# HG changeset patch # User proteore # Date 1548691727 18000 # Node ID b6607b7e683f7fecc298fdb52e00363d3160c317 # Parent b50d913ec067ea36f1ca4c1073020122f35d0fae planemo upload commit f2b3d1ff6bea930b2ce32c009e4d3de39a17edfb-dirty diff -r b50d913ec067 -r b6607b7e683f id_converter.R --- a/id_converter.R Tue Dec 18 09:57:21 2018 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,185 +0,0 @@ -# Read file and return file content as data.frame -read_file <- function(path,header){ - file <- try(read.csv(path,header=header, sep="\t",stringsAsFactors = FALSE, quote="\"",check.names = F),silent=TRUE) - if (inherits(file,"try-error")){ - stop("File not found !") - }else{ - return(file) - } -} - -str2bool <- function(x){ - if (any(is.element(c("t","true"),tolower(x)))){ - return (TRUE) - }else if (any(is.element(c("f","false"),tolower(x)))){ - return (FALSE) - }else{ - return(NULL) - } -} - -mapping_ids <- function(list_id,input_id_type,ref_file,options){ - list_id = list_id[!is.na(list_id)] - if (!any(grep(";",ref_file[input_id_type]))) { - res <- ref_file[match(list_id,ref_file[input_id_type][,]),c(input_id_type,options)] - res=as.data.frame(res) - res=res[which(!is.na(res[,1])),] - row.names(res)=res[,1] - res=res[2:ncol(res)] - } else { - if (length(options) > 1) { - res <- data.frame(t(sapply(list_id, function(x) apply(ref_file[grep(x,ref_file[input_id_type][,]),options],2,function(y) paste(y[y!=""],sep="",collapse=";")) ))) - } else if (length(options)==1){ - res <- data.frame(sapply(list_id, function(x) gsub(";+$","",paste(ref_file[grep(x,ref_file[input_id_type][,]),options],sep="",collapse=";")))) - colnames(res)=options - } - } - - return (res) -} - -get_list_from_cp <-function(list){ - list = strsplit(list, "[ \t\n]+")[[1]] - list = list[list != ""] #remove empty entry - list = gsub("-.+", "", list) #Remove isoform accession number (e.g. "-2") - return(list) -} - -order_columns <- function (df,ncol){ - if (ncol==1){ #already at the right position - return (df) - } else { - df = df[,c(2:ncol,1,(ncol+1):dim.data.frame(df)[2])] - } - return (df) -} - -#take data frame, return data frame -split_ids_per_line <- function(line,ncol){ - - #print (line) - header = colnames(line) - line[ncol] = gsub("[[:blank:]]|\u00A0","",line[ncol]) - - if (length(unlist(strsplit(as.character(line[ncol]),";")))>1) { - if (length(line)==1 ) { - lines = as.data.frame(unlist(strsplit(as.character(line[ncol]),";")),stringsAsFactors = F) - } else { - if (ncol==1) { #first column - lines = suppressWarnings(cbind(unlist(strsplit(as.character(line[ncol]),";")), line[2:length(line)])) - } else if (ncol==length(line)) { #last column - lines = suppressWarnings(cbind(line[1:ncol-1],unlist(strsplit(as.character(line[ncol]),";")))) - } else { - lines = suppressWarnings(cbind(line[1:ncol-1], unlist(strsplit(as.character(line[ncol]),";"),use.names = F), line[(ncol+1):length(line)])) - } - } - colnames(lines)=header - return(lines) - } else { - return(line) - } -} - -#create new lines if there's more than one id per cell in the columns in order to have only one id per line -one_id_one_line <-function(tab,ncol){ - - if (ncol(tab)>1){ - - tab[,ncol] = sapply(tab[,ncol],function(x) gsub("[[:blank:]]","",x)) - header=colnames(tab) - res=as.data.frame(matrix(ncol=ncol(tab),nrow=0)) - for (i in 1:nrow(tab) ) { - lines = split_ids_per_line(tab[i,],ncol) - res = rbind(res,lines) - } - }else { - res = unlist(sapply(tab[,1],function(x) strsplit(x,";")),use.names = F) - res = data.frame(res[which(!is.na(res[res!=""]))],stringsAsFactors = F) - colnames(res)=colnames(tab) - } - return(res) -} - -get_args <- function(){ - args <- commandArgs(TRUE) - if(length(args)<1) { - args <- c("--help") - } - - # Help section - if("--help" %in% args) { - cat("Selection and Annotation HPA - Arguments: - --ref_file: path to reference file (id_mapping_file.txt) - --input_type: type of input (list of id or filename) - --id_type: type of input IDs - --input: list of IDs (text or filename) - --column_number: the column number which contains list of input IDs - --header: true/false if your file contains a header - --target_ids: target IDs to map to - --output: output filename \n") - q(save="no") - } - - # Parse arguments - parseArgs <- function(x) strsplit(sub("^--", "", x), "=") - argsDF <- as.data.frame(do.call("rbind", parseArgs(args))) - args <- as.list(as.character(argsDF$V2)) - names(args) <- argsDF$V1 - - return(args) -} - -mapping = function() { - - args <- get_args() - - #save(args,file="/home/dchristiany/proteore_project/ProteoRE/tools/id_converter/args.rda") - #load("/home/dchristiany/proteore_project/ProteoRE/tools/id_converter/args.rda") - - input_id_type = args$id_type # Uniprot, ENSG.... - list_id_input_type = args$input_type # list or file - options = strsplit(args$target_ids, ",")[[1]] - output = args$output - id_mapping_file = args$ref_file - - # Extract input IDs - if (list_id_input_type == "list") { - list_id = get_list_from_cp(args$input) - } else if (list_id_input_type == "file") { - filename = args$input - column_number = as.numeric(gsub("c", "" ,args$column_number)) - header = str2bool(args$header) - file_all = read_file(filename, header) - file_all = one_id_one_line(file_all,column_number) - list_id = trimws(gsub("[$,\xc2\xa0]","",sapply(strsplit(as.character(file_all[,column_number]), ";"), "[", 1))) - # Remove isoform accession number (e.g. "-2") - list_id = unique(gsub("-.+", "", list_id)) - } - - # Extract ID maps - id_map = read_file(id_mapping_file, T) - - # Map IDs - res <- mapping_ids(list_id,input_id_type,id_map,options) - - #merge data frames - if (list_id_input_type == "list"){ - list_id <- data.frame(list_id) - output_content = merge(list_id,res,by.x=1,by.y="row.names",incomparables = NA, all.x=T) - colnames(output_content)[1]=input_id_type - } else if (list_id_input_type == "file") { - output_content = merge(file_all,res,by.x=column_number,by.y="row.names",incomparables = NA, all.x=T) - output_content = order_columns(output_content,column_number) - } - - #write output - header=colnames(output_content) - output_content <- as.data.frame(apply(output_content, c(1,2), function(x) gsub("^$|^ $", NA, x))) - colnames(output_content)=header - write.table(output_content, output, row.names = FALSE, sep = '\t', quote = FALSE) -} - -mapping() - -#Rscript id_converter_UniProt.R "UniProt.AC" "test-data/UnipIDs.txt,c1,false" "file" "Ensembl_PRO,Ensembl,neXtProt_ID" "test-data/output.txt" ../../utils/mapping_file.txt diff -r b50d913ec067 -r b6607b7e683f id_converter.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/id_converter.py Mon Jan 28 11:08:47 2019 -0500 @@ -0,0 +1,183 @@ +import sys, os, argparse, re, csv + +def get_args() : + parser = argparse.ArgumentParser() + parser.add_argument("-d", "--ref_file", help="path to reference file: _id_mapping.tsv", required=True) + parser.add_argument("--input_type", help="type of input (list of id or filename)", required=True) + parser.add_argument("-t", "--id_type", help="type of input IDs", required=True) + parser.add_argument("-i", "--input", help="list of IDs (text or filename)", required=True) + parser.add_argument("-c", "--column_number", help="list of IDs (text or filename)") + parser.add_argument("--header", help="true/false if your file contains a header") + parser.add_argument("--target_ids", help="target IDs to map to", required=True) + parser.add_argument("-o", "--output", help="output filename", required=True) + args = parser.parse_args() + return args + +#return list of (unique) ids from string +def get_input_ids_from_string(input) : + ids_list = list(set(re.split(r'\s+',input.replace("\r","").replace("\n"," ").replace("\t"," ")))) + if "" in ids_list : ids_list.remove("") + #if "NA" in ids_list : ids_list.remove("NA") + return ids_list + +#return input_file and list of unique ids from input file path +def get_input_ids_from_file(input,nb_col,header) : + with open(input, "r") as csv_file : + input_file= list(csv.reader(csv_file, delimiter='\t')) + + input_file, ids_list = one_id_one_line(input_file,nb_col,header) + if "" in ids_list : ids_list.remove("") + #if "NA" in ids_list : ids_list.remove("NA") + + return input_file, ids_list + +#return input file by adding lines when there are more than one id per line +def one_id_one_line(input_file,nb_col,header) : + + if header : + new_file = [input_file[0]] + input_file = input_file[1:] + else : + new_file=[] + ids_list=[] + + for line in input_file : + if line != [] and set(line) != {''}: + line[nb_col] = re.sub(r"\s+","",line[nb_col]) + if ";" in line[nb_col] : + ids = line[nb_col].split(";") + for id in ids : + new_file.append(line[:nb_col]+[id]+line[nb_col+1:]) + ids_list.append(id) + else : + new_file.append(line) + ids_list.append(line[nb_col]) + + ids_list= list(set(ids_list)) + + return new_file, ids_list + +#return the column number in int format +def nb_col_to_int(nb_col): + try : + nb_col = int(nb_col.replace("c", "")) - 1 + return nb_col + except : + sys.exit("Please specify the column where you would like to apply the filter with valid format") + +#replace all blank cells to NA +def blank_to_NA(csv_file) : + tmp=[] + for line in csv_file : + line = ["NA" if cell=="" or cell==" " or cell=="NaN" else cell for cell in line] + tmp.append(line) + + return tmp + +def str2bool(v): + if v.lower() in ('yes', 'true', 't', 'y', '1'): + return True + elif v.lower() in ('no', 'false', 'f', 'n', '0'): + return False + else: + raise argparse.ArgumentTypeError('Boolean value expected.') + +#return result dictionary +def map_to_dictionary(ids,ids_dictionary,id_in,id_out) : + + result_dict = {} + for id in ids : + for target_id in id_out : + if id in ids_dictionary : + res = ";".join(ids_dictionary[id][target_id]) + else : + res="" + + if id in result_dict : + result_dict[id].append(res) + else : + result_dict[id]=[res] + + return result_dict + +#create empty dictionary with index for tab +def create_ids_dictionary (ids_list) : + ids_dictionary = {} + ids_dictionary_index={} + for i,id in enumerate(ids_list) : + ids_dictionary_index[i]=id + + return(ids_dictionary,ids_dictionary_index) + +def main(): + + #Get args from command line + args = get_args() + target_ids = args.target_ids.split(",") + header=False + if args.id_type in target_ids : target_ids.remove(args.id_type) + if args.input_type=="file" : + args.column_number = nb_col_to_int(args.column_number) + header = str2bool(args.header) + + #Get ref file to build dictionary + csv.field_size_limit(sys.maxsize) # to handle big files + with open(args.ref_file, "r") as csv_file : + tab = csv.reader(csv_file, delimiter='\t') + tab = [line for line in tab] + + ids_list=tab[0] + + #create empty dictionary and dictionary index + ids_dictionary, ids_dictionary_index = create_ids_dictionary(ids_list) + + #fill dictionary and sub dictionaries with ids + id_index = ids_list.index(args.id_type) + for line in tab[1:] : + ref_ids=line[id_index] + other_id_type_index = [accession_id for accession_id in ids_dictionary_index.keys() if accession_id!=id_index] + for id in ref_ids.replace(" ","").split(";") : #if there's more than one id, one key per id (example : GO) + if id not in ids_dictionary : #if the key is not created yet + ids_dictionary[id]={} + for other_id_type in other_id_type_index : + if ids_dictionary_index[other_id_type] not in ids_dictionary[id] : + ids_dictionary[id][ids_dictionary_index[other_id_type]] = set(line[other_id_type].replace(" ","").split(";")) + else : + ids_dictionary[id][ids_dictionary_index[other_id_type]] |= set(line[other_id_type].replace(" ","").split(";")) + if len(ids_dictionary[id][ids_dictionary_index[other_id_type]]) > 1 and '' in ids_dictionary[id][ids_dictionary_index[other_id_type]] : + ids_dictionary[id][ids_dictionary_index[other_id_type]].remove('') + + #Get file and/or ids from input + if args.input_type == "list" : + ids = get_input_ids_from_string(args.input) + elif args.input_type == "file" : + input_file, ids = get_input_ids_from_file(args.input,args.column_number,args.header) + + #Mapping ids + result_dict = map_to_dictionary(ids,ids_dictionary,args.id_type,target_ids) + + #creating output file + if header : + output_file=[input_file[0]+target_ids] + input_file = input_file[1:] + else : + output_file=[[args.id_type]+target_ids] + + if args.input_type=="file" : + for line in input_file : + output_file.append(line+result_dict[line[args.column_number]]) + elif args.input_type=="list" : + for id in ids : + output_file.append([id]+result_dict[id]) + + #convert blank to NA + output_file = blank_to_NA(output_file) + + #write output file + with open(args.output,"w") as output : + writer = csv.writer(output,delimiter="\t") + writer.writerows(output_file) + +if __name__ == "__main__": + main() + diff -r b50d913ec067 -r b6607b7e683f id_converter.xml --- a/id_converter.xml Tue Dec 18 09:57:21 2018 -0500 +++ b/id_converter.xml Mon Jan 28 11:08:47 2019 -0500 @@ -1,14 +1,13 @@ - + (Human, Mouse, Rat) - R - - $__tool_directory__/id_converter.R + + ]]> @@ -55,11 +54,11 @@ - - - + + + - + @@ -101,7 +100,7 @@ - + @@ -140,7 +139,7 @@ - + diff -r b50d913ec067 -r b6607b7e683f tool-data/proteore_id_mapping.loc.sample --- a/tool-data/proteore_id_mapping.loc.sample Tue Dec 18 09:57:21 2018 -0500 +++ b/tool-data/proteore_id_mapping.loc.sample Mon Jan 28 11:08:47 2019 -0500 @@ -1,4 +1,5 @@ #This file lists the locations of reference file for id_converter tool -human_id_mapping Human (Homo sapiens) tool-data/human_id_mapping_23-10-2018.tsv -mouse_id_mapping Mouse (Mus musculus) tool-data/mouse_id_mapping_23-10-2018.tsv -rat_id_mapping Rat (Rattus norvegicus) tool-data/rat_id_mapping_23-10-2018.tsv +# +human_id_mapping_23-10-2018 Human (homo sapiens) Human tool-data/human_id_mapping_23-10-2018.tsv +mouse_id_mapping_23-10-2018 Mouse (Mus musculus) Mouse tool-data/mouse_id_mapping_23-10-2018.tsv +rat_id_mapping_23-10-2018 Rat (Rattus norvegicus) Rat tool-data/rat_id_mapping_23-10-2018.tsv diff -r b50d913ec067 -r b6607b7e683f tool_data_table_conf.xml.sample --- a/tool_data_table_conf.xml.sample Tue Dec 18 09:57:21 2018 -0500 +++ b/tool_data_table_conf.xml.sample Mon Jan 28 11:08:47 2019 -0500 @@ -1,7 +1,7 @@ - value, name, path + id, name, value, path
\ No newline at end of file