comparison id_converter.py @ 19:9d758344d36e draft

planemo upload commit 339ab77a83db03409c8001324f10b36ff5b13a39-dirty

18:5252bbcfbdd7

    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])]

    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(",")

        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('')

    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()

19:9d758344d36e

    ids_list= list(set(ids_list))

    return new_file, ids_list

#not used
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 = ["UniProt-AC","UniProt-AC_reviewed","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","BioGrid","STRING","KEGG"] # All Ids
    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])]

    for i,id in enumerate(ids_list) :
        ids_dictionary_index[i]=id
            
    return(ids_dictionary,ids_dictionary_index)

def create_header(input_file,ncol,id_type,target_ids):
    col_names = list(range(1,len(input_file[0])+1))
    col_names = ["col"+str(e) for e in col_names]
    col_names[ncol]=id_type
    col_names = col_names+target_ids
    return(col_names)

def main():
    
    #Get args from command line
    args = get_args()
    target_ids = args.target_ids.split(",")

        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("NA","").replace(" ","").split(";"))
                else :
                    ids_dictionary[id][ids_dictionary_index[other_id_type]] |= set(line[other_id_type].replace("NA","").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:]  
        elif args.input_type=="file":
            col_names = create_header(input_file,args.column_number,args.id_type,target_ids)
            writer.writerow(col_names)
        else : 
            writer.writerow([args.id_type]+target_ids)

        #write lines 
        previous_line=""
        if args.input_type=="file" :
            for line in input_file :
                res = [";".join(list(res_ids)) for res_ids in result_dict[line[args.column_number]]]
                line = ["NA" if cell=="" or cell==" " or cell=="NaN" else cell for cell in line+res]
                if previous_line != line :
                    writer.writerow(line)
                    previous_line=line
        elif args.input_type=="list" :
            for id in ids :
                res = [";".join(list(res_ids)) for res_ids in result_dict[id]]
                line = ["NA" if cell=="" or cell==" " or cell=="NaN" else cell for cell in [id]+res]
                if previous_line != line :
                    writer.writerow(line)
                    previous_line=line

        #print ("output file created")

if __name__ == "__main__":
    main()