cols = line.split('\t')
OTU = cols[9]
Hit = cols[8]
if not OTU in iSeqMapped:
iSeqMapped[OTU] = [Hit]
else:
iSeqMapped[OTU].append(Hit)
with open(ClusterComp, 'w') as clusters:
clusters.write('OTU\tiSeqs\n')
for k, v in natsorted(iSeqMapped.items()):
clusters.write('%s\t%s\n' % (k, ', '.join(v)))
#strip N's
ufitslib.log.info("Cleaning up padding from OTUs")
otu_clean = os.path.join(tmp, args.out + '.EE' + args.maxee + '.clean.fa')
ufitslib.fasta_strip_padding(uclust_out, otu_clean)
#run optional uchime_ref
if not args.uchime_ref:
uchime_out = otu_clean
else:
uchime_out = os.path.join(
tmp, args.out + '.EE' + args.maxee + '.uchime.otus.fa')
#R. Edgar now says using largest DB is better for UCHIME, so use the one distributed with taxonomy
if args.uchime_ref in [
'ITS', '16S', 'LSU', 'COI'
]: #test if it is one that is setup, otherwise default to full path
uchime_db = os.path.join(parentdir, 'DB',
args.uchime_ref + '.extracted.fa')
if not os.path.isfile(uchime_db):
ufitslib.log.error(
tax = col[2]
if any(x in tax for x in filt_tax_values):
record = seqDict[ID]
record.id = 'OTU' + str(otu_counter) + ';UTAX;tax=' + tax
record.name = ''
record.description = ''
SeqIO.write(record, output, 'fasta')
otu_counter += 1
total = ufitslib.countfasta(ref_clustered) - num_refcluster
ufitslib.log.info('{0:,}'.format(total) + ' classified to %s' %
taxonomyLookup.get(args.utax_level))
#clean up padded N's
ufitslib.log.info("Cleaning up padding from OTUs")
otu_clean = os.path.join(tmp, args.out + '.clean.otus.fa')
ufitslib.fasta_strip_padding(ref_clustered, otu_clean)
total = ufitslib.countfasta(otu_clean)
ufitslib.log.info('{0:,}'.format(total) + ' total OTUs')
#now map reads back to OTUs
uc_out = os.path.join(tmp, args.out + '.EE' + args.maxee + '.mapping.uc')
otu_table = os.path.join(tmp, args.out + '.EE' + args.maxee + '.otu_table.txt')
#setup reads to map
if args.map_filtered:
reads = filter_fasta
else:
reads = orig_fasta
ufitslib.log.info("Mapping Reads to OTUs and Building OTU table")
cmd = [
'vsearch', '--usearch_global', reads, '--strand', 'plus', '--id', '0.97',
'--db', otu_clean, '--uc', uc_out, '--otutabout', otu_table
ID = col[0]
tax = col[2]
if any(x in tax for x in filt_tax_values):
record = seqDict[ID]
record.id = 'OTU'+str(otu_counter)+';UTAX;tax='+tax
record.name = ''
record.description = ''
SeqIO.write(record, output, 'fasta')
otu_counter += 1
total = ufitslib.countfasta(ref_clustered) - num_refcluster
ufitslib.log.info('{0:,}'.format(total) + ' classified to %s' % taxonomyLookup.get(args.utax_level))
#clean up padded N's
ufitslib.log.info("Cleaning up padding from OTUs")
otu_clean = os.path.join(tmp, args.out + '.clean.otus.fa')
ufitslib.fasta_strip_padding(ref_clustered, otu_clean)
total = ufitslib.countfasta(otu_clean)
ufitslib.log.info('{0:,}'.format(total) + ' total OTUs')
#now map reads back to OTUs
uc_out = os.path.join(tmp, args.out + '.EE' + args.maxee + '.mapping.uc')
otu_table = os.path.join(tmp, args.out + '.EE' + args.maxee + '.otu_table.txt')
#setup reads to map
if args.map_filtered:
reads = filter_fasta
else:
reads = orig_fasta
ufitslib.log.info("Mapping Reads to OTUs and Building OTU table")
cmd = ['vsearch', '--usearch_global', reads, '--strand', 'plus', '--id', '0.97', '--db', otu_clean, '--uc', uc_out, '--otutabout', otu_table]
ufitslib.runSubprocess(cmd, ufitslib.log)
cols = line.split('\t')
OTU = cols[9]
Hit = cols[8]
if not OTU in iSeqMapped:
iSeqMapped[OTU] = [Hit]
else:
iSeqMapped[OTU].append(Hit)
with open(ClusterComp, 'w') as clusters:
clusters.write('OTU\tiSeqs\n')
for k,v in natsorted(iSeqMapped.items()):
clusters.write('%s\t%s\n' % (k, ', '.join(v)))
#strip N's
ufitslib.log.info("Cleaning up padding from OTUs")
otu_clean = os.path.join(tmp, args.out + '.EE' + args.maxee + '.clean.fa')
ufitslib.fasta_strip_padding(uclust_out, otu_clean)
#run optional uchime_ref
if not args.uchime_ref:
uchime_out = otu_clean
else:
uchime_out = os.path.join(tmp, args.out + '.EE' + args.maxee + '.uchime.otus.fa')
#R. Edgar now says using largest DB is better for UCHIME, so use the one distributed with taxonomy
if args.uchime_ref in ['ITS', '16S', 'LSU', 'COI']: #test if it is one that is setup, otherwise default to full path
uchime_db = os.path.join(parentdir, 'DB', args.uchime_ref+'.extracted.fa')
if not os.path.isfile(uchime_db):
ufitslib.log.error("Database not properly configured, run `ufits install` to setup DB, skipping chimera filtering")
uchime_out = otu_clean
else:
uchime_db = os.path.abspath(args.uchime_ref)
cmd = ["vsearch", "--sortbysize", unoise_out, "--minsize", args.minsize, "--output", sort_out]
ufitslib.runSubprocess(cmd, ufitslib.log)
# now run clustering algorithm
radius = str(100 - int(args.pct_otu))
otu_out = os.path.join(tmp, args.out + ".EE" + args.maxee + ".otus.fa")
ufitslib.log.info("Clustering OTUs (UPARSE)")
cmd = [usearch, "-cluster_otus", sort_out, "-relabel", "OTU", "-otu_radius_pct", radius, "-otus", otu_out]
ufitslib.runSubprocess(cmd, ufitslib.log)
numOTUs = ufitslib.countfasta(otu_out)
ufitslib.log.info("{0:,}".format(numOTUs) + " OTUs")
# clean up padded N's
ufitslib.log.info("Cleaning up padding from OTUs")
otu_clean = os.path.join(tmp, args.out + ".EE" + args.maxee + ".clean.otus.fa")
ufitslib.fasta_strip_padding(otu_out, otu_clean)
# optional UCHIME Ref
if not args.uchime_ref:
uchime_out = otu_clean
else:
uchime_out = os.path.join(tmp, args.out + ".EE" + args.maxee + ".uchime.otus.fa")
# check if file is present, remove from previous run if it is.
if os.path.isfile(uchime_out):
os.remove(uchime_out)
# R. Edgar now says using largest DB is better for UCHIME, so use the one distributed with taxonomy
if args.uchime_ref in [
"ITS",
"16S",
"LSU",
"COI",
