def setUp(self):
self.config = build_config(["--cf-create-clusters",
"--cf-mean-threshold", "0.6",
"--cf-min-cds", "5",
"--cf-min-pfams", "5"], modules=[clusterfinder],
isolated=True)
update_config({"enabled_cluster_types": []})
self.record = DummyRecord(seq=Seq("A" * 2000))
for start, end, probability, pfam_id in [(10, 20, 0.1, 'PF77777'),
(30, 40, 0.3, 'PF00106'),
(50, 60, 0.4, 'PF00107'),
(60, 70, 0.7, 'PF00109'),
(70, 80, 0.98, 'PF08484'),
(90, 100, 0.8, 'PF02401'),
(100, 110, 0.32, 'PF04369'),
(110, 120, 1.0, 'PF00128'),
(130, 140, 0.2, 'PF77776'),
(500, 505, None, 'PF77775'),
(1010, 1020, 0.1, 'PF77774'),
(1030, 1040, 0.3, 'PF00106'),
(1050, 1060, 0.4, 'PF00107'),
(1060, 1070, 0.7, 'PF00109'),
(1070, 1080, 0.98, 'PF08484'),
(1090, 1100, 0.8, 'PF02401'),
(1100, 1110, 0.32, 'PF04369'),
(1110, 1120, 1.0, 'PF00128')]:
location = FeatureLocation(start, end, strand=1)
self.record.add_cds_feature(CDSFeature(location, locus_tag=str(start), translation="A"))
pfam = DummyPFAMDomain(location=location, protein_start=start + 1,
protein_end=end-1, identifier=pfam_id)
pfam.domain_id = "pfam_%d" % start
pfam.probability = probability
self.record.add_pfam_domain(pfam)
def test_blank_records(self):
blank_no_pfams = DummyRecord()
blank_no_ids = Record(Seq("ATGTTATGAGGGTCATAACAT", generic_dna))
fake_pfam = DummyPFAMDomain(identifier="PF00000")
blank_no_ids.add_pfam_domain(fake_pfam)
assert not pfam2go.get_gos_for_pfams(blank_no_pfams)
assert not pfam2go.get_gos_for_pfams(blank_no_ids)
def setUp(self):
self.record = secmet.Record()
# except for Thioesterase, all domains were found in BN001301.1
# TE domains were found in Y16952
for filename, domain_type in [("PKS_KS.input", "PKS_KS"), ("AT.input", "PKS_AT"),
("ACP.input", "ACP"), ("DH.input", "PKS_DH"),
("KR.input", "PKS_KR"), ("TE.input", "Thioesterase"),
("ER.input", "PKS_ER")]:
for domain in rebuild_domains(filename, domain_type):
self.record.add_antismash_domain(domain)
# these PFAMs found in BN001301.1 with clusterhmmer, one was excluded
# to avoid a Biopython SearchIO bug
domain_fasta = fasta.read_fasta(path.get_full_path(__file__, 'data', "p450.input"))
for name, translation in domain_fasta.items():
pfam_domain = DummyPFAMDomain(domain="p450", domain_id="PFAM_p450_" + name)
pfam_domain.translation = translation
self.record.add_pfam_domain(pfam_domain)
def test_domains_of_interest(self):
domain = DummyPFAMDomain(domain="p450")
analysis = ActiveSiteAnalysis("not-p450", (domain, ), "PKSI-KR.hmm2",
[5, 6], ["C", "S"])
assert analysis.domains_of_interest == []
analysis = ActiveSiteAnalysis("p450", (domain, ), "PKSI-KR.hmm2",
[5, 6], ["C", "S"])
assert analysis.domains_of_interest == [domain]
def set_dummy_with_pfams(pfam_ids: Dict[str, FeatureLocation]) -> DummyRecord:
pfam_domains = []
for pfam_id, pfam_location in pfam_ids.items():
domain_id = '%s.%d.%d' % (pfam_id, pfam_location.start,
pfam_location.end)
pfam_domain = DummyPFAMDomain(location=pfam_location,
protein_start=0,
protein_end=5,
identifier=pfam_id,
domain_id=domain_id)
pfam_domains.append(pfam_domain)
return DummyRecord(features=pfam_domains)
def test_add_results_to_record(self):
pfams = {
'PF00015.2': FeatureLocation(0, 3),
'PF00351.1': FeatureLocation(0, 3),
'PF00015.27': FeatureLocation(3, 6)
}
fake_record = set_dummy_with_pfams(pfams)
fake_duplicate_pfam = DummyPFAMDomain(identifier="PF00015.2")
fake_record.add_pfam_domain(fake_duplicate_pfam)
assert fake_duplicate_pfam in fake_record.get_pfam_domains()
gos_for_fake_pfam = pfam2go.get_gos_for_pfams(fake_record)
fake_results = pfam2go.Pfam2GoResults(fake_record.id,
gos_for_fake_pfam)
fake_results.add_to_record(fake_record)
assert fake_duplicate_pfam.full_identifier == 'PF00015.2'
for pfam in fake_record.get_pfam_domains():
assert sorted(pfam.gene_ontologies.ids) == sorted(
fake_results.get_all_gos(pfam))
# make sure identical pfams (with different version numbers) all have the same gene ontologies
if pfam.identifier == "PF00015":
assert pfam.version in [2, 27]
assert sorted(pfam.gene_ontologies.ids) == sorted(
fake_results.get_all_gos(fake_duplicate_pfam))
def setUp(self):
self.domain = DummyPFAMDomain(domain="p450")
self.alignment = Alignment(self.domain, "WLAD-QGAR", "WLaer.rGA", 10,
19)