Gen SampleSheet for irida

gen_samples.py

#!/usr/bin/env python3
# Author: thanh le viet 12-2019

import pathlib
import click
import re


@click.command()
@click.option('--pid', default='', help='Project ID')
@click.option('--pe/--se', default=True, help='Paired-End reads?')
@click.option('--sort/--no-sort', default=False, help='Sort samples [Experiment]')
@click.option('--path', default='', help='Path to fastq files')
@click.option('--pattern', default='*_R1_001.fastq.gz', help='Path to fastq files')
def gen_sample_list(path, pattern, pid, pe, sort):
    """
    :param sort: Sorting sample in numeric order
    :param path: path to the folder of fastq files
    :param pattern: pattern to scan, by default: *_R1_001.fastq.gz
    :param pid: IRIDA project ID, you need to manually create in IRIDA control management
    :param pe: Are the reads paired-end?
    :return: A csv file SampleList.csv
    """

    regex = re.compile("_S[0-9]{1,3}")
    p = pathlib.Path(path)
    fastqs = p.rglob(pattern)
    fastq_names = [fq.name for fq in fastqs]
    _sorted_fastq_names = fastq_names
    # Sort sample
    if sort:
        _sorted_fastq_names = sorted(
            fastq_names, key=lambda s: int(regex.split(s)[0].split("_")[-1]))
    sample_ids = [regex.split(sp)[0] for sp in _sorted_fastq_names]
    sample_file = p / 'SampleList.csv'
    # print(sorted(fastq_names, key=lambda s: int(regex.split(s)[0].split("_")[-1])))
    with sample_file.open(mode='w') as fh:
        fh.write('[Data]\n')
        fh.write("Sample_Name,Project_ID,File_Forward,File_Reverse\n")
        reverse_reads = ""
        for i in range(0, len(_sorted_fastq_names)):
            if pe:
                reverse_reads = _sorted_fastq_names[i].replace("_R1", "_R2")
            fh.write(
                f"{sample_ids[i]}, {pid}, {_sorted_fastq_names[i]}, {reverse_reads}\n")
    print("Finish!")


if __name__ == '__main__':
    gen_sample_list()