def test_parse_file_gff(tmp_path):
"""GFF files are handled correctly with/without FASTA files"""
gff = tmp_path / "test.gff"
gff.write_text("content")
with pytest.raises(FileNotFoundError):
gp.parse_file(gff)
(tmp_path / "test.fasta").write_text("content")
assert gp.parse_file(gff) == dict(name="test", records=[])
def get_sequences(query_file=None, query_ids=None, query_profiles=None):
"""Convenience function to get dictionary of query sequences from file or IDs.
Parameters:
query_file (str): Path to FASTA genbank or EMBL file containing query
protein sequences.
query_ids (list): NCBI sequence accessions.
query_profiles (list): Pfam profile accessions.
Raises:
ValueError: Did not receive values for query_file or query_ids.
Returns:
sequences (dict): Dictionary of query sequences keyed on accession.
"""
if query_file and not query_ids:
organism = gp.parse_file(query_file)
if Path(query_file).suffix.lower() in gp.FASTA_SUFFIXES:
sequences = OrderedDict(
(r.id, str(r.seq)) for r in organism["records"])
else:
genes = gp.organisms_to_tuples([organism])
sequences = OrderedDict((gene[0], gene[4]) for gene in genes)
elif query_ids:
sequences = efetch_sequences(query_ids)
elif query_profiles:
sequences = None
else:
raise ValueError(
"Expected 'query_file' or 'query_ids', or 'query_profiles'")
return sequences
def test_parse_file_valid(tmp_path):
"""Files with valid extensions parsed correctly"""
paths = [
tmp_path / "test.gbk",
tmp_path / "test.fasta",
tmp_path / "test.embl"
]
for path in paths:
path.write_text("content")
assert gp.parse_file(path) == dict(name="test", records=[])
def parse_query_sequences(query_file=None, query_ids=None, query_profiles=None):
"""Creates a Cluster object from query sequences.
If EMBL/GenBank, Cluster will use exact genomic coordinates parsed from file.
Otherwise, a fake Cluster will be created where genes are drawn to scale,
but always on positive strand and with fixed intergenic distance.
"""
if query_file:
organism = gp.parse_file(query_file)
if Path(query_file).suffix.lower() in gp.FASTA_SUFFIXES:
cluster = fasta_seqrecords_to_cluster(organism["records"])
else:
cluster = seqrecord_to_cluster(organism["records"][0])
elif query_ids:
sequences = efetch_sequences(query_ids)
cluster = dict_to_cluster(sequences)
elif query_profiles:
cluster = dict_to_cluster({key: None for key in query_profiles})
else:
raise ValueError("Expected 'query_file', 'query_ids' or 'query_profiles'")
return cluster
def test_parse_file_invalid_ext(tmp_path):
"""parse_file throws ValueError on invalid extensions"""
invalid = tmp_path / "test.invalid"
invalid.write_text("content")
with pytest.raises(ValueError):
gp.parse_file(invalid)