Mercurial > repos > proteore > proteore_expression_rnaseq_abbased
changeset 5:f15cdeeba4b4 draft
planemo upload commit 4af7ac25de19ca10b1654820e909c647a2d337b2-dirty
| author | proteore |
|---|---|
| date | Mon, 19 Mar 2018 10:07:38 -0400 |
| parents | 2f95774977ff |
| children | 71214d6034e7 |
| files | expression_rnaseq_abbased.xml get_data_HPA_v2.R |
| diffstat | 2 files changed, 34 insertions(+), 14 deletions(-) [+] |
line wrap: on
line diff
--- a/expression_rnaseq_abbased.xml Wed Mar 14 11:27:05 2018 -0400 +++ b/expression_rnaseq_abbased.xml Mon Mar 19 10:07:38 2018 -0400 @@ -12,11 +12,11 @@ #if $inputtype.filetype == "copy_paste": - Rscript --vanilla $__tool_directory__/get_data_HPA_v2.R --inputtype copypaste --input '$inputtype.genelist' --header FALSE --proteinatlas $__tool_directory__/proteinatlas.csv --column c1 --select '$options.hpaparams' --output '$output' + Rscript $__tool_directory__/add_expression_HPA.R --inputtype="copypaste" --input='$inputtype.genelist' --atlas="$__tool_directory__/proteinatlas.csv" --select='$options.hpaparams' --output='$output' #else - Rscript --vanilla $__tool_directory__/get_data_HPA_v2.R --inputtype tabfile --input '$inputtype.genelist' --header '$inputtype.header' --proteinatlas $__tool_directory__/proteinatlas.csv --column '$inputtype.column' --select '$options.hpaparams' --output '$output' + Rscript $__tool_directory__/add_expression_HPA.R --inputtype="tabfile" --input='$inputtype.genelist' --header='$inputtype.header' --atlas="$__tool_directory__/proteinatlas.csv" --column='$inputtype.column' --select='$options.hpaparams' --output='$output' #end if @@ -36,23 +36,23 @@ <param name="genelist" type="data" format="txt,tabular" label="Choose your file" help="This file must imperatively have 1 column filled with Ensembl Gene IDs (ENSG). Please use the ID_Converter tool if this is not the case."/> <param name="column" type="text" label="Please specify the column where are your Ensembl gene IDs (e.g : Enter c1 if ENSG ID are in column n°1)" value="c1"/> <param name="header" type="select" label="Does your file have a header?" multiple="false" optional="false"> - <option value="TRUE" selected="true">Yes</option> - <option value="FALSE" selected="false">No</option> + <option value="true" selected="true">Yes</option> + <option value="false" selected="false">No</option> </param> </when> </conditional> <section name="options" title="RNAseq/Ab-based expression data" expanded="True"> <param name="hpaparams" type="select" label="Choose the information from RNAseq/ab-based data you want to add to your list (see below for details)" multiple="True" display="checkboxes"> <option value="Gene" selected="true">Gene name</option> - <option value="Gene.description" selected="false">Gene description</option> + <option value="Gene description" selected="false">Gene description</option> <option value="Evidence">Evidence (at protein level, at transcript level or no evidence)</option> <option value="Antibody">Antibody reference</option> - <option value="RNA.tissue.category">RNA tissue category</option> - <option value="Reliability.IH">IH detection level</option> - <option value="Reliability.IF">IF detection level</option> - <option value="Subcellular.location">Subcellular location</option> - <option value="RNA.TS.TPM">RNA tissue specificity abundance in 'Transcript Per Million'</option> - <option value="TPM.max.in.non.specific">RNA non-specific tissue abundance in 'Transcript Per Million'</option> + <option value="RNA tissue category">RNA tissue category</option> + <option value="Reliability (IH)">IH detection level</option> + <option value="Reliability (IF)">IF detection level</option> + <option value="Subcellular location">Subcellular location</option> + <option value="RNA TS TPM">RNA tissue specificity abundance in 'Transcript Per Million'</option> + <option value="TPM max in non-specific">RNA non-specific tissue abundance in 'Transcript Per Million'</option> </param> </section>
--- a/get_data_HPA_v2.R Wed Mar 14 11:27:05 2018 -0400 +++ b/get_data_HPA_v2.R Mon Mar 19 10:07:38 2018 -0400 @@ -17,6 +17,26 @@ # --output : output file name # Useful functions +# Read file and return file content as data.frame +readfile = function(filename, header) { + if (header == "true") { + # Read only first line of the file as header: + headers <- read.table(filename, nrows = 1, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE, quote = "") + #Read the data of the files (skipping the first row) + file <- read.table(filename, skip = 1, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE, quote = "") + # Remove empty rows + file <- file[!apply(is.na(file) | file == "", 1, all), , drop=FALSE] + #And assign the header to the data + names(file) <- headers + } + else { + file <- read.table(filename, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE, quote = "") + # Remove empty rows + file <- file[!apply(is.na(file) | file == "", 1, all), , drop=FALSE] + } + return(file) +} + '%!in%' <- function(x,y)!('%in%'(x,y)) args = commandArgs(trailingOnly = TRUE) @@ -52,9 +72,9 @@ if (typeinput=="tabfile"){ if (header=="TRUE"){ - listfile = read.table(listfile,header=TRUE,sep="\t",quote="\"",fill=TRUE, na.strings=c("","NA")) + listfile = readfile(listfile, "true") }else{ - listfile = read.table(listfile,header=FALSE,sep="\t",quote="\"",fill=TRUE, na.strings=c("","NA")) + listfile = readfile(listfile, "false") } sample = listfile[,column] @@ -86,7 +106,7 @@ # the file with the fields "Protein not found in proteinatlas" if (length(which(sample %!in% proteinatlas[,3]))!=0){ proteins_not_found = as.data.frame(sample[which(sample %!in% proteinatlas[,3])]) - proteins_not_found = cbind(proteins_not_found,matrix(rep("Protein not found in HPA",length(proteins_not_found)),nrow=length(proteins_not_found),ncol=length(colnames(data))-1)) + proteins_not_found = cbind(proteins_not_found,matrix(rep("Protein not found in HPA",length(proteins_not_found)),nrow=length(proteins_not_found),ncol=length(colnames(data))-1)) colnames(proteins_not_found)=colnames(data)