Filter multi FASTA file using a list of sequence IDs one per line

filter_fasta.py

#!/usr/bin/env python3
"""
Filter sequences from a multifasta file based on an exclusion list.

Usage:
    python filter_fasta.py -i input.fasta -e exclude_ids.txt -o output.fasta

The exclude list should have one sequence ID per line (without the leading '>').
Matching is done against the first word of each FASTA header.
"""

import argparse


def load_exclude_ids(exclude_file):
    """Load sequence IDs to exclude from a text file (one per line)."""
    with open(exclude_file, "r") as f:
        return set(line.strip().lstrip(">").split()[0] for line in f if line.strip())


def filter_fasta(input_file, exclude_ids, output_file):
    """Write sequences to output, skipping those in exclude_ids."""
    excluded = 0
    kept = 0
    skip = False

    with open(input_file, "r") as fin, open(output_file, "w") as fout:
        for line in fin:
            if line.startswith(">"):
                seq_id = line.strip().lstrip(">").split()[0]
                skip = seq_id in exclude_ids
                if skip:
                    excluded += 1
                else:
                    kept += 1
            if not skip:
                fout.write(line)

    print(f"Done! Kept: {kept} sequences | Excluded: {excluded} sequences")
    print(f"Output written to: {output_file}")


def main():
    parser = argparse.ArgumentParser(description="Exclude sequences from a multifasta file.")
    parser.add_argument("-i", "--input",   required=True, help="Input multifasta file")
    parser.add_argument("-e", "--exclude", required=True, help="File with sequence IDs to exclude (one per line)")
    parser.add_argument("-o", "--output",  required=True, help="Output filtered fasta file")
    args = parser.parse_args()

    exclude_ids = load_exclude_ids(args.exclude)
    print(f"Loaded {len(exclude_ids)} IDs to exclude.")
    filter_fasta(args.input, exclude_ids, args.output)


if __name__ == "__main__":
    main()