def test_get_multifasta(self):
"Test utils.get_multifasta"
expected = """>orf0001
FAKESEQ
>orf0003
FAKESEQ
>orf0006
FAKESEQ"""
ret = utils.get_multifasta(self.rec)
self.assertMultiLineEqual(expected, ret)
def run(seq_record, options):
"run hmmsearch against PFAM for all CDS features"
if 'pfamdir' not in options:
options.pfamdir = utils.get_full_path(__file__, '')
query_sequence = utils.get_multifasta(seq_record)
target_hmmfile = path.join(options.pfamdir, 'Pfam-A.hmm')
logging.info('Running whole-genome pfam search')
results = utils.run_hmmscan(target_hmmfile, query_sequence)
_annotate(seq_record, options, results)
def run(seq_record, options):
"run hmmsearch against PFAM for all CDS features"
if 'pfamdir' not in options:
options.pfamdir = utils.get_full_path(__file__, '')
query_sequence = utils.get_multifasta(seq_record)
target_hmmfile = path.join(options.pfamdir, 'Pfam-A.hmm')
logging.info('Running whole-genome pfam search')
if options.skip_cleanup:
results_file = path.join(options.full_outputfolder_path, 'fullhmmer.txt')
if path.exists(results_file):
results = list(SearchIO.parse(results_file, 'hmmer3-text'))
else:
results = utils.run_hmmscan(target_hmmfile, query_sequence, results_file=results_file)
else:
results = utils.run_hmmscan(target_hmmfile, query_sequence)
_annotate(seq_record, options, results)
def detect_signature_genes(seq_record, enabled_clustertypes, options):
"Function to be executed by module"
feature_by_id = utils.get_feature_dict(seq_record)
full_fasta = utils.get_multifasta(seq_record)
rulesdict = create_rules_dict(enabled_clustertypes)
results = []
sig_by_name = {}
results_by_id = {}
for sig in _signature_profiles:
sig_by_name[sig.name] = sig
runresults = utils.run_hmmsearch(utils.get_full_path(
__file__, 'bgc_seeds.hmm'),
full_fasta,
use_tempfile=True)
for runresult in runresults:
acc = runresult.accession.split('.')[0]
# Store result if it is above cut-off
for hsp in runresult.hsps:
if hsp.query_id in sig_by_name:
sig = sig_by_name[hsp.query_id]
elif acc in sig_by_name:
sig = sig_by_name[acc]
else:
logging.error(
'BUG: Failed to find signature for ID %s / ACC %s',
hsp.query_id, acc)
continue
if hsp.bitscore > sig.cutoff:
results.append(hsp)
if hsp.hit_id not in results_by_id:
results_by_id[hsp.hit_id] = [hsp]
else:
results_by_id[hsp.hit_id].append(hsp)
#Get overlap tables (for overlap filtering etc)
overlaps = utils.get_overlaps_table(seq_record)
#Filter results by comparing scores of different models (for PKS systems)
results, results_by_id = filter_results(results, results_by_id)
# Filter results of overlapping genes (only for plants)
if options.taxon == 'plants':
results, results_by_id = filter_result_overlapping_genes(
results, results_by_id, overlaps, feature_by_id)
#Filter multiple results of the same model in one gene
results, results_by_id = filter_result_multiple(results, results_by_id)
#Use rules to determine gene clusters
typedict = apply_cluster_rules(results_by_id, feature_by_id,
enabled_clustertypes, rulesdict, overlaps)
#Find number of sequences on which each pHMM is based
nseqdict = get_nseq()
#Save final results to seq_record
for cds in results_by_id.keys():
feature = feature_by_id[cds]
_update_sec_met_entry(feature, results_by_id[cds], typedict[cds],
nseqdict)
find_clusters(seq_record, rulesdict)
#Find additional NRPS/PKS genes in gene clusters
add_additional_nrpspks_genes(typedict, results_by_id, seq_record, nseqdict)
#Add details of gene cluster detection to cluster features
store_detection_details(results_by_id, rulesdict, seq_record)
#If all-orfs option on, remove irrelevant short orfs
if options.all_orfs:
remove_irrelevant_allorfs(seq_record)