def main():
args = parse_args()
utility.add_tmp_dir(args)
utility.check_input(args)
utility.check_dependencies(['prodigal', 'hmmsearch', 'blastp', 'blastn'])
utility.check_database(args)
print("\n## Calling genes with Prodigal")
utility.run_prodigal(args['fna'], args['tmp_dir'])
print(" all genes: %s/genes.[ffn|faa]" % args['tmp_dir'])
print("\n## Identifying PhyEco phylogenetic marker genes with HMMER")
utility.run_hmmsearch(args['db'], args['tmp_dir'], args['tmp_dir'],
args['threads'])
extract_homologs(args['tmp_dir'])
print(" hmm results: %s/phyeco.hmmsearch" % args['tmp_dir'])
print(" marker genes: %s/markers" % args['tmp_dir'])
print(
"\n## Performing pairwise BLAST alignment of marker genes against database"
)
align_homologs(args['db'], args['tmp_dir'], args['seq_type'],
args['threads'])
print(" blast results: %s/alns" % args['tmp_dir'])
print("\n## Finding taxonomic outliers")
flagged = flag_contigs(args['db'], args['tmp_dir'], args)
out = '%s/flagged_contigs' % args['tmp_dir']
print(" flagged contigs: %s" % out)
with open(out, 'w') as f:
for contig in flagged:
f.write(contig + '\n')
def main():
args = fetch_args()
utility.add_tmp_dir(args)
utility.check_input(args)
utility.check_dependencies(['blastn'])
utility.check_database(args)
tmp_dir = '%s/%s' % (args['out'], args['program'])
if not os.path.exists(args['tmp_dir']):
os.makedirs(args['tmp_dir'])
print("\n## Searching database with BLASTN")
for target in ['hg38', 'phix']:
db = '%s/known-contam/%s/%s' % (args['db'], target, target)
out = '%s/%s.m8' % (args['tmp_dir'], target)
run_blastn(args['fna'], db, out, args['threads'], args['qcov'],
args['pid'], args['evalue'])
print("\n## Identifying contigs with hits to db")
flagged = set([])
for target in ['hg38', 'phix']:
out = '%s/%s.m8' % (args['tmp_dir'], target)
for r in utility.parse_blast(out):
flagged.add(r['qname'])
flagged = list(flagged)
out = '%s/flagged_contigs' % args['tmp_dir']
print(" flagged contigs: %s" % out)
with open(out, 'w') as f:
for contig in flagged:
f.write(contig + '\n')
def main():
args = fetch_args()
utility.add_tmp_dir(args)
utility.check_input(args)
utility.check_database(args)
print "\n## Computing mean genome-wide GC content"
contigs = {}
for id, seq in utility.parse_fasta(args['fna']):
contig = Contig()
contig.id = id
contig.seq = str(seq)
contig.gc = compute_gc(seq)
contigs[id] = contig
mean = np.mean([c.gc for c in contigs.values()])
std = np.std([c.gc for c in contigs.values()])
print "\n## Computing per-contig deviation from mean"
for contig in contigs.values():
contig.values = {}
contig.values['delta'] = abs(contig.gc - mean)
contig.values['percent'] = 100 * abs(contig.gc - mean)/mean
contig.values['z-score'] = abs(contig.gc - mean)/std
print "\n## Identifying outlier contigs"
flagged = []
for contig in contigs.values():
if contig.values['delta'] > args['cutoff']:
flagged.append(contig.id)
out = '%s/flagged_contigs' % args['tmp_dir']
print (" flagged contigs: %s" % out)
with open(out, 'w') as f:
for contig in flagged:
f.write(contig+'\n')
def main():
args = fetch_args()
utility.add_tmp_dir(args)
utility.check_input(args)
utility.check_database(args)
print("\n## Reading database info")
ref_taxonomy = read_ref_taxonomy(args['db'])
taxon_to_taxonomy = {}
for taxonomy in set(ref_taxonomy.values()):
for taxon in taxonomy.split('|'):
taxon_to_taxonomy[taxon] = taxonomy
min_pid = {'k': 57, 'p': 77, 'c': 82, 'o': 86, 'f': 87, 'g': 91, 's': 96}
if args['min_genes'] is not None:
args['min_genes'] = dict([(r, args['min_genes']) for r in ranks])
else:
args['min_genes'] = {
'k': 237,
'p': 44,
'c': 30,
'o': 24,
'f': 22,
'g': 20,
's': 19
}
print("\n## Calling genes with Prodigal")
utility.run_prodigal(args['fna'], args['tmp_dir'])
print(" all genes: %s/genes.[ffn|faa]" % args['tmp_dir'])
print(
"\n## Performing pairwise alignment of genes against MetaPhlan2 db of clade-specific genes"
)
utility.run_lastal(args['db'], args['tmp_dir'], args['threads'])
print(" alignments: %s/genes.m8" % args['tmp_dir'])
print("\n## Finding top hits to db")
genes = {}
for aln in utility.parse_last(args['tmp_dir'] + '/genes.m8'):
# clade exclusion
ref_taxa = ref_taxonomy[aln['tid']].split('|')
if (args['exclude_clades'] and any(
[taxon in ref_taxa
for taxon in args['exclude_clades'].split(',')])):
continue
# initialize gene
if aln['qid'] not in genes:
genes[aln['qid']] = Gene()
genes[aln['qid']].id = aln['qid']
genes[aln['qid']].contig_id = aln['qid'].rsplit('_', 1)[0]
# get top alignments
if genes[aln['qid']].aln is None:
genes[aln['qid']].aln = aln
genes[aln['qid']].ref_taxa = ref_taxa
elif float(aln['score']) > float(genes[aln['qid']].aln['score']):
genes[aln['qid']].ref_taxa = ref_taxa
print(" %s genes with a database hit" % len(genes))
print("\n## Classifying genes at each taxonomic rank")
counts = {}
for gene in genes.values():
for ref_taxon in gene.ref_taxa:
rank = ref_taxon.split('__')[0]
if rank not in counts: counts[rank] = 0
if rank == 't':
continue
elif float(gene.aln['pid']) < min_pid[rank]:
continue
elif gene.aln['qcov'] < 0.4:
continue
elif gene.aln['tcov'] < 0.4:
continue
gene.taxa[rank] = ref_taxon
counts[rank] += 1
for rank in ranks:
print(" %s: %s classified genes" % (rank_names[rank], counts[rank]))
print("\n## Taxonomically classifying contigs")
contigs = {}
for id, seq in utility.parse_fasta(args['fna']):
contigs[id] = Contig()
contigs[id].id = id
contigs[id].length = len(seq)
# aggregate hits by contig
for gene in genes.values():
contigs[gene.contig_id].genes.append(gene)
# classify contigs at each level
for contig in contigs.values():
contig.classify()
# summarize
counts = {}
for contig in contigs.values():
for rank, taxon in contig.cons_taxa.items():
if rank not in counts:
counts[rank] = 0
if taxon is not None:
counts[rank] += 1
print(" total contigs: %s" % len(contigs))
for rank in ranks:
print(" %s: %s classified contigs" %
(rank_names[rank], counts[rank]))
print("\n## Taxonomically classifying genome")
bin = Bin()
bin.classify(contigs, args['min_bin_fract'], args['min_contig_fract'],
args['min_gene_fract'], args['min_genes'],
args['lowest_rank'])
print(" consensus taxon: %s" % bin.cons_taxon)
print("\n## Identifying taxonomically discordant contigs")
if bin.cons_taxon is not None:
bin.rank_index = taxon_to_taxonomy[bin.cons_taxon].split('|').index(
bin.cons_taxon)
bin.taxonomy = taxon_to_taxonomy[bin.cons_taxon].split(
'|')[0:bin.rank_index + 1]
flag_contigs(contigs, bin)
flagged = []
for contig in contigs.values():
if contig.flagged:
flagged.append(contig.id)
out = '%s/flagged_contigs' % args['tmp_dir']
print(" flagged contigs: %s" % out)
with open(out, 'w') as f:
for contig in flagged:
f.write(contig + '\n')
def main():
args = fetch_args()
utility.add_tmp_dir(args)
utility.check_input(args)
utility.check_dependencies(['mash'])
if not os.path.exists(args['mash_sketch']):
sys.exit("\nError: mash sketch '%s' not found\n" % args['mash_sketch'])
print("\n## Finding conspecific genomes in database")
run_mash(args['mash_sketch'], args['fna'], args['tmp_dir'],
args['threads'])
genomes = find_conspecific(args['tmp_dir'], args['mash_dist'],
args['exclude'])
print(" %s genomes within %s mash-dist" %
(len(genomes), args['mash_dist']))
out = '%s/conspecific.list' % args['tmp_dir']
with open(out, 'w') as f:
f.write('genome_id\tmash_dist\n')
for genome_id, mash_dist in genomes:
f.write(genome_id + '\t' + str(mash_dist) + '\n')
print(" list of genomes: %s" % (out))
print(" mash output: %s/mash.dist" % args['tmp_dir'])
if len(genomes) < args['min_genomes']:
sys.exit("\nError: insufficient number of conspecific genomes\n")
if len(genomes) > args['max_genomes']:
print("\n## Selecting top %s most-similar genomes" %
args['max_genomes'])
genomes = genomes[0:args['max_genomes']]
out = '%s/conspecific_subset.list' % args['tmp_dir']
with open(out, 'w') as f:
f.write('genome_id\tmash_dist\n')
for genome_id, mash_dist in genomes:
f.write(genome_id + '\t' + str(mash_dist) + '\n')
print(" list of genomes: %s" % (out))
print(
"\n## Performing pairwise alignment of contigs in bin to database genomes"
)
alignments = align_contigs(args, genomes)
num_alns = sum([len(_.split('\n')) for _ in alignments])
print(" total alignments: %s" % num_alns)
print("\n## Summarizing alignments")
contigs = find_contig_targets(args, genomes, alignments)
out = '%s/contig_hits.tsv' % args['tmp_dir']
with open(out, 'w') as f:
f.write('contig_id\tlength\talignment_rate\n')
for contig, values in contigs.items():
row = [
contig,
str(values['len']),
'%s/%s' % (values['hits'], len(genomes))
]
f.write('\t'.join(row) + '\n')
print(" contig features: %s" % out)
print("\n## Identifying contigs with no conspecific alignments")
flagged_contigs = flag_contigs(args, contigs)
flagged_length = round(
sum([contigs[id]['len'] for id in flagged_contigs]) / 1000.0, 2)
print(" %s flagged contigs, %s Kbp" %
(len(flagged_contigs), flagged_length))
out = '%s/flagged_contigs' % args['tmp_dir']
with open(out, 'w') as f:
for contig in flagged_contigs:
f.write(contig + '\n')
print(" flagged contigs: %s" % out)
def main():
args = fetch_args()
utility.add_tmp_dir(args)
utility.check_input(args)
utility.check_dependencies(['blastn'])
utility.check_database(args)
print "\n## Counting tetranucleotides"
# init data
kmer_counts = init_kmers()
contigs = {}
for rec in Bio.SeqIO.parse(args['fna'], 'fasta'):
contig = Contig()
contig.id = rec.id
contig.seq = str(rec.seq)
contig.kmers = kmer_counts.copy()
contigs[rec.id] = contig
# count kmers
for contig in contigs.values():
start, stop, step = 0, 4, 1
while stop <= len(contig.seq):
kmer_fwd = contig.seq[start:stop]
kmer_rev = str(Bio.Seq.Seq(kmer_fwd).reverse_complement())
if kmer_fwd in kmer_counts:
contigs[rec.id].kmers[kmer_fwd] += 1
elif kmer_rev in kmer_counts:
contigs[rec.id].kmers[kmer_rev] += 1
start += step
stop += step
print "\n## Normalizing counts"
for contig in contigs.values():
total = float(sum(contig.kmers.values()))
for kmer, count in contig.kmers.items():
if total > 0:
contig.kmers[kmer] = 100*count/total
else:
contig.kmers[kmer] = 0.00
print "\n## Performing PCA"
df = pd.DataFrame(dict([(c.id, c.kmers) for c in contigs.values()]))
pca = PCA(n_components=1)
pca.fit(df)
pc1 = pca.components_[0]
print "\n## Computing per-contig deviation from the mean along the first principal component"
mean_pc = np.mean(pc1)
std_pc = np.std(pc1)
for contig_id, contig_pc in zip(list(df.columns), pc1):
contigs[contig_id].pc = contig_pc
contigs[contig_id].values = {}
contigs[contig_id].values['zscore'] = abs(contig_pc - mean_pc)/std_pc if std_pc > 0 else 0.0
contigs[contig_id].values['delta'] = abs(contig_pc - mean_pc)
contigs[contig_id].values['percent'] = 100*abs(contig_pc - mean_pc)/mean_pc
print "\n## Identifying outlier contigs"
flagged = []
for contig in contigs.values():
if contig.values['delta'] > args['cutoff']:
flagged.append(contig.id)
out = '%s/flagged_contigs' % args['tmp_dir']
print (" flagged contigs: %s" % out)
with open(out, 'w') as f:
for contig in flagged:
f.write(contig+'\n')