 'control_key')
treated <- LoadCachedObject(db, 'treated_key')
res=read.table(res, row.names=1, header=TRUE, sep='')
## Warning in file(file, "rt"): cannot open file '/
## media/dario/dati/RNASeqGUI_Projects/CADS_FC/Results/
## Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Gage_Analysis/
## Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Pathway_result.txt':
## File o directory non esistente
## Error in file(file, "rt"): non posso aprire questa connessione
counts=read.table(countFile, row.names=1, header=TRUE)
print('Pathway list selected:')
## [1] "Pathway list selected:"
print(head(res,10))
## [1] "/media/dario/dati/RNASeqGUI_Projects/CADS_FC/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Gage_Analysis/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Pathway_result.txt"
print('Count file selected:')
## [1] "Count file selected:"
print(head(counts))
## DEC_1 DEC_2 E2_1 E2_2 UNTR_1
## ENSMUSG00000063889 1386.2100 1296.7846 1840.5502 1797.3179 1927.78005
## ENSMUSG00000024231 1618.9080 1662.3452 1738.6008 1696.5656 1716.66789
## ENSMUSG00000024232 144.2284 159.8542 177.8831 178.9201 214.62411
## ENSMUSG00000073647 139.4464 131.0292 126.9828 108.9937 78.76874
## ENSMUSG00000024235 1926.7159 1819.7991 1337.5621 1318.2114 1214.82938
## ENSMUSG00000024234 913.4006 860.6585 927.9543 923.3442 924.83273
## UNTR_2
## ENSMUSG00000063889 1927.03014
## ENSMUSG00000024231 1643.01010
## ENSMUSG00000024232 230.77168
## ENSMUSG00000073647 67.22854
## ENSMUSG00000024235 1255.74910
## ENSMUSG00000024234 960.87190
#if(conversion==TRUE){
# if(hsa==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','hgnc_symbol'), mart=ensembl)}
# if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','mgi_symbol'), mart=ensembl)}
# if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','bdgp_symbol'), mart=ensembl)}
# if(dre==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','zfin_symbol'), mart=ensembl)}
#counts <- mol.sum(mol.data = counts, id.map = results,sum.method = 'mean') }
#if(conversion3==TRUE){newrownames = strsplit(rownames(counts),'\.')
# nrownames = NULL
# for (i in 1:length(newrownames) ){ nrownames[i] = newrownames[[i]][1]}
# rownames(counts) = nrownames
# if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','hgnc_symbol'), mart=ensembl)}
# if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','mgi_symbol'), mart=ensembl)}
# if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','bdgp_symbol'), mart=ensembl) }
# if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','zfin_symbol'), mart=ensembl)}
#counts <- mol.sum(mol.data = counts, id.map = results,sum.method = 'mean')}
counts <- LoadCachedObject(db, 'counts_key')
if (geneSet1 == TRUE){ #kegg
if(hsa==TRUE){ks=kegg.gsets(species = 'hsa', id.type = 'entrez')}
if(mmu==TRUE){ks=kegg.gsets(species = 'mmu', id.type = 'entrez')}
if(dme==TRUE){ks=kegg.gsets(species = 'dme', id.type = 'entrez')}
if(dre==TRUE){ks=kegg.gsets(species = 'dre', id.type = 'entrez')}
kegg.gs=ks$kg.sets
gs = rownames(res)[num_of_path]
print('Path selected:')
print(gs)
outname = gsub(' |:|/', '_', substr(gs, 0, 100))
if(hsa==TRUE){results1 <- getBM(attributes = c('entrezgene','hgnc_symbol'), mart=ensembl)}
if(mmu==TRUE){results1 <- getBM(attributes = c('entrezgene','mgi_symbol') , mart=ensembl)}
if(dme==TRUE){results1 <- getBM(attributes = c('entrezgene','bdgp_symbol'), mart=ensembl)}
if(dre==TRUE){results1 <- getBM(attributes = c('entrezgene','zfin_symbol'), mart=ensembl)}
kegg.gs[[gs]] <- mol.sum(mol.data = kegg.gs[[gs]], id.map = results1, sum.method = 'mean')
#gage::geneData(genes=rownames(kegg.gs[[gs]]),exprs=log(counts+1),ref=control,samp=treated,
#outname=outname,txt=T,heatmap=T,limit=3,scatterplot=T)
}
## [1] "Path selected:"
## NULL
## Error in kegg.gs[[gs]]: tentativo di selezione meno di un elemento
if (geneSet2 == TRUE){ #GO
data(bods)
if(hsa==TRUE){row=subset(bods, bods[,3] == 'hsa')}
if(mmu==TRUE){row=subset(bods, bods[,3] == 'mmu')}
if(dme==TRUE){row=subset(bods, bods[,3] == 'dme')}
if(dre==TRUE){row=subset(bods, bods[,3] == 'dre')}
go=go.gsets(species = row[2], id.type = 'entrez')
go.gs=go$go.sets
gs = rownames(res)[num_of_path]
outname = gsub(' |:|/', '_', substr(gs, 12, 100))
if(hsa==TRUE){results1 <- getBM(attributes = c('entrezgene','hgnc_symbol'), mart=ensembl)}
if(mmu==TRUE){results1 <- getBM(attributes = c('entrezgene','mgi_symbol') , mart=ensembl)}
if(dme==TRUE){results1 <- getBM(attributes = c('entrezgene','bdgp_symbol'), mart=ensembl)}
if(dre==TRUE){results1 <- getBM(attributes = c('entrezgene','zfin_symbol'), mart=ensembl)}
go.gs[[gs]] <- mol.sum(mol.data = go.gs[[gs]], id.map = results1, sum.method = 'mean')
#gage::geneData(genes=rownames(go.gs[[gs]]),exprs=log(counts+1),ref=control,samp=treated,
#outname=outname,txt=T,heatmap=T,limit=3,scatterplot=T)
}
Here starts the automatically generated code
2016-06-16 20:24:31 and the GAGE_result.txt file has been saved in the BMDC_analysis/Results folder.You chose the following Pathway/GO file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Gage_Analysis/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Pathway_result.txt
,geneSet1:
TRUE
,geneSet2:
FALSE
,Project:
BMDC_analysis
,hsa:
FALSE
,mmu:
TRUE
,dme:
FALSE
,dre:
FALSE
,conversion:
TRUE
, num_of_path:
12
,countFile:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt
This R code has been run:
geneSet1 <- TRUE
geneSet2 <- FALSE
db <- InitDb(db.name = paste(geneSet1,geneSet2,'kegggoheatmap_db',sep='_'), db.path=file.path('cache'))
res <- LoadCachedObject(db, 'res_key')
Project <- LoadCachedObject(db, 'project_key')
hsa <- LoadCachedObject(db, 'hsa_key')
mmu <- LoadCachedObject(db, 'mmu_key')
dme <- LoadCachedObject(db, 'dme_key')
dre <- LoadCachedObject(db, 'dre_key')
conversion <- LoadCachedObject(db, 'conversion_key')
num_of_path <- LoadCachedObject(db, 'num_of_path_key')
countFile <- LoadCachedObject(db, 'countFile_key')
control <- LoadCachedObject(db, 'control_key')
treated <- LoadCachedObject(db, 'treated_key')
res=read.table(res, row.names=1, header=TRUE, sep='')
## Warning in file(file, "rt"): cannot open file '/
## media/dario/dati/RNASeqGUI_Projects/CADS_FC/Results/
## Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Gage_Analysis/
## Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Pathway_result.txt':
## File o directory non esistente
## Error in file(file, "rt"): non posso aprire questa connessione
counts=read.table(countFile, row.names=1, header=TRUE)
print('Pathway list selected:')
## [1] "Pathway list selected:"
print(head(res,10))
## [1] "/media/dario/dati/RNASeqGUI_Projects/CADS_FC/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Gage_Analysis/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Pathway_result.txt"
print('Count file selected:')
## [1] "Count file selected:"
print(head(counts))
## DEC_1 DEC_2 E2_1 E2_2 UNTR_1
## ENSMUSG00000063889 1386.2100 1296.7846 1840.5502 1797.3179 1927.78005
## ENSMUSG00000024231 1618.9080 1662.3452 1738.6008 1696.5656 1716.66789
## ENSMUSG00000024232 144.2284 159.8542 177.8831 178.9201 214.62411
## ENSMUSG00000073647 139.4464 131.0292 126.9828 108.9937 78.76874
## ENSMUSG00000024235 1926.7159 1819.7991 1337.5621 1318.2114 1214.82938
## ENSMUSG00000024234 913.4006 860.6585 927.9543 923.3442 924.83273
## UNTR_2
## ENSMUSG00000063889 1927.03014
## ENSMUSG00000024231 1643.01010
## ENSMUSG00000024232 230.77168
## ENSMUSG00000073647 67.22854
## ENSMUSG00000024235 1255.74910
## ENSMUSG00000024234 960.87190
#if(conversion==TRUE){
# if(hsa==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','hgnc_symbol'), mart=ensembl)}
# if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','mgi_symbol'), mart=ensembl)}
# if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','bdgp_symbol'), mart=ensembl)}
# if(dre==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','zfin_symbol'), mart=ensembl)}
#counts <- mol.sum(mol.data = counts, id.map = results,sum.method = 'mean') }
#if(conversion3==TRUE){newrownames = strsplit(rownames(counts),'\.')
# nrownames = NULL
# for (i in 1:length(newrownames) ){ nrownames[i] = newrownames[[i]][1]}
# rownames(counts) = nrownames
# if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','hgnc_symbol'), mart=ensembl)}
# if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','mgi_symbol'), mart=ensembl)}
# if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','bdgp_symbol'), mart=ensembl) }
# if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','zfin_symbol'), mart=ensembl)}
#counts <- mol.sum(mol.data = counts, id.map = results,sum.method = 'mean')}
counts <- LoadCachedObject(db, 'counts_key')
if (geneSet1 == TRUE){ #kegg
if(hsa==TRUE){ks=kegg.gsets(species = 'hsa', id.type = 'entrez')}
if(mmu==TRUE){ks=kegg.gsets(species = 'mmu', id.type = 'entrez')}
if(dme==TRUE){ks=kegg.gsets(species = 'dme', id.type = 'entrez')}
if(dre==TRUE){ks=kegg.gsets(species = 'dre', id.type = 'entrez')}
kegg.gs=ks$kg.sets
gs = rownames(res)[num_of_path]
print('Path selected:')
print(gs)
outname = gsub(' |:|/', '_', substr(gs, 0, 100))
if(hsa==TRUE){results1 <- getBM(attributes = c('entrezgene','hgnc_symbol'), mart=ensembl)}
if(mmu==TRUE){results1 <- getBM(attributes = c('entrezgene','mgi_symbol') , mart=ensembl)}
if(dme==TRUE){results1 <- getBM(attributes = c('entrezgene','bdgp_symbol'), mart=ensembl)}
if(dre==TRUE){results1 <- getBM(attributes = c('entrezgene','zfin_symbol'), mart=ensembl)}
kegg.gs[[gs]] <- mol.sum(mol.data = kegg.gs[[gs]], id.map = results1, sum.method = 'mean')
#gage::geneData(genes=rownames(kegg.gs[[gs]]),exprs=log(counts+1),ref=control,samp=treated,
#outname=outname,txt=T,heatmap=T,limit=3,scatterplot=T)
}
## [1] "Path selected:"
## NULL
## Error in kegg.gs[[gs]]: tentativo di selezione meno di un elemento
if (geneSet2 == TRUE){ #GO
data(bods)
if(hsa==TRUE){row=subset(bods, bods[,3] == 'hsa')}
if(mmu==TRUE){row=subset(bods, bods[,3] == 'mmu')}
if(dme==TRUE){row=subset(bods, bods[,3] == 'dme')}
if(dre==TRUE){row=subset(bods, bods[,3] == 'dre')}
go=go.gsets(species = row[2], id.type = 'entrez')
go.gs=go$go.sets
gs = rownames(res)[num_of_path]
outname = gsub(' |:|/', '_', substr(gs, 12, 100))
if(hsa==TRUE){results1 <- getBM(attributes = c('entrezgene','hgnc_symbol'), mart=ensembl)}
if(mmu==TRUE){results1 <- getBM(attributes = c('entrezgene','mgi_symbol') , mart=ensembl)}
if(dme==TRUE){results1 <- getBM(attributes = c('entrezgene','bdgp_symbol'), mart=ensembl)}
if(dre==TRUE){results1 <- getBM(attributes = c('entrezgene','zfin_symbol'), mart=ensembl)}
go.gs[[gs]] <- mol.sum(mol.data = go.gs[[gs]], id.map = results1, sum.method = 'mean')
#gage::geneData(genes=rownames(go.gs[[gs]]),exprs=log(counts+1),ref=control,samp=treated,
#outname=outname,txt=T,heatmap=T,limit=3,scatterplot=T)
}
Here starts the automatically generated code
2016-06-16 20:25:28 and the GAGE_result.txt file has been saved in the BMDC_analysis/Results folder.You chose the following Pathway/GO file:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Gage_Analysis/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Pathway_result.txt
,geneSet1:
TRUE
,geneSet2:
FALSE
,Project:
BMDC_analysis
,hsa:
FALSE
,mmu:
TRUE
,dme:
FALSE
,dre:
FALSE
,conversion:
TRUE
, num_of_path:
22
,countFile:
/RNASeqGUI_Projects/BMDC_analysis/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt
This R code has been run:
geneSet1 <- TRUE
geneSet2 <- FALSE
db <- InitDb(db.name = paste(geneSet1,geneSet2,'kegggoheatmap_db',sep='_'), db.path=file.path('cache'))
res <- LoadCachedObject(db, 'res_key')
Project <- LoadCachedObject(db, 'project_key')
hsa <- LoadCachedObject(db, 'hsa_key')
mmu <- LoadCachedObject(db, 'mmu_key')
dme <- LoadCachedObject(db, 'dme_key')
dre <- LoadCachedObject(db, 'dre_key')
conversion <- LoadCachedObject(db, 'conversion_key')
num_of_path <- LoadCachedObject(db, 'num_of_path_key')
countFile <- LoadCachedObject(db, 'countFile_key')
control <- LoadCachedObject(db, 'control_key')
treated <- LoadCachedObject(db, 'treated_key')
res=read.table(res, row.names=1, header=TRUE, sep='')
## Warning in file(file, "rt"): cannot open file '/
## media/dario/dati/RNASeqGUI_Projects/CADS_FC/Results/
## Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Gage_Analysis/
## Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Pathway_result.txt':
## File o directory non esistente
## Error in file(file, "rt"): non posso aprire questa connessione
counts=read.table(countFile, row.names=1, header=TRUE)
print('Pathway list selected:')
## [1] "Pathway list selected:"
print(head(res,10))
## [1] "/media/dario/dati/RNASeqGUI_Projects/CADS_FC/Results/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Gage_Analysis/Proportion_counts_FeatureCounts.txt_UQUA.txt_DEC_vs_UNTR.txt_prob=0.95_DE_UP_genes_NOISeq_Pathway_result.txt"
print('Count file selected:')
## [1] "Count file selected:"
print(head(counts))
## DEC_1 DEC_2 E2_1 E2_2 UNTR_1
## ENSMUSG00000063889 1386.2100 1296.7846 1840.5502 1797.3179 1927.78005
## ENSMUSG00000024231 1618.9080 1662.3452 1738.6008 1696.5656 1716.66789
## ENSMUSG00000024232 144.2284 159.8542 177.8831 178.9201 214.62411
## ENSMUSG00000073647 139.4464 131.0292 126.9828 108.9937 78.76874
## ENSMUSG00000024235 1926.7159 1819.7991 1337.5621 1318.2114 1214.82938
## ENSMUSG00000024234 913.4006 860.6585 927.9543 923.3442 924.83273
## UNTR_2
## ENSMUSG00000063889 1927.03014
## ENSMUSG00000024231 1643.01010
## ENSMUSG00000024232 230.77168
## ENSMUSG00000073647 67.22854
## ENSMUSG00000024235 1255.74910
## ENSMUSG00000024234 960.87190
#if(conversion==TRUE){
# if(hsa==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','hgnc_symbol'), mart=ensembl)}
# if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','mgi_symbol'), mart=ensembl)}
# if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','bdgp_symbol'), mart=ensembl)}
# if(dre==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','zfin_symbol'), mart=ensembl)}
#counts <- mol.sum(mol.data = counts, id.map = results,sum.method = 'mean') }
#if(conversion3==TRUE){newrownames = strsplit(rownames(counts),'\.')
# nrownames = NULL
# for (i in 1:length(newrownames) ){ nrownames[i] = newrownames[[i]][1]}
# rownames(counts) = nrownames
# if(hsa==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='hsapiens_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','hgnc_symbol'), mart=ensembl)}
# if(mmu==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='mmusculus_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','mgi_symbol'), mart=ensembl)}
# if(dme==TRUE){ ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='dmelanogaster_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','bdgp_symbol'), mart=ensembl) }
# if(dre==TRUE){ensembl=useMart('ENSEMBL_MART_ENSEMBL', host='www.ensembl.org', dataset='drerio_gene_ensembl')
# results <- getBM(attributes = c('ensembl_gene_id','zfin_symbol'), mart=ensembl)}
#counts <- mol.sum(mol.data = counts, id.map = results,sum.method = 'mean')}
counts <- LoadCachedObject(db, 'counts_key')
if (geneSet1 == TRUE){ #kegg
if(hsa==TRUE){ks=kegg.gsets(species = 'hsa', id.type = 'entrez')}
if(mmu==TRUE){ks=kegg.gsets(species = 'mmu', id.type = 'entrez')}
if(dme==TRUE){ks=kegg.gsets(species = 'dme', id.type = 'entrez')}
if(dre==TRUE){ks=kegg.gsets(species = 'dre', id.type = 'entrez')}
kegg.gs=ks$kg.sets
gs = rownames(res)[num_of_path]
print('Path selected:')
print(gs)
outname = gsub(' |:|/', '_', substr(gs, 0, 100))
if(hsa==TRUE){results1 <- getBM(attributes = c('entrezgene','hgnc_symbol'), mart=ensembl)}
if(mmu==TRUE){results1 <- getBM(attributes = c('entrezgene','mgi_symbol') , mart=ensembl)}
if(dme==TRUE){results1 <- getBM(attributes = c('entrezgene','bdgp_symbol'), mart=ensembl)}
if(dre==TRUE){results1 <- getBM(attributes = c('entrezgene','zfin_symbol'), mart=ensembl)}
kegg.gs[[gs]] <- mol.sum(mol.data = kegg.gs[[gs]], id.map = results1, sum.method = 'mean')
#gage::geneData(genes=rownames(kegg.gs[[gs]]),exprs=log(counts+1),ref=control,samp=treated,
#outname=outname,txt=T,heatmap=T,limit=3,scatterplot=T)
}
## [1] "Path selected:"
## NULL
## Error in kegg.gs[[gs]]: tentativo di selezione meno di un elemento
if (geneSet2 == TRUE){ #GO
data(bods)
if(hsa==TRUE){row=subset(bods, bods[,3] == 'hsa')}
if(mmu==TRUE){row=subset(bods, bods[,3] == 'mmu')}
if(dme==TRUE){row=subset(bods, bods[,3] == 'dme')}
if(dre==TRUE){row=subset(bods, bods[,3] == 'dre')}
go=go.gsets(species = row[2], id.type = 'entrez')
go.gs=go$go.sets
gs = rownames(res)[num_of_path]
outname = gsub(' |:|/', '_', substr(gs, 12, 100))
if(hsa==TRUE){results1 <- getBM(attributes = c('entrezgene','hgnc_symbol'), mart=ensembl)}
if(mmu==TRUE){results1 <- getBM(attributes = c('entrezgene','mgi_symbol') , mart=ensembl)}
if(dme==TRUE){results1 <- getBM(attributes = c('entrezgene','bdgp_symbol'), mart=ensembl)}
if(dre==TRUE){results1 <- getBM(attributes = c('entrezgene','zfin_symbol'), mart=ensembl)}
go.gs[[gs]] <- mol.sum(mol.data = go.gs[[gs]], id.map = results1, sum.method = 'mean')
#gage::geneData(genes=rownames(go.gs[[gs]]),exprs=log(counts+1),ref=control,samp=treated,
#outname=outname,txt=T,heatmap=T,limit=3,scatterplot=T)
}