Mercurial > repos > estrain > microrunqc

comparison run_fastq_scan.py @ 0:4e629e82c5b1 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit a820b38dea9a409c11e220ba904da232fdbc4c05
author estrain
date Fri, 13 Mar 2026 12:51:10 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:4e629e82c5b1
1 #!/usr/bin/env
2
3 ## Run fastq-scan to get mean read length and mean quality score
4 ## author: errol strain, estrain@gmail.com
5
6 from argparse import (ArgumentParser, FileType)
7 import sys
8 import glob
9 import subprocess
10 import json
11
12 def parse_args():
13 "Parse the input arguments, use '-h' for help."
14
15 parser = ArgumentParser(description='Run fastq-scan on a pair of gzipped FASTQ files')
16
17 # Read inputs
18 parser.add_argument('--fastq', type=str, required=True, nargs=2, help='FASTQ files')
19 parser.add_argument('--output', type=str, required=True, nargs=1, help='Output File')
20 parser.add_argument('--type', type=str, required=True, nargs=1, help='File Type (text or gz)')
21
22 return parser.parse_args()
23
24 args =parse_args()
25
26 # FASTA file
27 r1 = args.fastq[0]
28 r2 = args.fastq[1]
29
30 # Read 1
31 if str(args.type[0]) == "gz" :
32 cmd1 = ["zcat", r1]
33 else :
34 cmd1 = ["cat", r1]
35 cmd2 = ["fastq-scan"]
36 pcmd1= subprocess.Popen(cmd1,stdout= subprocess.PIPE,shell=False)
37 r1json = json.loads(subprocess.Popen(cmd2, stdin=pcmd1.stdout,stdout=subprocess.PIPE,shell=False).communicate()[0])
38 r1q = round(r1json["qc_stats"]["qual_mean"],1)
39 r1l = round(r1json["qc_stats"]["read_mean"],1)
40
41 # Read 2
42 if str(args.type[0]) == "gz" :
43 cmd1 = ["zcat", r2]
44 else :
45 cmd1 = ["cat", r2]
46 cmd2 = ["fastq-scan"]
47 pcmd1= subprocess.Popen(cmd1,stdout= subprocess.PIPE,shell=False)
48 r2json = json.loads(subprocess.Popen(cmd2, stdin=pcmd1.stdout,stdout=subprocess.PIPE,shell=False).communicate()[0])
49 r2q = round(r2json["qc_stats"]["qual_mean"],1)
50 r2l = round(r2json["qc_stats"]["read_mean"],1)
51
52 # Write output to be used by sum_mlst.py
53 output = open(args.output[0],"w")
54 output.write(str(r1l) + "\t" + str(r2l) + "\t" + str(r1q) + "\t" + str(r2q))