Script to organize FASTQs in directories and construct a CSV file input on QIAGEN site taking as argument the bioinfo worklist

fastq_to_file.py

import os
import sys
import pandas as pd

#Get the worklist as a parameter
worklist_bioinfo = sys.argv[1]

#Create DataFrame from worklist
header = ['pool', 'analysis_type', 'exame', 'control', 'gender']
worklist_df = pd.read_csv(worklist_bioinfo, header=None, names=header)
worklist_df.set_index(['pool'], inplace=True)
worklist_df['sample name'] = worklist_df.index
worklist_df['read file 1'] = 0
worklist_df['read file 2'] = 0
worklist_df['gender'] = worklist_df['gender'].replace({
'F':'Female', 'M':'Male', '-':'None'})

#Iterate trough folder and find fastqs
for root, dirs, files in os.walk("."):

    for file in files:

        if file.endswith("fastq.gz"):

            file_name = file.split(".")[0]
            pool_name  = file.split("_")[0]

            if "R1" in file_name:
                worklist_df.ix[pool_name, 'read file 1'] = file
            else:
                worklist_df.ix[pool_name, 'read file 2'] = file


worklist_df = worklist_df[(worklist_df['read file 1']!=0) & (worklist_df['read file 2']!=0)].fillna("None")
exames  = worklist_df['exame'].unique()

for exame in exames:

    df_to_write = worklist_df[worklist_df['exame'] == exame]

    #Create folder with exam name
    if not os.path.exists(os.path.dirname(
    os.path.realpath(__file__)) + "/" + exame):
        os.makedirs(exame)

    #Move all FASTQ files to exam folder
    for index, row in df_to_write.iterrows():
        os.rename(row['read file 1'], '%s/%s' % (exame, row['read file 1']))
        os.rename(row['read file 2'], '%s/%s' % (exame, row['read file 2']))

    #Create txt file inside exam folder
    df_to_write = df_to_write[['read file 1', 'read file 2', 'sample name', 'gender']]
    df_to_write.to_csv('%s/qiagen-%s.txt' % (exame,exame), index=None, sep='\t')