comparison id_converter.py @ 18:5252bbcfbdd7 draft

planemo upload commit dc6d9d8f1808c4c6bcc42ac6861a8b811e4cee58-dirty

17:1e45ea50f145

import sys, os, argparse, re, csv

def get_args() :
    parser = argparse.ArgumentParser()
    parser.add_argument("-d", "--ref_file", help="path to reference file: <species>_id_mapping.tsv", required=True)
    parser.add_argument("--input_type", help="type of input (list of id or filename)", required=True)

    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

    
    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 :
                    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,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()

18:5252bbcfbdd7

import sys, os, argparse, re, csv, itertools

def get_args() :
    parser = argparse.ArgumentParser()
    parser.add_argument("-d", "--ref_file", help="path to reference file: <species>_id_mapping.tsv", required=True)
    parser.add_argument("--input_type", help="type of input (list of id or filename)", required=True)

    ids_list= list(set(ids_list))

    return new_file, ids_list

def output_one_id_one_line(line,convert_ids,target_ids):

    ids_not_processed = ["GI","PDB","GO","PIR","MIM","UniGene","BioGrid","STRING"]  #ids with multiple ids per line in output file
    ids_not_processed = [id for id in ids_not_processed if id in target_ids]    #ids present in target_ids with multiple ids per line in output file

    for id_not_processed in ids_not_processed :
        index = target_ids.index(id_not_processed)
        convert_ids[index] = [";".join(convert_ids[index])]

    res = itertools.product(*convert_ids)   #getting all possibilities between lists of ids
    res = [list(e) for e in res]            #convert to lists
    res = [line+list(ids) for ids in res]   #adding the rest of the line

    return(res)
        
#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

    
    result_dict = {}
    for id in ids : 
        for target_id in id_out :
            if id in ids_dictionary :
                res = ids_dictionary[id][target_id]
            else :
                res=""
            
            if id in result_dict :
                result_dict[id].append(res)

                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('')

    print ("dictionary created")

    #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,header)

    print ("starting mapping")

    #Mapping ids
    result_dict = map_to_dictionary(ids,ids_dictionary,args.id_type,target_ids)

    print ("mapping done")

    print ("creating output file")
    #creating output file 
    with open(args.output,"w") as output :
        writer = csv.writer(output,delimiter="\t")
        #writer.writerows(output_file)

        #write header
        if header : 
            writer.writerow(input_file[0]+target_ids)
            input_file = input_file[1:]
        else :
            writer.writerow([args.id_type]+target_ids)

        #write lines 
        if args.input_type=="file" :
            for line in input_file :
                tmp = output_one_id_one_line(line,result_dict[line[args.column_number]],target_ids)
                tmp = blank_to_NA(tmp)
                for row in tmp :
                    writer.writerow(row)
        elif args.input_type=="list" :
            for id in ids :
                tmp = output_one_id_one_line([id],result_dict[id],target_ids)
                tmp = blank_to_NA(tmp)
                for row in tmp :
                    writer.writerow(row)

        print ("output file created")

if __name__ == "__main__":
    main()