pyhmmer

import pyhmmer from pyhmmer.easel import Alphabet, Sequence from pyhmmer.hmm import HMM from pyhmmer.pipeliner import Pipeline # 1. Define the alphabet for sequences and HMMs alphabet = Alphabet.amino() # 2. Create a simple HMM from a seed sequence (or load from .hmm file) # For a real application, you would typically load an HMM from a file # using `pyhmmer.plan7.HMMFile('your_file.hmm').read_one()` seed_sequence = Sequence(name=b"seed_seq", sequence=b"AGILRVAG") hmm = HMM.from_sequence(seed_sequence, alphabet) hmm.name = b"my_simple_hmm" # 3. Create target sequences to search against target_sequences = [ Sequence(name=b"target1", sequence=b"AGILRVAGGPPPL"), Sequence(name=b"target2", sequence=b"GPPPLGGAGILRV"), Sequence(name=b"target3", sequence=b"XXXXXAGILRVXXXX") # Contains mismatching chars ] # 4. Initialize the HMMER pipeline # The pipeline manages memory and resources for the search process pipeline = Pipeline(alphabet) # 5. Run the search: search the HMM against the target sequences # This method returns a pyhmmer.search.SearchResult object results = pipeline.search_hmm(hmm, target_sequences) # 6. Process and print the results found_hits = False for hit in results.hits: found_hits = True print(f"\n--- Hit Found ---") print(f"Query HMM: {hit.query_name.decode()}") print(f"Target Sequence: {hit.target_name.decode()}") print(f" E-value: {hit.evalue:.2e}, Bit Score: {hit.score:.2f}") for dom in hit.domains: print(f" Domain: Query {dom.query_start}-{dom.query_end} (HMM positions)") print(f" Target {dom.target_start}-{dom.target_end} (Sequence positions)") if not found_hits: print("No significant hits found for the HMM against target sequences.")