Download sequenncing file meta data using `ffq`

download _json_ffq.py

# Download meta data using ffq.
# Need input `SraRunTable.txt`

# Author: Ji Huang
# Date: 2022-09-21

import pandas as pd
import subprocess
import os

# Define output folder.
output_folder = "../data/json/"

try:
    os.makedirs(output_folder)
except OSError as e:
    print(e)

# Read in SRA table to be processed.
sra_table = pd.read_table('SraRunTable.txt',delimiter=',')

srr_number = list(sra_table["Run"])

# Check if there are repeated SRR number.
if len(srr_number)==len(set(srr_number)):
    print("There are no redundant SRR numbers.")
    print("There are " + str(len(srr_number)), "unique SRR numbers.")

else:
    print("There are redundant SRR numbers.")
    print("There are ", len(set(srr_number)), "unique SRR numbers.")
    srr_number = set(srr_number)

# Use a loop to download meta data.
for i in srr_number:
    output_json = os.path.join(output_folder, i+".json")

    ffq_command = "ffq --ftp -o " + output_json + " " + i

    subprocess.run(ffq_command, shell = True)
    print(i + " is done!")