def test_digest():
pytest.importorskip("Bio")
fasta_records = bioframe.load_fasta(testdir + "/test_data/test.fa")
assert len(fasta_records) == 2
### no HindIII sites in the test.fa fasta records, so shouldn't change shape[0]
assert bioframe.digest(fasta_records, "HindIII").shape == (2, 3)
### one DpnII site on chrTEST2, shape[0] should increase by one
assert bioframe.digest(fasta_records, "DpnII").shape == (3, 3)
### DpnII site is on chrTEST2 position 3, first interval of chrTEST2 should end at 3
assert bioframe.digest(fasta_records, "DpnII").iloc[1].end == 3
def digest(chromsizes_path, fasta_path, enzyme_name):
import bioframe
chromsizes = bioframe.read_chromsizes(chromsizes_path, all_names=True)
fasta_records = bioframe.load_fasta(fasta_path,
engine="pyfaidx",
as_raw=True)
if not chromsizes.index.isin(fasta_records).all():
raise ValueError("Some chromosomes mentioned in {}"
" are not found in {}".format(chromsizes_path,
fasta_path))
frags = bioframe.digest(fasta_records, enzyme_name)
print(frags.to_csv(sep="\t", index=False))