comparison add_expression_HPA.R @ 12:f8d3a8a2f2e5 draft

"planemo upload commit 58e072579a4be282c00b54ebb88fbc59e189a7ed-dirty"
author proteore
date Thu, 23 Jan 2020 10:44:39 +0000
parents 07858c6dbbff
children 8ee4cfdc1a92
comparison
equal deleted inserted replaced
11:4c27466a4e15 12:f8d3a8a2f2e5
1 # Read file and return file content as data.frame 1 # Read file and return file content as data.frame
2 read_file <- function(path,header){ 2 read_file <- function(path,header){
3 file <- read.csv(path,header=header, sep="\t",stringsAsFactors = FALSE, quote="\"", check.names = F) 3 file <- try(read.csv(path,header=header, sep="\t",stringsAsFactors = FALSE, quote="\"", check.names = F),silent=TRUE)
4 return(file) 4 if (inherits(file,"try-error")){
5 stop("File not found !")
6 }else{
7 return(file)
8 }
5 } 9 }
6 10
7 #convert a string to boolean 11 #convert a string to boolean
8 str2bool <- function(x){ 12 str2bool <- function(x){
9 if (any(is.element(c("t","true"),tolower(x)))){ 13 if (any(is.element(c("t","true"),tolower(x)))){
140 cat(paste(sep = "", collapse = " ", c("Column",ncol,"not found in file") )) 144 cat(paste(sep = "", collapse = " ", c("Column",ncol,"not found in file") ))
141 stopQuietly() 145 stopQuietly()
142 } 146 }
143 } 147 }
144 148
149 convert_to_previous_header <- function(options){
150 header = c('Gene','description','Evidence','Antibody','RNA tissue specificity','Reliability (IH)','Reliability (IF)','Subcellular location','RNA tissue specific NX')
151 names(header) = c('Gene','description','Evidence','Antibody','RNA tissue category','Reliability (IH)','Reliability (IF)','Subcellular location','RNA TS TPM')
152 options = names(header[which(header %in% options)])
153 return(options)
154 }
155
145 main = function() { 156 main = function() {
146 157
147 args = get_args() 158 args = get_args()
148 159
149 #save(args,file="/home/dchristiany/proteore_project/ProteoRE/tools/add_expression_data_HPA/args.rda") 160 #save(args,file="/home/dchristiany/proteore_project/ProteoRE/tools/add_expression_data_HPA/args.rda")
174 protein_atlas = read_file(args$atlas, T) 185 protein_atlas = read_file(args$atlas, T)
175 186
176 # Add expression 187 # Add expression
177 output = args$output 188 output = args$output
178 options = strsplit(args$select, ",")[[1]] 189 options = strsplit(args$select, ",")[[1]]
190 if (tail(unlist(strsplit(args$atlas,"/")),1) == "HPA_full_atlas_23-10-2018.tsv"){ options = convert_to_previous_header(options)}
179 res = add_expression(ids, protein_atlas, options) 191 res = add_expression(ids, protein_atlas, options)
180 192
181 # Write output 193 # Write output
182 if (is.null(res)) { 194 if (is.null(res)) {
183 write.table("None of the ENSG ids entered can be found in HPA data file",file=output,sep="\t",quote=FALSE,col.names=TRUE,row.names=FALSE) 195 write.table("None of the ENSG ids entered can be found in HPA data file",file=output,sep="\t",quote=FALSE,col.names=TRUE,row.names=FALSE)