43 lines
1.3 KiB
Python
43 lines
1.3 KiB
Python
|
# scripts/run_hmm_pipeline.py
|
||
|
|
import argparse
|
||
|
|
from pathlib import Path
|
||
|
|
import sys
|
||
|
|
|
||
|
|
# 把 bba/bba 这一层加入 Python 搜索路径，这样才能 import pipelines.*
|
||
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
|
||
|
|
|
||
|
|
from pipelines.hmm_pipeline import run_hmmsearch_pipeline
|
||
|
|
|
||
|
|
def main():
|
||
|
|
ap = argparse.ArgumentParser()
|
||
|
|
ap.add_argument("--hmm", required=True)
|
||
|
|
ap.add_argument("--pep", required=True)
|
||
|
|
ap.add_argument("--out", required=True)
|
||
|
|
ap.add_argument("--prefix", required=True)
|
||
|
|
ap.add_argument("--cpu", type=int, default=4)
|
||
|
|
ap.add_argument("--no-cut-tc", action="store_true")
|
||
|
|
ap.add_argument("--full-evalue", type=float, default=None)
|
||
|
|
ap.add_argument("--dom-i-evalue", type=float, default=None)
|
||
|
|
args = ap.parse_args()
|
||
|
|
|
||
|
|
out = run_hmmsearch_pipeline(
|
||
|
|
hmm_profile=args.hmm,
|
||
|
|
protein_fasta=args.pep,
|
||
|
|
out_dir=args.out,
|
||
|
|
prefix=args.prefix,
|
||
|
|
cut_tc=not args.no_cut_tc,
|
||
|
|
cpu=args.cpu,
|
||
|
|
full_evalue_max=args.full_evalue,
|
||
|
|
dom_i_evalue_max=args.dom_i_evalue,
|
||
|
|
)
|
||
|
|
|
||
|
|
print("=== DONE ===")
|
||
|
|
print("domtblout:", out.domtblout)
|
||
|
|
print("hmmout:", out.hmmout)
|
||
|
|
print("filter:", out.domtblout_filter)
|
||
|
|
print("id_list:", out.id_list)
|
||
|
|
print(f"hits: {out.hit_count}, unique_ids: {out.unique_id_count}")
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
main()
|