def annotate_pksnrps(pksnrpsvars, seq_record, options):
withinclustergenes = utils.get_withincluster_cds_features(seq_record)
if len(withinclustergenes) == 0:
logging.debug('No genes within a sec_met cluster found for %r' %
seq_record.id)
return pksnrpsvars
run_nrpspks_specific_hmmer(seq_record, withinclustergenes, pksnrpsvars)
name_nrpspks(seq_record, pksnrpsvars, withinclustergenes, options)
pksnrpsvars.pksnrpscoregenes = utils.get_pksnrps_cds_features(seq_record)
return pksnrpsvars
def retrieve_gene_cluster_annotations(seq_record, smcogdict, gtrcoglist,
transportercoglist, geneclusternr):
allcoregenes = [
utils.get_gene_id(cds)
for cds in utils.get_secmet_cds_features(seq_record)
]
pksnrpscoregenes = [
utils.get_gene_id(cds)
for cds in utils.get_pksnrps_cds_features(seq_record)
]
feature_by_id = utils.get_feature_dict(seq_record)
clustergenes = [
utils.get_gene_id(cds) for cds in utils.get_cluster_cds_features(
utils.get_cluster_by_nr(seq_record, geneclusternr), seq_record)
]
clustertype = utils.get_cluster_type(
utils.get_cluster_by_nr(seq_record, geneclusternr))
annotations = {}
colors = []
starts = []
ends = []
strands = []
pksnrpsprots = []
gtrs = []
transporters = []
for j in clustergenes:
cdsfeature = feature_by_id[j]
if cdsfeature.qualifiers.has_key('product'):
annotations[j] = cdsfeature.qualifiers['product'][0]
else:
annotations[j] = 'Unannotated gene'
starts.append(cdsfeature.location.start)
ends.append(cdsfeature.location.end)
if cdsfeature.strand == -1:
strands.append("-")
else:
strands.append("+")
if j in allcoregenes:
colors.append("#810E15")
else:
colors.append("grey")
if j in pksnrpscoregenes:
pksnrpsprots.append(j)
if smcogdict.has_key(j):
if len(smcogdict[j]) > 0 and smcogdict[j][0] in gtrcoglist:
gtrs.append(j)
if len(smcogdict[j]) > 0 and smcogdict[j][0] in transportercoglist:
transporters.append(j)
clustersize = max(ends) - min(starts)
return clustergenes, clustertype, annotations, colors, starts, ends, strands, pksnrpsprots, gtrs, transporters, clustersize
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 run_smcog_analysis(seq_record, options):
#run_smcog_analysis(opts, globalvars, geneclustervars, pksnrpscoregenes)
logging.info('Running smCOG analysis')
smcogvars = utils.Storage()
smcogvars.smcogtreedict = {}
smcogvars.smcogdict = {}
geneclustergenes = utils.get_withincluster_cds_features(seq_record)
pksnrpscoregenes = utils.get_pksnrps_cds_features(seq_record)
logging.info("Performing smCOG analysis")
smcogs_fasta = utils.get_specific_multifasta(geneclustergenes)
smcogs_opts = ["-E", "1E-6"]
smcogs_results = utils.run_hmmscan(utils.get_full_path(__file__, "smcogs.hmm"), smcogs_fasta, smcogs_opts)
hmmlengthsdict = utils.hmmlengths(utils.get_full_path(__file__, "smcogs.hmm"))
smcogvars.smcogdict = parse_hmmscan_results(smcogs_results, hmmlengthsdict)
#Write output
options.smcogsfolder = path.abspath(path.join(options.outputfoldername, "smcogs"))
if not os.path.exists(options.smcogsfolder):
os.mkdir(options.smcogsfolder)
originaldir = os.getcwd()
os.chdir(options.smcogsfolder)
smcogfile = open("smcogs.txt","w")
pksnrpscoregenenames = [utils.get_gene_id(feature) for feature in pksnrpscoregenes]
for feature in geneclustergenes:
k = utils.get_gene_id(feature)
if k not in pksnrpscoregenenames:
if smcogvars.smcogdict.has_key(k):
l = smcogvars.smcogdict[k]
smcogfile.write(">> " + k + "\n")
smcogfile.write("name\tstart\tend\te-value\tscore\n")
smcogfile.write("** smCOG hits **\n")
for i in l:
smcogfile.write(str(i[0]) + "\t" + str(i[1]) + "\t" + str(i[2]) + "\t" + str(i[3]) + "\t" + str(i[4]) + "\n")
smcogfile.write("\n\n")
smcogfile.close()
#smCOG phylogenetic tree construction
logging.info("Calculating and drawing phylogenetic trees of cluster genes "
"with smCOG members")
with TemporaryDirectory(change=True):
smcoganalysisgenes = []
for feature in geneclustergenes:
k = utils.get_gene_id(feature)
if k not in pksnrpscoregenenames:
smcoganalysisgenes.append(feature)
smcogsets = []
equalpartsizes = int(len(smcoganalysisgenes)/options.cpus)
for i in range(options.cpus):
if i == 0:
geneslist = smcoganalysisgenes[:equalpartsizes]
elif i == (options.cpus - 1):
geneslist = smcoganalysisgenes[(i*equalpartsizes):]
else:
geneslist = smcoganalysisgenes[(i*equalpartsizes):((i+1)*equalpartsizes)]
smcogsets.append(geneslist)
processes = []
z = 0
for k in smcogsets:
processes.append(Process(target=smcog_analysis,
args=[k, z, seq_record,
smcogvars.smcogdict, options.smcogsfolder]))
z += 1
for k in processes:
k.start()
time.sleep(1)
while True:
processrunning = "n"
for k in processes:
if k.is_alive():
processrunning = "y"
if processrunning == "y":
time.sleep(5)
else:
break
for k in processes:
k.join()
os.chdir(options.smcogsfolder)
dircontents = os.listdir(os.getcwd())
for k in dircontents:
if ".png" in k:
tag = k.split(".png")[0]
smcogvars.smcogtreedict[tag] = tag + ".png"
os.chdir(originaldir)
_annotate(geneclustergenes, smcogvars, options)
def test_get_pksnrps_cds_featuers(self):
"""Test utils.get_pksnrps_cds_features()"""
self.features[3].qualifiers['sec_met'] = ["NRPS/PKS Domain: "]
features = utils.get_pksnrps_cds_features(self.record)
self.assertEqual([self.features[3]], features)
