Created
January 8, 2019 21:57
-
-
Save wdecoster/bcebd528dea8fbebb435594c85a05b3d to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from argparse import ArgumentParser | |
from Bio import SeqIO | |
from collections import Counter, defaultdict | |
import gzip | |
def main(): | |
args = get_args() | |
primers = defaultdict(int) | |
for pattern in args.pattern: | |
for read in SeqIO.parse(gzip.open(args.fastq, 'rt'), "fastq"): | |
primer = get_pattern(str(read.seq), pattern, length=22) | |
if primer: | |
primers[primer] += 1 | |
for sequence, number in Counter(primers).most_common(n=20): | |
print("{}\t{}x".format(sequence, number)) | |
def get_pattern(seq, pattern, length): | |
if pattern in seq: | |
pos = seq.index(pattern) | |
return seq[pos - (length - len(pattern)): pos + len(pattern)] | |
def get_args(): | |
parser = ArgumentParser(description="Get primers based on a fastq www.biostars.org/p/356286") | |
parser.add_argument("--pattern", help="pattern(s) to search for", nargs="*", required=True) | |
parser.add_argument("--fastq", help="gzip compressed fastq file", required=True) | |
return parser.parse_args() | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment