def test_get_structure_pred(self):
"Test utils.get_structure_pred()"
cluster = FakeFeature('cluster', FeatureLocation(23, 42),
{'product': ['fake']})
self.assertEqual('N/A', utils.get_structure_pred(cluster))
cluster.qualifiers['product'][0] = 'ectoine'
self.assertEqual('ectoine', utils.get_structure_pred(cluster))
cluster.qualifiers['note'] = ['Monomers prediction: fake']
self.assertEqual('fake', utils.get_structure_pred(cluster))
def generate_structure_images(seq_records, options):
"Generate the structure images based on Monomers prediction in cluster feature"
for seq_record in seq_records:
# Ugly temporary solution:
# At first we have to regenerate the relevant information for the pksnrpsvars dictionary from the seq_record file
pksnrpsvars = utils.Storage()
pksnrpsvars.compound_pred_dict = {}
pksnrpsvars.failedstructures = []
geneclusters = utils.get_cluster_features(seq_record)
for genecluster in geneclusters:
geneclusternr = utils.get_cluster_number(genecluster)
pksnrpsvars.compound_pred_dict[geneclusternr] = utils.get_structure_pred(genecluster)
if len(pksnrpsvars.compound_pred_dict) > 0:
generate_chemical_structure_preds(pksnrpsvars, seq_record, options)
def retrieve_pksnrps_info(seq_record, geneclusternr, pksnrpsprots):
pksnrpsprotsnames = [utils.get_gene_id(cds) for cds in utils.get_pksnrps_cds_features(seq_record)]
domaindict = utils.get_nrpspks_domain_dict(seq_record)
substr_spec_preds = utils.get_nrpspks_substr_spec_preds(seq_record)
pksnrpsdomains = {}
domsdetails = {}
substrspecnrpspredictordict = {}
substrspecminowadict = {}
substrspecpkssigdict = {}
substrspecconsensusdict = {}
krpredictionsdict = {}
for i in pksnrpsprots:
domlist = []
domsdetails = {}
doms = domaindict[i]
for j in doms:
nr = 1
while j[0] + str(nr) in domlist:
nr += 1
domname = j[0] + str(nr)
domlist.append(domname)
domsdetails[domname] = [j[1],j[2]]
if "AMP-binding" in domname or "A-OX" in domname:
domname2 = i + "_" + "A" + str(nr)
substrspecminowadict[domname2] = substr_spec_preds.minowa_nrps_preds[i + "_A" + str(nr)]
substrspecnrpspredictordict[domname2] = [substr_spec_preds.nrps_code_preds[i + "_A" + str(nr)], substr_spec_preds.nrps_svm_preds[i + "_A" + str(nr)]]
substrspecconsensusdict[domname2] = substr_spec_preds.consensuspreds[i + "_A" + str(nr)]
if "PKS_AT" in domname:
domname2 = i + "_" + "AT" + str(nr)
substrspecminowadict[domname2] = substr_spec_preds.minowa_pks_preds[i + "_AT" + str(nr)]
substrspecpkssigdict[domname2] = substr_spec_preds.pks_code_preds[i + "_AT" + str(nr)]
substrspecconsensusdict[domname2] = substr_spec_preds.consensuspreds[i + "_AT" + str(nr)]
if "CAL_domain" in domname:
domname2 = i + "_" + "CAL" + str(nr)
substrspecminowadict[domname2] = substr_spec_preds.minowa_cal_preds[i + "_CAL" + str(nr)]
substrspecconsensusdict[domname2] = substr_spec_preds.consensuspreds[i + "_CAL" + str(nr)]
if "CAL_domain" in domname:
domname2 = i + "_" + "CAL" + str(nr)
substrspecminowadict[domname2] = substr_spec_preds.minowa_cal_preds[i + "_CAL" + str(nr)]
substrspecconsensusdict[domname2] = substr_spec_preds.consensuspreds[i + "_CAL" + str(nr)]
if "PKS_KR" in domname:
domname2 = i + "_" + "KR" + str(nr)
krpredictionsdict[domname2] = [substr_spec_preds.kr_activity_preds[i + "_KR" + str(nr)], substr_spec_preds.kr_stereo_preds[i + "_KR" + str(nr)]]
pksnrpsdomains[i] = [domlist,domsdetails]
structpred = utils.get_structure_pred(utils.get_cluster_by_nr(seq_record, geneclusternr))
return pksnrpsprotsnames, pksnrpsdomains, substrspecnrpspredictordict, substrspecminowadict, substrspecpkssigdict, substrspecconsensusdict, krpredictionsdict, structpred
def write_BGC(txt, info, options):
"Write BGC table to TXT"
#TXT columns: BGC ID, BGC_type, detection_rules_used, BGC_range, genes, subclusters,
# NRPSs_PKSs, signature_genes, RiPPs, pred_structure, monomers
txt.write("\t".join([
"BGC ID", "BGC type", "detection rules used", "BGC_range", "genes",
"subclusters", "NRPSs/PKSs", "signature_genes", "RiPPs",
"predicted structure", "monomers"
]) + "\n")
for BGCnr in info.clusternrs:
#Retrieve all data that will be written out
BGC_ID = "%s_c%s" % (info.seq_record.id.partition(".")[0], BGCnr)
cluster_feature = utils.get_cluster_by_nr(info.seq_record, BGCnr)
cluster_gene_features = utils.get_cluster_cds_features(
cluster_feature, info.seq_record)
BGC_type = info.clustertypes[BGCnr].replace("-", ";")
detection_rules_used = '"' + ";".join(
get_detection_rules(cluster_feature)) + '"'
BGC_range = ";".join([
str(cluster_feature.location.start),
str(cluster_feature.location.end)
])
genes = ";".join(info.accessions[BGCnr])
if 'subclusterblast' in cluster_feature.qualifiers:
subclusters = ";".join([
qual.partition("\t")[2]
for qual in cluster_feature.qualifiers['subclusterblast']
])
else:
subclusters = ""
#TODO The subclusterblast module should probably be changed for the precalcs to provide a list here of the 100% hits instead of all hits
NRPSs_PKSs = ";".join([
utils.get_gene_acc(cds).partition(".")[0]
for cds in cluster_gene_features
if 'sec_met' in cds.qualifiers and len([
qual for qual in cds.qualifiers['sec_met']
if qual.startswith('NRPS/PKS Domain:')
]) > 0
])
signature_genes = ";".join([
utils.get_gene_acc(cds).partition(".")[0]
for cds in cluster_gene_features if 'sec_met' in cds.qualifiers
])
if len(_find_core_peptides(cluster_feature, info.seq_record)) != 0:
ripp_list = []
for peptide in _find_core_peptides(cluster_feature,
info.seq_record):
for cds in cluster_gene_features:
if utils.features_overlap(cds, peptide):
ripp_list.append(
utils.get_gene_acc(cds).partition(".")[0])
break
# RiPPs = ";".join([[utils.get_gene_acc(cds).partition(".")[0] for cds in cluster_gene_features
# if utils.features_overlap(cds, peptide)][0] for peptide in
# _find_core_peptides(cluster_feature, info.seq_record)])
RiPPs = ";".join(ripp_list)
else:
RiPPs = "-"
if 'structure' in cluster_feature.qualifiers:
pred_structure = ";".join(cluster_feature.qualifiers['structure'])
else:
pred_structure = "N/A"
monomers = utils.get_structure_pred(cluster_feature)
#Write data to TXT
txt.write("\t".join([
BGC_ID, BGC_type, detection_rules_used, BGC_range, genes,
subclusters, NRPSs_PKSs, signature_genes, RiPPs, pred_structure,
monomers
]) + "\n")