def annotate_geneclusters(seq_record, options):
"""Re-annotate gene clusters in the seq_record"""
pfam_features = utils.get_pfam_features(seq_record)
cf_clusters = find_cf_clusters(pfam_features, seq_record, options)
#Integrate ClusterFinder clusters with existing cluster features
newclusters = []
cluster_features = utils.get_cluster_features(seq_record)
for cf_cluster in cf_clusters:
overlaps = False
cf_type = "cf_putative"
for cluster in cluster_features:
cluster_sig_genes = [gene for gene in utils.get_secmet_cds_features(seq_record) if gene in utils.get_cluster_cds_features(cluster, seq_record)]
if utils.features_overlap(cf_cluster, cluster):
overlaps = True
if options.borderpredict: #Predict gene cluster borders using ClusterFinder
if ((cluster.location.end + cluster.location.start) / 2) in cf_cluster.location:
cluster.location = cf_cluster.location
for sig_gene in cluster_sig_genes:
startpoint = min([sig_gene.location.start, sig_gene.location.end])
endpoint = max([sig_gene.location.start, sig_gene.location.end])
if cluster.location.start > startpoint:
cluster.location = FeatureLocation(startpoint, cluster.location.end)
if cluster.location.end < endpoint:
cluster.location = FeatureLocation(cluster.location.start, endpoint)
elif cf_cluster.location.start < cluster.location.start and cf_cluster.location.end > cluster.location.end:
cluster.location = cf_cluster.location
elif cf_cluster.location.start < cluster.location.start:
cluster.location = FeatureLocation(cf_cluster.location.start, cluster.location.end)
elif cf_cluster.location.end > cluster.location.end:
cluster.location = FeatureLocation(cluster.location.start, cf_cluster.location.end)
cluster.qualifiers['probability'] = [ "%01.4f" % cf_cluster.probability ]
if not overlaps:
cf_cluster_CDSs = utils.get_cluster_cds_features(cf_cluster, seq_record)
for CDS in cf_cluster_CDSs:
if 'sec_met' in CDS.qualifiers:
type_sec_met_qualifiers = [feat for feat in CDS.qualifiers['sec_met'] if "Type: " in feat]
for qualifier in type_sec_met_qualifiers:
if "cf_fatty_acid" in qualifier:
if cf_type == "cf_putative":
cf_type = "cf_fatty_acid"
elif cf_type == "cf_saccharide":
cf_type = "cf_fatty_acid-saccharide"
if "cf_saccharide" in qualifier:
if cf_type == "cf_putative":
cf_type = "cf_saccharide"
elif cf_type == "cf_fatty_acid":
cf_type = "cf_fatty_acid-saccharide"
new_cluster = SeqFeature(cf_cluster.location, type="cluster")
new_cluster.qualifiers['product'] = [cf_type]
new_cluster.qualifiers['probability'] = [ "%01.4f" % cf_cluster.probability ]
newclusters.append(new_cluster)
seq_record.features.extend(newclusters)
#Re-number clusters
clusters = utils.get_cluster_features(seq_record)
clusters.sort(compare_feature_locations)
clusternr = options.clusternr_offset
for cluster in clusters:
cluster.qualifiers['note'] = ["Cluster number: %s" % clusternr]
clusternr += 1
options.next_clusternr = clusternr
def perform_subclusterblast(options, seq_record, clusters, proteinlocations,
proteinstrands, proteinannotations, proteintags):
#Run BLAST on gene cluster proteins of each cluster and parse output
logging.info("Running NCBI BLAST+ subcluster searches..")
geneclusters = utils.get_sorted_cluster_features(seq_record)
with TemporaryDirectory(change=True):
for genecluster in geneclusters:
clusternumber = utils.get_cluster_number(genecluster)
if options.debug and os.path.exists(options.dbgclusterblast +
os.sep + "subclusterblast" +
os.sep + "cluster" +
str(clusternumber) + ".txt"):
logging.debug(
"Skipping SubClusterblast calculations, using results from %s instead"
% options.dbgclusterblast + os.sep + "subclusterblast" +
os.sep + "cluster" + str(clusternumber) + ".txt")
else:
logging.info(" Gene cluster " + str(clusternumber))
queryclusternames, queryclusterseqs, queryclusterprots = create_blast_inputs(
genecluster, seq_record)
write_clusterblast_inputfiles(options, queryclusternames,
queryclusterseqs)
run_clusterblast_processes(options, searchtype="subclusters")
blastoutput = read_clusterblast_output(options)
write_raw_clusterblastoutput(options.full_outputfolder_path,
blastoutput,
searchtype="subclusters")
logging.info(" Blast search finished. Parsing results...")
minseqcoverage = 40
minpercidentity = 45
blastdict, querylist, hitclusters = parse_blast(
blastoutput, seq_record, minseqcoverage, minpercidentity)
querylist = remove_queries_without_hits(querylist, blastdict)
allcoregenes = [
utils.get_gene_acc(cds)
for cds in utils.get_secmet_cds_features(seq_record)
]
rankedclusters, rankedclustervalues, hitclusterdict, hitclusterdata = score_clusterblast_output(
blastdict, querylist, hitclusters, clusters, allcoregenes)
# store all clusterblast related data in a utils.Storage object and serialize it
subclusterblastStorage = utils.Storage()
subclusterblastStorage.clusternumber = clusternumber
subclusterblastStorage.queryclusterprots = queryclusterprots
subclusterblastStorage.clusters = clusters
subclusterblastStorage.hitclusterdata = hitclusterdata
subclusterblastStorage.rankedclusters = rankedclusters
subclusterblastStorage.rankedclustervalues = rankedclustervalues
subclusterblastStorage.proteintags = proteintags
subclusterblastStorage.proteinlocations = proteinlocations
subclusterblastStorage.proteinannotations = proteinannotations
subclusterblastStorage.proteinstrands = proteinstrands
write_clusterblast_output(options,
seq_record,
subclusterblastStorage,
searchtype="subclusters")
def perform_clusterblast(options, seq_record, clusters, proteinlocations, proteinstrands, proteinannotations, proteintags):
#Run BLAST on gene cluster proteins of each cluster and parse output
logging.info("Running DIAMOND gene cluster searches..")
geneclusters = utils.get_sorted_cluster_features(seq_record)
with TemporaryDirectory(change=True) as tempdir:
for genecluster in geneclusters:
clusternumber = utils.get_cluster_number(genecluster)
if options.debug and os.path.exists(options.dbgclusterblast + os.sep + "clusterblast" + os.sep + "cluster" + str(clusternumber) + ".txt"):
logging.debug ("Skipping Clusterblast calculations, using results from %s instead" % options.dbgclusterblast + os.sep + "clusterblast" + os.sep + "cluster" + str(clusternumber) + ".txt")
else:
logging.info(" Gene cluster " + str(clusternumber))
queryclusternames, queryclusterseqs, queryclusterprots = create_blast_inputs(genecluster, seq_record)
utils.writefasta(queryclusternames, queryclusterseqs, "input.fasta")
if options.taxon == "plants":
out, err, retcode = run_diamond("input.fasta", path.join(options.clusterblastdir, "plantgeneclusterprots"), tempdir, options)
else:
out, err, retcode = run_diamond("input.fasta", path.join(options.clusterblastdir, "geneclusterprots"), tempdir, options)
if retcode != 0:
logging.error("Running diamond failed: returned %s, stderr: %r, stdout: %r", retcode, err, out)
out, err, retcode = convert_to_tabular(tempdir)
if retcode != 0:
logging.error("Converting daa failed: returned %s, stderr: %r, stdout: %r", retcode, err, out)
with open("input.out", 'r') as fh:
blastoutput = fh.read()
write_raw_clusterblastoutput(options.full_outputfolder_path, blastoutput)
logging.info(" DIAMOND search finished. Parsing results...")
minseqcoverage = 10
minpercidentity = 30
blastdict, querylist, hitclusters = parse_blast(blastoutput, seq_record, minseqcoverage, minpercidentity)
querylist = remove_queries_without_hits(querylist, blastdict)
allcoregenes = [utils.get_gene_acc(cds) for cds in utils.get_secmet_cds_features(seq_record)]
rankedclusters, rankedclustervalues, hitclusterdict, hitclusterdata = score_clusterblast_output(blastdict, querylist, hitclusters, clusters, allcoregenes)
# store all clusterblast related data in a utils.Storage object
clusterblastStorage = utils.Storage()
clusterblastStorage.clusternumber = clusternumber
clusterblastStorage.queryclusterprots = queryclusterprots
clusterblastStorage.clusters = clusters
clusterblastStorage.hitclusterdata = hitclusterdata
clusterblastStorage.rankedclusters = rankedclusters
clusterblastStorage.rankedclustervalues = rankedclustervalues
clusterblastStorage.proteintags = proteintags
clusterblastStorage.proteinlocations = proteinlocations
clusterblastStorage.proteinannotations = proteinannotations
clusterblastStorage.proteinstrands = proteinstrands
#write_clusterblast_output(options, seq_record, clusternumber, queryclusterprots, clusters, hitclusterdata, rankedclusters, rankedclustervalues, proteintags, proteinlocations, proteinannotations, proteinstrands)
write_clusterblast_output(options, seq_record, clusterblastStorage)
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 perform_knownclusterblast(options, seq_record, clusters, proteins):
# Run BLAST on gene cluster proteins of each cluster and parse output
logging.debug("Running DIAMOND knowncluster searches..")
geneclusters = utils.get_sorted_cluster_features(seq_record)
all_names, all_seqs, all_prots = [], [], []
prots_by_cluster = []
for genecluster in geneclusters:
names, seqs, prots = clusterblast.create_blast_inputs(
genecluster, seq_record)
all_names.extend(names)
all_seqs.extend(seqs)
all_prots.extend(prots)
prots_by_cluster.append(prots)
debug_path = os.path.join(options.dbgclusterblast,
"knownclusterblastoutput.txt")
if options.dbgclusterblast and os.path.exists(debug_path):
logging.debug("Skipping DIAMOND calculations, using previous results")
with open(debug_path, "r") as fh:
blastoutput = fh.read()
else:
with TemporaryDirectory(change=True) as tempdir:
utils.writefasta(
[qcname.replace(" ", "_") for qcname in all_names], all_seqs,
"input.fasta")
out, err, retcode = clusterblast.run_diamond(
"input.fasta",
os.path.join(options.knownclusterblastdir,
'knownclusterprots'), tempdir, options)
if retcode != 0:
logging.debug("out: %r, err: %r, retcode: %s", out, err,
retcode)
with open("input.out", 'r') as fh:
blastoutput = fh.read()
clusterblast.write_raw_clusterblastoutput(
options.full_outputfolder_path,
blastoutput,
searchtype="knownclusters")
minseqcoverage = 40
minpercidentity = 45
clusters_by_number, _ = clusterblast.parse_all_clusters(
blastoutput, minseqcoverage, minpercidentity, seq_record)
knownclusterblastStorage = utils.Storage()
knownclusterblastStorage.clusters = clusters
knownclusterblastStorage.proteins = proteins
for genecluster, queryclusterprots in zip(geneclusters, prots_by_cluster):
clusternumber = utils.get_cluster_number(genecluster)
cluster_names_to_queries = clusters_by_number.get(clusternumber, {})
allcoregenes = [
utils.get_gene_id(cds)
for cds in utils.get_secmet_cds_features(seq_record)
]
ranking = clusterblast.score_clusterblast_output(
clusters, allcoregenes, cluster_names_to_queries)
# store all clusterblast related data in a utils.Storage object and serialize it
knownclusterblastStorage.clusternumber = clusternumber
knownclusterblastStorage.queryclusterprots = queryclusterprots
knownclusterblastStorage.ranking = ranking
clusterblast.write_clusterblast_output(options,
seq_record,
knownclusterblastStorage,
searchtype="knownclusters")
mibig_protein_homology(blastoutput, seq_record, geneclusters, clusters,
options)
def perform_clusterblast(options, seq_record, clusters, proteins):
#Run BLAST on gene cluster proteins of each cluster and parse output
geneclusters = utils.get_sorted_cluster_features(seq_record)
debug_path = os.path.abspath(
os.path.join(options.dbgclusterblast, "clusterblastoutput.txt"))
with TemporaryDirectory(change=True) as tempdir:
all_names, all_seqs, all_prots = [], [], []
prots_by_cluster = []
for genecluster in geneclusters:
names, seqs, prots = create_blast_inputs(genecluster, seq_record)
all_names.extend(names)
all_seqs.extend(seqs)
all_prots.extend(prots)
prots_by_cluster.append(prots)
if options.dbgclusterblast and os.path.exists(debug_path):
logging.debug(
"Skipping DIAMOND calculations, using results from %s instead",
debug_path)
with open(debug_path, "r") as fh:
blastoutput = fh.read()
logging.debug(" Parsing results from given file...")
else:
logging.debug("Running DIAMOND gene cluster search..")
utils.writefasta(all_names, all_seqs, "input.fasta")
out, err, retcode = run_diamond(
"input.fasta",
path.join(options.clusterblastdir, "geneclusterprots"),
tempdir, options)
if retcode != 0:
logging.error(
"Running diamond failed: returned %s, stderr: %r, stdout: %r",
retcode, err, out)
logging.debug(" DIAMOND search finished. Parsing results...")
with open("input.out", 'r') as fh:
blastoutput = fh.read()
write_raw_clusterblastoutput(options.full_outputfolder_path,
blastoutput)
minseqcoverage = 10
minpercidentity = 30
clusters_by_number, _ = parse_all_clusters(blastoutput, minseqcoverage,
minpercidentity, seq_record)
clusterblastStorage = utils.Storage()
clusterblastStorage.clusters = clusters
clusterblastStorage.proteins = proteins
for genecluster, queryclusterprots in zip(geneclusters,
prots_by_cluster):
clusternumber = utils.get_cluster_number(genecluster)
cluster_names_to_queries = clusters_by_number.get(
clusternumber, {})
allcoregenes = [
utils.get_gene_acc(cds)
for cds in utils.get_secmet_cds_features(seq_record)
]
ranking = score_clusterblast_output(clusters, allcoregenes,
cluster_names_to_queries)
# store all clusterblast related data in a utils.Storage object
clusterblastStorage.clusternumber = clusternumber
clusterblastStorage.queryclusterprots = queryclusterprots
clusterblastStorage.ranking = ranking
write_clusterblast_output(options, seq_record, clusterblastStorage)
def parse_clusterblast_details(options,
seq_record,
clusternr,
details,
toptenhitclusters,
nrhitclusters,
queryclustergenes,
queryclustergenesdetails,
cb_accessiondict,
searchtype="general"):
#For every gene cluster, store hit genes and details
colorgroupsdict = {}
hitclusterdata = {}
hitclusternr = 1
compound_found = "n"
allcoregenes = [
utils.get_gene_id(cds)
for cds in utils.get_secmet_cds_features(seq_record)
]
if searchtype == "general":
seq_record.nrhitgeneclusters[clusternr] = 0
elif searchtype == "subclusters":
seq_record.sc_nrhitgeneclusters[clusternr] = 0
elif searchtype == "knownclusters":
seq_record.kc_nrhitgeneclusters[clusternr] = 0
for i in details:
hitclustergenes = []
hitclustergenesdetails = {}
hits_accessions_dict = {}
#Only calculate for first ten hit gene clusters
if hitclusternr <= options.nclusters:
if searchtype == "general":
seq_record.nrhitgeneclusters[clusternr] = hitclusternr
elif searchtype == "subclusters":
seq_record.sc_nrhitgeneclusters[clusternr] = hitclusternr
elif searchtype == "knownclusters":
seq_record.kc_nrhitgeneclusters[clusternr] = hitclusternr
accession = cb_accessiondict[hitclusternr]
hitclustergeneslines = ((i.split(
"Table of genes, locations, strands and annotations of subject cluster:\n"
)[1]).split("\n\nTable of Blast hits ")[0]).split("\n")
for j in hitclustergeneslines:
tabs = j.split("\t")
hitclustergenes.append(tabs[0])
hitclustergenesdetails[tabs[0]] = [
tabs[2], tabs[3], tabs[4], tabs[5], tabs[1]
]
blasthitslines = ((i.split("%coverage, e-value):\n")[1]
).split("\n\n")[0]).split("\n")
querygeneswithhits = []
coregeneswithhits = []
for k in blasthitslines:
if k.split("\t")[0] not in querygeneswithhits:
querygeneswithhits.append(k.split("\t")[0])
if hits_accessions_dict.has_key(k.split("\t")[1]):
hits_accessions_dict[k.split("\t")[1]].append(
k.split("\t")[0])
else:
hits_accessions_dict[k.split("\t")[1]] = [k.split("\t")[0]]
if k.split("\t")[0] in allcoregenes and k.split(
"\t")[0] not in coregeneswithhits:
coregeneswithhits.append(k.split("\t")[0])
if searchtype == "general":
for k in seq_record.known_compound_dict.keys():
if k in i and compound_found == "n" and len(
querygeneswithhits) > 2 and len(
coregeneswithhits) > 0:
seq_record.closestcompounddict[
clusternr] = seq_record.known_compound_dict[k]
compound_found = "y"
#Create Blast dict
blasthitdict, blastdetailsdict, querygenes, hitgenes, revblasthitdict = create_blastdicts(
blasthitslines)
#Create colorgroups dict
colorgroupsdict = construct_colorgroups(
colorgroupsdict, clusternr, blasthitdict, blastdetailsdict,
seq_record.internalhomologygroupsdict, hitclusternr)
#Store all data in hitclusterdata dict
hitclusterdata[hitclusternr] = [
colorgroupsdict, hitclustergenes, hitclustergenesdetails,
queryclustergenes, queryclustergenesdetails, toptenhitclusters,
accession, hits_accessions_dict, blastdetailsdict
]
hitclusternr += 1
elif hitclusternr > options.nclusters and hitclusternr <= 50:
blasthitslines = ((i.split("%coverage, e-value):\n")[1]
).split("\n\n")[0]).split("\n")
querygeneswithhits = []
coregeneswithhits = []
for k in blasthitslines:
if k.split("\t")[0] not in querygeneswithhits:
querygeneswithhits.append(k.split("\t")[0])
if k.split("\t")[0] in allcoregenes and k.split(
"\t")[0] not in coregeneswithhits:
coregeneswithhits.append(k.split("\t")[0])
hitclusternr += 1
if searchtype == "general":
seq_record.queryclusterdata[clusternr] = [
nrhitclusters, hitclusterdata
]
elif searchtype == "subclusters":
seq_record.sc_queryclusterdata[clusternr] = [
nrhitclusters, hitclusterdata
]
elif searchtype == "knownclusters":
seq_record.kc_queryclusterdata[clusternr] = [
nrhitclusters, hitclusterdata
]
def test_get_secmet_cds_featuers(self):
"Test utils.get_secmet_cds_features()"
self.features[3].qualifiers['sec_met'] = ["Type: Fake"]
self.features[4].qualifiers['sec_met'] = ["Type: none"]
features = utils.get_secmet_cds_features(self.record)
self.assertEqual([self.features[3]], features)
def annotate_geneclusters(seq_record, options):
"""Re-annotate gene clusters in the seq_record"""
pfam_features = utils.get_pfam_features(seq_record)
cf_clusters = find_cf_clusters(pfam_features, seq_record, options)
# Integrate ClusterFinder clusters with existing cluster features
newclusters = []
cluster_features = utils.get_cluster_features(seq_record)
secmet_cds_features = utils.get_secmet_cds_features(seq_record)
for cf_cluster in cf_clusters:
overlaps = False
cf_type = "cf_putative"
for cluster in cluster_features:
if not utils.features_overlap(cf_cluster, cluster):
continue
overlaps = True
# Get signature genes from antiSMASH-predicted cluster
features_in_cluster = utils.get_cluster_cds_features(
cluster, seq_record)
cluster_sig_genes = [
gene for gene in secmet_cds_features
if gene in features_in_cluster
]
# Predict gene cluster borders using ClusterFinder
if options.borderpredict:
if ((cluster.location.end + cluster.location.start) /
2) in cf_cluster.location:
# Make sure that antiSMASH signature genes are still included in the cluster
for sig_gene in cluster_sig_genes:
startpoint = min(
[sig_gene.location.start, sig_gene.location.end])
endpoint = max(
[sig_gene.location.start, sig_gene.location.end])
if cf_cluster.location.start > startpoint:
cf_cluster.location = FeatureLocation(
startpoint, cf_cluster.location.end)
if cf_cluster.location.end < endpoint:
cf_cluster.location = FeatureLocation(
cf_cluster.location.start, endpoint)
cluster_border = SeqFeature(cf_cluster.location,
type="cluster_border")
cluster_border.qualifiers = {
"tool": ["clusterfinder"],
"probability": [cf_cluster.probability],
"note": ["best prediction"],
}
seq_record.features.append(cluster_border)
elif cf_cluster.location.start < cluster.location.start and cf_cluster.location.end > cluster.location.end:
cluster.location = cf_cluster.location
elif cf_cluster.location.start < cluster.location.start:
cluster.location = FeatureLocation(cf_cluster.location.start,
cluster.location.end)
elif cf_cluster.location.end > cluster.location.end:
cluster.location = FeatureLocation(cluster.location.start,
cf_cluster.location.end)
cluster.qualifiers['probability'] = [
"%01.4f" % cf_cluster.probability
]
if not overlaps and not ('borderpredict_only' in options
and options.borderpredict_only):
cf_cluster_CDSs = utils.get_cluster_cds_features(
cf_cluster, seq_record)
for CDS in cf_cluster_CDSs:
if 'sec_met' in CDS.qualifiers:
type_sec_met_qualifiers = [
feat for feat in CDS.qualifiers['sec_met']
if "Type: " in feat
]
for qualifier in type_sec_met_qualifiers:
if "cf_fatty_acid" in qualifier:
if cf_type == "cf_putative":
cf_type = "cf_fatty_acid"
elif cf_type == "cf_saccharide":
cf_type = "cf_fatty_acid-saccharide"
if "cf_saccharide" in qualifier:
if cf_type == "cf_putative":
cf_type = "cf_saccharide"
elif cf_type == "cf_fatty_acid":
cf_type = "cf_fatty_acid-saccharide"
new_cluster = SeqFeature(cf_cluster.location, type="cluster")
new_cluster.qualifiers['product'] = [cf_type]
new_cluster.qualifiers['probability'] = [
"%01.4f" % cf_cluster.probability
]
newclusters.append(new_cluster)
if len(newclusters):
seq_record.features.extend(newclusters)
renumber_clusters(seq_record, options)
def perform_knownclusterblast(options, seq_record, clusters, proteinlocations,
proteinstrands, proteinannotations, proteintags):
#Run BLAST on gene cluster proteins of each cluster and parse output
logging.info("Running DIAMOND knowncluster searches..")
geneclusters = utils.get_sorted_cluster_features(seq_record)
with TemporaryDirectory(change=True) as tempdir:
for genecluster in geneclusters:
clusternumber = utils.get_cluster_number(genecluster)
if options.debug and os.path.exists(options.dbgclusterblast +
os.sep + "knwonclusterblast" +
os.sep + "cluster" +
str(clusternumber) + ".txt"):
logging.debug(
"Skipping SubClusterblast calculations, using results from %s instead"
% options.dbgclusterblast + os.sep + "knownclusterblast" +
os.sep + "cluster" + str(clusternumber) + ".txt")
else:
logging.info(" Gene cluster " + str(clusternumber))
queryclusternames, queryclusterseqs, queryclusterprots = create_blast_inputs(
genecluster, seq_record)
utils.writefasta(
[qcname.replace(" ", "_") for qcname in queryclusternames],
queryclusterseqs, "input.fasta")
out, err, retcode = run_diamond(
"input.fasta",
path.join(options.knownclusterblastdir,
'knownclusterprots'), tempdir, options)
if retcode != 0:
logging.debug("out: %r, err: %r, retcode: %s", out, err,
retcode)
convert_to_tabular(tempdir)
with open("input.out", 'r') as fh:
blastoutput = fh.read()
write_raw_clusterblastoutput(options.full_outputfolder_path,
blastoutput,
searchtype="knownclusters")
logging.info(" DIAMOND search finished. Parsing results...")
minseqcoverage = 40
minpercidentity = 45
blastdict, querylist, hitclusters = parse_blast(
blastoutput, seq_record, minseqcoverage, minpercidentity)
querylist = remove_queries_without_hits(querylist, blastdict)
allcoregenes = [
utils.get_gene_id(cds)
for cds in utils.get_secmet_cds_features(seq_record)
]
rankedclusters, rankedclustervalues, hitclusterdict, hitclusterdata = score_clusterblast_output(
blastdict, querylist, hitclusters, clusters, allcoregenes)
# store all clusterblast related data in a utils.Storage object and serialize it
knownclusterblastStorage = utils.Storage()
knownclusterblastStorage.clusternumber = clusternumber
knownclusterblastStorage.queryclusterprots = queryclusterprots
knownclusterblastStorage.clusters = clusters
knownclusterblastStorage.hitclusterdata = hitclusterdata
knownclusterblastStorage.rankedclusters = rankedclusters
knownclusterblastStorage.rankedclustervalues = rankedclustervalues
knownclusterblastStorage.proteintags = proteintags
knownclusterblastStorage.proteinlocations = proteinlocations
knownclusterblastStorage.proteinannotations = proteinannotations
knownclusterblastStorage.proteinstrands = proteinstrands
write_clusterblast_output(options,
seq_record,
knownclusterblastStorage,
searchtype="knownclusters")
