Mercurial > repos > ning > ebseq
changeset 28:97d36e663171 draft
Deleted selected files
author | ning |
---|---|
date | Mon, 16 Jun 2014 16:17:36 -0400 |
parents | fdbabf28d095 |
children | f2327f520c4d |
files | ChoosePatterns.R ChoosePatterns.xml EBGeneMultiCondTest.R EBGeneMultiCondTest.xml EBGeneTwoCondTest.R EBGeneTwoCondTest.xml EBIsoformMultiCondTest.R EBIsoformMultiCondTest.xml EBIsoformTwoCondTest.R EBIsoformTwoCondTest.xml GetAllPatterns.R GetAllPatterns.xml GetIg.R GetIg.xml GetNormalizedExpression.R GetNormalizedExpression.xml |
diffstat | 16 files changed, 0 insertions(+), 623 deletions(-) [+] |
line wrap: on
line diff
--- a/ChoosePatterns.R Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,27 +0,0 @@ -sink(file="/tmp/none") -sink("/dev/null") -options(warn=-1) -options(echo=F) - -#invisible("EBSeq") -suppressMessages(library("EBSeq")) - -args <- commandArgs(trailingOnly = T) -inputfile <- args[1] -Idx <- args[2] -outputfile <- args[3] - -print(args) - -ReadIn=read.table(inputfile,stringsAsFactors=F,header=T, sep="\t") - -IndexIn=strsplit(Idx,split=",")[[1]] -Index=as.numeric(IndexIn) - -Mat=data.matrix(ReadIn) - -Out=Mat[Index,] - - -write.table(Out,file=outputfile,quote=F,col.names=T,row.names=T,sep = "\t") -
--- a/ChoosePatterns.xml Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,19 +0,0 @@ -<tool id="Choose_Patterns" name="Choose Patterns of interests in a Multiple Condition Design"> - <description>Choose patterns of interests in a multiple condition design</description> - <command>R --quiet --slave --file=$GALAXY_ROOT_DIR/tools/EBSeq/ChoosePatterns.R --args $All_Possible_Patterns $Rows_of_interests $output</command> - <inputs> - <param name="All_Possible_Patterns" type="data" label="All Possible Patterns" help=""/> - <param name="Rows_of_interests" type="text" size="60" value="1,2,3" label="Enter the rows - of interests (separated by comma, no space please)" /> - </inputs> - <outputs> - <data format="tabular" name="output" /> - </outputs> - -<help> -Input could be obtained from Get All Possible Patterns Function - -</help> - - -</tool>
--- a/EBGeneMultiCondTest.R Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,65 +0,0 @@ -sink(file="/tmp/none") -sink("/dev/null") -options(warn=-1) -options(echo=F) - -invisible("EBSeq") -suppressMessages(library("EBSeq")) - -args <- commandArgs(trailingOnly = T) -inputfile <- args[1] -WhetherSampleName <- args[2] -CondIn <- args[3] -PatternFile <- args[4] -outputfile <- args[5] -MAP.out<-args[6] -Sizesout <-args[7] - -#write.table(PatternFile,outputfile,quote=F,col.names=T,row.names=T,sep = "\t") - -#write.table(args,outputfile,quote=F,col.names=T,row.names=T,sep = "\t") - -Conditions=strsplit(CondIn,split=",")[[1]] - -if(WhetherSampleName=="y"){ - ReadIn=read.table(inputfile,stringsAsFactors=F,header=T, sep="\t") - Names=names(ReadIn)[-1] - } -if(WhetherSampleName=="n"){ - ReadIn=read.table(inputfile,stringsAsFactors=F,header=F, sep="\t") - Names=paste0("S",1:length(Conditions)) -} - -PatternIn=read.table(PatternFile,stringsAsFactors=F,header=T,sep="\t") - -if(class(ReadIn[[1]])=="character"){ - GeneMat=do.call(cbind,ReadIn[-1]) - rownames(GeneMat)=ReadIn[[1]] - colnames(GeneMat)=Names -} -if(class(ReadIn[[1]])=="numeric"){ - GeneMat=data.matrix(ReadIn) - colnames(GeneMat)=Names - } - -Patterns=data.matrix(PatternIn) - - -Sizes=MedianNorm(GeneMat) -EBOut=EBMultiTest(Data=GeneMat,Conditions=as.factor(Conditions), - AllParti=Patterns,sizeFactors=Sizes, maxround=5) -PPout=GetMultiPP(EBOut) -MultiPP=PPout$PP -MultiMAP=PPout$MAP -Data.norm=round(GetNormalizedMat(GeneMat, Sizes),2) - -Mat=cbind(MultiMAP,Data.norm[names(MultiMAP),]) - -colnames(Mat)= -c("MAP",Names) -options(warn=-1) - -write.table(round(MultiPP,2),file=outputfile,quote=F,col.names=T,row.names=T,sep = "\t") -write.table(Mat,file=MAP.out ,quote=F,col.names=T,row.names=T,sep = "\t") -write.table(Sizes,file=Sizesout,quote=F,col.names=F,row.names=F,sep = "\t") -
--- a/EBGeneMultiCondTest.xml Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,34 +0,0 @@ -<tool id="EBGeneMultiCondTest" name="Gene level DE test across multiple conditions"> - <description>Runs EBSeq to find DE genes across multiple (more than two) conditions</description> - <command>R --quiet --slave --file=$GALAXY_ROOT_DIR/tools/EBSeq/EBGeneMultiCondTest.R --args $Gene_Expression $First_Row_Sample_Names $Conditions $Patterns $PP_of_each_pattern $Pattern_with_highest_PP $Sizes</command> - <inputs> - <param name="Gene_Expression" type="data" format="tabular" label="Gene Expression (tab delimited, please use the unnormalized values, e.g. expected counts form RSEM)"/> - <param name="First_Row_Sample_Names" type="select" format="text"> - <label>The First Row is Sample Names?</label> - <option value="y">Yes</option> - <option value="n">No</option> - </param> - <param name="Conditions" type="text" size="60" value="C1,C2" label="Enter which condition each - sample belongs to (separated by comma, no space please)." - help=""/> - <param name="Patterns" type="data" format="tabular" label="Patterns of Interests"/> - </inputs> - <outputs> - <data format="tabular" name="PP_of_each_pattern" /> - <data format="tabular" name="Pattern_with_highest_PP" /> - <data format="tabular" name="Sizes" /> - </outputs> - - <help> -The input Conditions should have exactly two levels. The length of the Condition vector should be exactly the same as the number of columns in the data file (except the gene names column). - -The patterns of interests could be obtained by function Get All Possible Patterns (and optionally, if there are too many patterns generated, the function Choose Patterns could be used to choose only subset of the patterns.) - -Three output files will be generated. The first file contains the Posterior probability of being each pattern. The second file contains the pattern with highest PP for each gene and the normalized expressions. Genes are with the same order as in input file. -The last file provides the library size factor for each sample. - - -</help> - - -</tool>
--- a/EBGeneTwoCondTest.R Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,71 +0,0 @@ -sink(file="/tmp/none") -sink("/dev/null") -options(warn=-1) -options(echo=F) - -invisible("EBSeq") -suppressMessages(library("EBSeq")) - -args <- commandArgs(trailingOnly = T) -inputfile <- args[1] -WhetherSampleName <- args[2] -CondIn <- args[3] -FDR <- args[4] -outputfile <- args[5] -Sort.out<-args[6] -Sort.out.FDR <-args[7] -Sizesout <-args[8] - -Conditions=strsplit(CondIn,split=",")[[1]] - -if(WhetherSampleName=="y"){ - ReadIn=read.table(inputfile,stringsAsFactors=F,header=T,sep="\t") - Names=names(ReadIn)[-1] - } -if(WhetherSampleName=="n"){ - ReadIn=read.table(inputfile,stringsAsFactors=F,header=F,sep="\t") - Names=paste0("S",1:length(Conditions)) -} - -if(class(ReadIn[[1]])=="character"){ - GeneMat=do.call(cbind,ReadIn[-1]) - rownames(GeneMat)=ReadIn[[1]] - colnames(GeneMat)=Names -} -if(class(ReadIn[[1]])=="numeric"){ - GeneMat=data.matrix(ReadIn) - colnames(GeneMat)=Names - } - - -Sizes=MedianNorm(GeneMat) -EBOut=EBTest(Data=GeneMat,Conditions=as.factor(Conditions),sizeFactors=Sizes, maxround=5) -PP=GetPP(EBOut) -PP.sort=sort(PP,decreasing=T) -PP.sort.FDR=PP.sort[which(PP.sort>=1-as.numeric(FDR))] - -Data.norm=GetNormalizedMat(GeneMat, Sizes) -FC=PostFC(EBOut) -realFC=FC[[2]] -postFC=FC[[1]] - -Mat=cbind(PP, realFC[names(PP)], postFC[names(PP)],Data.norm[names(PP),]) -Mat.sort=cbind(PP.sort, realFC[names(PP.sort)], postFC[names(PP.sort)],Data.norm[names(PP.sort),]) - - -if(length(PP.sort.FDR)>1)Mat.sort.FDR=cbind(PP.sort.FDR, realFC[names(PP.sort.FDR)], postFC[names(PP.sort.FDR)],Data.norm[names(PP.sort.FDR),]) - -if(length(PP.sort.FDR)==1)Mat.sort.FDR=matrix( - c(PP.sort.FDR, realFC[names(PP.sort.FDR)], postFC[names(PP.sort.FDR)],Data.norm[names(PP.sort.FDR),]) - ,nrow=1) - -colnames(Mat)=colnames(Mat.sort)= - c("PPDE","RealFC","PosteriorFC",colnames(Data.norm)) -if(length(PP.sort.FDR)>0)colnames(Mat.sort.FDR)= - c("PPDE","RealFC","PosteriorFC",colnames(Data.norm)) - -write.table(round(Mat,2),file=outputfile,quote=F,col.names=T,row.names=T,sep = "\t") -write.table(round(Mat.sort,2),file=Sort.out ,quote=F,col.names=T,row.names=T,sep = "\t") -if(length(PP.sort.FDR)>0)write.table(round(Mat.sort.FDR,2),file=Sort.out.FDR,quote=F,col.names=T,row.names=T,sep = "\t") -write.table(Sizes,file=Sizesout,quote=F,col.names=F,row.names=F,sep = "\t") -
--- a/EBGeneTwoCondTest.xml Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,39 +0,0 @@ -<tool id="EBGeneTwoCondTest" name="Gene level DE test across two conditions"> - <description>Runs EBSeq to find DE genes across two conditions</description> - <command>R --quiet --slave --file=$GALAXY_ROOT_DIR/tools/EBSeq/EBGeneTwoCondTest.R --args $Gene_Expression $First_Row_Sample_Names $Conditions $Target_FDR $Output $Sorted_Output $Sorted_Output_with_target_FDR $Sizes</command> - <inputs> - <param name="Gene_Expression" type="data" format="tabular" label="Gene Expression (tab delimited, please use the unnormalized values, e.g. expected counts form RSEM)"/> - <param name="First_Row_Sample_Names" type="select" format="text"> - <label>The First Row is Sample Names?</label> - <option value="y">Yes</option> - <option value="n">No</option> - </param> - <param name="Conditions" type="text" size="60" value="C1,C2" label="Enter which condition each - sample belongs to (separated by comma, no space please)." - help=""/> - <param name="Target_FDR" type="text" format="tabular" value="0.05" label="Target FDR" - /> - </inputs> - <outputs> - <data format="tabular" name="Output" /> - <data format="tabular" name="Sorted_Output" /> - <data format="tabular" name="Sorted_Output_with_target_FDR" /> - <data format="tabular" name="Sizes" /> - </outputs> - - <help> -The input Conditions should have exactly two levels. The length of the Condition vector should be exactly the same as the number of -columns in the data file (except the gene names column). - -Four output files will be generated. Each of the first 3 files contains Posterior probability of being -DE (PPDE), Fold Change (RealFC), Posterior Fold Change (PostFC) and normalized gene expressions. -The Four files are: -Genes with the same order as in input file; -Genes sorted by PPDE; DE Genes under target FDR (PPDE>=TargetFDR) -and sorted by PPDE; -Library size factor for each sample. - -</help> - - -</tool>
--- a/EBIsoformMultiCondTest.R Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,66 +0,0 @@ -sink(file="/tmp/none") -sink("/dev/null") -options(warn=-1) -options(echo=F) - -invisible("EBSeq") -suppressMessages(library("EBSeq")) - -args <- commandArgs(trailingOnly = T) -inputfile <- args[1] -WhetherSampleName <- args[2] -CondIn <- args[3] -PatternFile <- args[5] -Ig.file <- args[4] -outputfile <- args[6] -MAP.out<-args[7] -Sizesout <-args[8] - -#write.table(args,file=outputfile,quote=F,col.names=T,row.names=T,sep = "\t") - - -Conditions=strsplit(CondIn,split=",")[[1]] -if(WhetherSampleName=="y"){ - ReadIn=read.table(inputfile,stringsAsFactors=F,header=T, sep="\t") - Names=names(ReadIn)[-1] - } -if(WhetherSampleName=="n"){ - ReadIn=read.table(inputfile,stringsAsFactors=F,header=F, sep="\t") - Names=paste0("S",1:length(Conditions)) -} - -PatternIn=read.table(PatternFile,stringsAsFactors=F,header=T,sep="\t") -IgVIn=read.table(Ig.file,stringsAsFactors=F,header=F,sep="\t") -IgV=IgVIn[[1]] - -if(class(ReadIn[[1]])=="character"){ - GeneMat=do.call(cbind,ReadIn[-1]) - rownames(GeneMat)=ReadIn[[1]] - colnames(GeneMat)=Names -} -if(class(ReadIn[[1]])=="numeric"){ - GeneMat=data.matrix(ReadIn) - colnames(GeneMat)=Names - } - -Patterns=data.matrix(PatternIn) - -Sizes=MedianNorm(GeneMat) -#write.table(Conditions,file=outputfile,quote=F,col.names=T,row.names=T,sep = "\t") -EBOut=EBMultiTest(Data=GeneMat,NgVector=IgV,Conditions=as.factor(Conditions), - AllParti=Patterns,sizeFactors=Sizes, maxround=5) -PPout=GetMultiPP(EBOut) -MultiPP=PPout$PP -MultiMAP=PPout$MAP -Data.norm=round(GetNormalizedMat(GeneMat, Sizes),2) - -Mat=cbind(MultiMAP,Data.norm[names(MultiMAP),]) - -colnames(Mat)= -c("MAP",Names) -options(warn=-1) - -write.table(round(MultiPP,2),file=outputfile,quote=F,col.names=T,row.names=T,sep = "\t") -write.table(Mat,file=MAP.out ,quote=F,col.names=T,row.names=T,sep = "\t") -write.table(Sizes,file=Sizesout,quote=F,col.names=F,row.names=F,sep = "\t") -
--- a/EBIsoformMultiCondTest.xml Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,37 +0,0 @@ -<tool id="EBIsoformMultiCondTest" name="Isoform level DE test across multiple conditions"> - <description>Runs EBSeq to find DE isoforms across multiple (more than two) conditions</description> - <command>R --quiet --slave --file=$GALAXY_ROOT_DIR/tools/EBSeq/EBIsoformMultiCondTest.R --args $Isoform_Expression $First_Row_Sample_Names $Conditions $Ig_Vector $Patterns_of_Interests $PP_of_each_pattern $Pattern_with_highest_PP $Sizes</command> - <inputs> - <param name="Isoform_Expression" type="data" format="tabular" label="Isoform Expression (tab delimited, please use the unnormalized values, e.g. expected counts form RSEM)"/> - <param name="First_Row_Sample_Names" type="select" format="text"> - <label>The First Row is Sample Names?</label> - <option value="y">Yes</option> - <option value="n">No</option> - </param> - <param name="Conditions" type="text" size="60" value="C1,C2" label="Enter which condition each - sample belongs to (separated by comma, no space please)." - help=""/> - <param name="Ig_Vector" type="data" format="tabular" label="Ig Vector to define the uncertainty groups"/> - <param name="Patterns_of_Interests" type="data" format="tabular" label="Patterns of Interests"/> - </inputs> - <outputs> - <data format="tabular" name="PP_of_each_pattern" /> - <data format="tabular" name="Pattern_with_highest_PP" /> - <data format="tabular" name="Sizes" /> - </outputs> - - <help> -The input Conditions should have exactly two levels. The length of the Condition vector should be exactly the same as the number of columns in the data file (except the isoform names column). - -The patterns of interests could be obtained by function Get All Possible Patterns (and optionally, if there are too many patterns generated, the function Choose Patterns could be used to choose only subset of the patterns.) - -The Ig Vector could be generated by the GetIg function or obtained from RSEM output. - -Three output files will be generated. The first file contains the Posterior probability of being each pattern. -The second file contains the pattern with highest PP for each isoform and the normalized expressions.Isoforms are with the same order as in input file. -The last file provides the library size factor for each sample. - -</help> - - -</tool>
--- a/EBIsoformTwoCondTest.R Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,75 +0,0 @@ -sink(file="/tmp/none") -sink("/dev/null") -options(warn=-1) -options(echo=F) - -invisible("EBSeq") -suppressMessages(library("EBSeq")) - -args <- commandArgs(trailingOnly = T) -inputfile <- args[1] -WhetherSampleName <- args[2] -CondIn <- args[3] -Ig.file <-args[4] -FDR <- args[5] -outputfile <- args[6] -Sort.out<-args[7] -Sort.out.FDR <-args[8] -Sizesout <-args[9] - - -Conditions=strsplit(CondIn,split=",")[[1]] -if(WhetherSampleName=="y"){ - ReadIn=read.table(inputfile,stringsAsFactors=F,header=T,sep="\t") - Names=names(ReadIn)[-1] - } -if(WhetherSampleName=="n"){ - ReadIn=read.table(inputfile,stringsAsFactors=F,header=F, sep="\t") - Names=paste0("S",1:length(Conditions)) -} - -if(class(ReadIn[[1]])=="character"){ - GeneMat=do.call(cbind,ReadIn[-1]) - rownames(GeneMat)=ReadIn[[1]] - colnames(GeneMat)=Names -} -if(class(ReadIn[[1]])=="numeric"){ - GeneMat=data.matrix(ReadIn) - colnames(GeneMat)=Names - } - -IgVIn=read.csv(Ig.file,stringsAsFactors=F,header=F) -IgV=IgVIn[[1]] -Conditions=strsplit(CondIn,split=",")[[1]] - -Sizes=MedianNorm(GeneMat) -EBOut=EBTest(Data=GeneMat,NgVector=IgV,Conditions=as.factor(Conditions),sizeFactors=Sizes, maxround=5) -PP=GetPP(EBOut) -PP.sort=sort(PP,decreasing=T) -PP.sort.FDR=PP.sort[which(PP.sort>=1-as.numeric(FDR))] - -Data.norm=GetNormalizedMat(GeneMat, Sizes) -FC=PostFC(EBOut) -realFC=FC[[2]] -postFC=FC[[1]] - -Mat=cbind(PP, realFC[names(PP)], postFC[names(PP)],Data.norm[names(PP),]) -Mat.sort=cbind(PP.sort, realFC[names(PP.sort)], postFC[names(PP.sort)],Data.norm[names(PP.sort),]) - - -if(length(PP.sort.FDR)>1)Mat.sort.FDR=cbind(PP.sort.FDR, realFC[names(PP.sort.FDR)], postFC[names(PP.sort.FDR)],Data.norm[names(PP.sort.FDR),]) - -if(length(PP.sort.FDR)==1)Mat.sort.FDR=matrix( - c(PP.sort.FDR, realFC[names(PP.sort.FDR)], postFC[names(PP.sort.FDR)],Data.norm[names(PP.sort.FDR),]) - ,nrow=1) - -colnames(Mat)=colnames(Mat.sort)= - c("PPDE","RealFC","PosteriorFC",colnames(Data.norm)) -if(length(PP.sort.FDR)>0)colnames(Mat.sort.FDR)= - c("PPDE","RealFC","PosteriorFC",colnames(Data.norm)) - -write.table(round(Mat,2),file=outputfile,quote=F,col.names=T,row.names=T,sep = "\t") -write.table(round(Mat.sort,2),file=Sort.out ,quote=F,col.names=T,row.names=T,sep = "\t") -if(length(PP.sort.FDR)>0)write.table(round(Mat.sort.FDR,2),file=Sort.out.FDR,quote=F,col.names=T,row.names=T,sep = "\t") -write.table(Sizes,file=Sizesout,quote=F,col.names=F,row.names=F,sep = "\t") -
--- a/EBIsoformTwoCondTest.xml Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,41 +0,0 @@ -<tool id="EBIsoformTwoCondTest" name="Isoform level DE test across two conditions"> - <description>Runs EBSeq to find DE isoforms across two conditions</description> - <command>R --quiet --slave --file=$GALAXY_ROOT_DIR/tools/EBSeq/EBIsoformTwoCondTest.R --args $Isoform_Expression $First_Row_Sample_Names $Conditions $Ig_Vector $Target_FDR $Output $Sorted_Output $Sorted_Outpu_with_target_FDR $Sizes</command> - <inputs> - <param name="Isoform_Expression" type="data" format="tabular" label="Isoform Expression (tab delimited, please use the unnormalized values, e.g. expected counts form RSEM)"/> - <param name="First_Row_Sample_Names" type="select" format="text"> - <label>The First Row is Sample Names?</label> - <option value="y">Yes</option> - <option value="n">No</option> - </param> - <param name="Conditions" type="text" size="60" value="C1,C2" label="Enter which condition each - sample belongs to (separated by comma, no space please)." - help=""/> - <param name="Ig_Vector" type="data" format="tabular" label="Ig Vector to define the uncertainty groups"/> - <param name="Target_FDR" type="text" format="tabular" value="0.05" label="Target FDR" - /> - </inputs> - <outputs> - <data format="tabular" name="Output" /> - <data format="tabular" name="Sorted_Output" /> - <data format="tabular" name="Sorted_Outpu_with_target_FDR" /> - <data format="tabular" name="Sizes" /> - </outputs> - - <help> -The input Conditions should have exactly two levels. The length of the Condition vector should be exactly the same as the number of columns in the data file (except the isoform names column). - -The Ig Vector could be generated by the GetIg function or obtained from RSEM output. - -Four output files will be generated. Each of the first 3 files contains Posterior probability of being DE (PPDE), Fold Change (RealFC), Posterior Fold Change (PostFC) and normalized isoform expressions. -The four files are: - -Isoforms with the same order as in input file; -Isoforms sorted by PPDE; DE Isoforms under target FDR (PPDE>=TargetFDR) -and sorted by PPDE; -Library size factor for each sample. - -</help> - - -</tool>
--- a/GetAllPatterns.R Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,23 +0,0 @@ -sink(file="/tmp/none") -sink("/dev/null") -options(warn=-1) -options(echo=F) - -invisible("EBSeq") -suppressMessages(library("EBSeq")) - -args <- commandArgs() -inputfile <- args[6] -outputfile <- args[7] -#PairwisePlots <-args[6] - -print(args) - -Conds=strsplit(inputfile,split=",")[[1]] - - -Out=GetPatterns(Conds) - - -write.table(Out,file=outputfile,quote=F,col.names=T,row.names=T,sep = "\t") -
--- a/GetAllPatterns.xml Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,19 +0,0 @@ -<tool id="Get_All_Patterns" name="Get All Possible Patterns in a Multiple Condition Design"> - <description>Get all possible patterns in a multiple condition design</description> - <command>R --quiet --slave --file=$GALAXY_ROOT_DIR/tools/EBSeq/GetAllPatterns.R --args $input $output</command> -<inputs> - <param name="input" type="text" size="60" value="C1,C2,C3" label="Enter the condition names - (separated by comma, no space please - )" help=""/> - </inputs> - <outputs> - <data format="tabular" name="output" /> - </outputs> - -<help> - - -</help> - - -</tool>
--- a/GetIg.R Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,23 +0,0 @@ -sink(file="/tmp/none") -sink("/dev/null") -options(warn=-1) -options(echo=F) - -invisible("EBSeq") -suppressMessages(library("EBSeq")) - -args <- commandArgs(trailingOnly = T) -inputfile <- args[1] -outputfile <- args[2] - -print(args) - -a1=read.csv(inputfile,stringsAsFactors=F,header=F, sep="\t") -Ng=GetNg(a1[[1]],a1[[2]]) -Ig=Ng$IsoformNgTrun - - - - -write.table(Ig,file=outputfile,quote=F,col.names=F,row.names=F,sep = "\t") -
--- a/GetIg.xml Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,18 +0,0 @@ -<tool id="Get_Ig" name="Get Ig vector from gene-isoform mapping for isoform level DE analysis"> - <description>Get Ig vector from gene-isoform mapping for isoform leve - l DE analysis</description> - <command>R --quiet --slave --file=$GALAXY_ROOT_DIR/tools/EBSeq/GetIg.R --args $input $output</command> - <inputs> - <param name="input" type="data" size="5" value="" label="" help="The first column should be gene names and the second column should be isoform names. No headers please."/> - </inputs> - <outputs> - <data format="tabular" name="output" /> - </outputs> - - <help> - - -</help> - - -</tool>
--- a/GetNormalizedExpression.R Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,41 +0,0 @@ -sink(file="/tmp/none") -sink("/dev/null") -options(warn=-1) -options(echo=F) - -invisible("EBSeq") -suppressMessages(library("EBSeq")) - -args <- commandArgs(trailingOnly = T) -inputfile <- args[1] -WhetherSampleName <- args[2] -outputfile <- args[3] -Boxplots<-args[4] -Sizesout <-args[5] - -print(args) - -if(WhetherSampleName=="y"){ - ReadIn=read.table(inputfile,stringsAsFactors=F,header=T, sep="\t") - Names=names(ReadIn)[-1] - } -if(WhetherSampleName=="n"){ - ReadIn=read.table(inputfile,stringsAsFactors=F,header=F, sep="\t") -} - -GeneMat=do.call(cbind,ReadIn[-1]) -rownames(GeneMat)=ReadIn[[1]] -if(WhetherSampleName=="y")colnames(GeneMat)=Names - - -Sizes=MedianNorm(GeneMat) - -Data.norm=GetNormalizedMat(GeneMat, Sizes) - -write.table(round(Data.norm,2),file=outputfile,quote=F,col.names=T,row.names=T,sep = "\t") -pdf(Boxplots) -boxplot(Data.norm,log="y",ylim=c(10^-1,10^6)) -dev.off() - -write.table(Sizes,file=Sizesout,quote=F,col.names=F,row.names=F,sep = "\t") -
--- a/GetNormalizedExpression.xml Mon Jun 16 16:16:43 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,25 +0,0 @@ -<tool id="Get_Normalized_Expressions" name="Get Normalized Expressions"> - <description>Calculate normalization factors and get the normalized expression matrix</description> - <command>R --quiet --slave --file=$GALAXY_ROOT_DIR/tools/EBSeq/GetNormalizedExpression.R --args $Gene_Expression $First_Row_Sample_Names $output $Boxplots $Sizes </command> - <inputs> - <param name="Gene_Expression" type="data" format="tabular" label="Gene Expression (tab delimited)"/> - <param name="First_Row_Sample_Names" type="select" format="text"> - <label>The First Row is Sample Names?</label> - <option value="y">Yes</option> - <option value="n">No</option> - </param> - </inputs> - <outputs> - <data format="tabular" name="output" /> - <data format="pdf" name="Boxplots" /> - <data format="tabular" name="Sizes" /> - </outputs> - - <help> -The function would provide the normalized expression values (normalized by the library size factors) and estimated library size factors. -A boxplot for checking will also be generated. - -</help> - - -</tool>