def main(args):
utilities.add_tmp_dir(args)
utilities.check_input(args)
utilities.check_dependencies(["blastn"])
utilities.check_database(args)
utilities.add_tmp_dir(args)
print("\u001b[1m" + "• Searching database with BLASTN" + "\u001b[0m")
for target in ["hg38", "phix"]:
db = f"{args['db']}/known-contam/{target}/{target}"
out = f"{args['tmp_dir']}/{target}.m8"
run_blastn(
args["fna"],
db,
out,
args["threads"],
args["qcov"],
args["pid"],
args["evalue"],
)
print("\u001b[1m" + "\n• Identifying contigs with hits to database" + "\u001b[0m")
flagged = set([])
for target in ["hg38", "phix"]:
out = f"{args['tmp_dir']}/{target}.m8"
for r in utilities.parse_blast(out):
flagged.add(r["qname"])
flagged = list(flagged)
out = f"{args['tmp_dir']}/flagged_contigs"
print(f" {len(flagged)} flagged contigs: {out}")
with open(out, "w") as f:
for contig in flagged:
f.write(contig + "\n")
def main(args):
utilities.add_tmp_dir(args)
utilities.check_input(args)
utilities.check_dependencies(["prodigal", "hmmsearch", "blastp", "blastn"])
utilities.check_database(args)
print("\u001b[1m" + "• Calling genes with Prodigal" + "\u001b[0m")
utilities.run_prodigal(args["fna"], args["tmp_dir"])
print(f" all genes: {args['tmp_dir']}/genes.[ffn|faa]")
print("\u001b[1m" +
"\n• Identifying PhyEco phylogenetic marker genes with HMMER" +
"\u001b[0m")
utilities.run_hmmsearch(args["db"], args["tmp_dir"], args["tmp_dir"],
args["threads"])
extract_homologs(args["tmp_dir"])
print(f" hmm results: {args['tmp_dir']}/phyeco.hmmsearch")
print(f" marker genes: {args['tmp_dir']}/markers")
print(
"\u001b[1m" +
"\n• Performing pairwise BLAST alignment of marker genes against database"
+ "\u001b[0m")
align_homologs(args["db"], args["tmp_dir"], args["seq_type"],
args["threads"])
print(f" blast results: {args['tmp_dir']}/alns")
print("\u001b[1m" + "\n• Finding taxonomic outliers" + "\u001b[0m")
flagged = flag_contigs(args["db"], args["tmp_dir"], args)
out = f"{args['tmp_dir']}/flagged_contigs"
print(f" {len(flagged)} flagged contigs: {out}")
with open(out, "w") as f:
for contig in flagged:
f.write(contig + "\n")
def main(args):
utilities.add_tmp_dir(args)
utilities.check_input(args)
utilities.check_dependencies(["coverm"])
print("\u001b[1m" + "• Computing contig coverage" + "\u001b[0m")
utilities.run_coverm(args["bams"], args["tmp_dir"], args["threads"])
coverage_df = pd.read_csv(f"{args['tmp_dir']}/coverage.tsv",
sep="\t",
index_col=0)
contig_id_list = []
contig_length_list = []
for id, seq in utilities.parse_fasta(args["fna"]):
contig_id_list.append(id)
contig_length_list.append(len(seq))
contig_coverage_df = coverage_df.loc[contig_id_list]
largest_mean_coverage_sample = contig_coverage_df.mean(axis=0).idxmax()
if contig_coverage_df.shape[1] > 1:
print(
"\u001b[1m" +
f"\n• Sample being used for outlier detection: {largest_mean_coverage_sample.split()[0]}"
+ "\u001b[0m")
contig_coverage_df = contig_coverage_df.loc[:,
largest_mean_coverage_sample]
if contig_coverage_df.mean() < 1:
sys.exit(
"\nError: The average coverage is less than 1 in all the supplied BAM files"
)
if args["weighted_mean"]:
print(
"\u001b[1m" +
"\n• Computing per-contig deviation from the weighted mean coverage"
+ "\u001b[0m")
reference = np.average(contig_coverage_df.values,
weights=contig_length_list)
else:
print("\u001b[1m" +
"\n• Computing per-contig deviation from the mean coverage" +
"\u001b[0m")
reference = contig_coverage_df.mean()
outliers = ((contig_coverage_df / reference) >= args["max_deviation"]) | (
(contig_coverage_df / reference) <= 1 / args["max_deviation"])
print("\u001b[1m" + "\n• Identifying outlier contigs" + "\u001b[0m")
flagged = contig_coverage_df.loc[outliers].index.tolist()
out = f"{args['tmp_dir']}/flagged_contigs"
print(f" {len(flagged)} flagged contigs: {out}")
with open(out, "w") as f:
for contig in flagged:
f.write(contig + "\n")
def main(args):
utilities.add_tmp_dir(args)
utilities.check_input(args)
if args["weighted_mean"]:
print("\u001b[1m" + "• Computing weighted mean contig GC content" +
"\u001b[0m")
else:
print("\u001b[1m" + "• Computing mean contig GC content" + "\u001b[0m")
contigs = {}
contig_length_list = []
for id, seq in utilities.parse_fasta(args["fna"]):
contig = Contig()
contig.id = id
contig.seq = str(seq)
contig.gc = round(SeqUtils.GC(seq), 2)
contigs[id] = contig
contig_length_list.append(len(seq))
if args["weighted_mean"]:
print("\u001b[1m" +
"\n• Computing per-contig deviation from weighted mean" +
"\u001b[0m")
reference = np.average([c.gc for c in contigs.values()],
weights=contig_length_list)
else:
print("\u001b[1m" + "\n• Computing per-contig deviation from mean" +
"\u001b[0m")
reference = np.average([c.gc for c in contigs.values()])
for contig in contigs.values():
contig.values = {}
contig.values["delta"] = abs(contig.gc - reference)
print("\u001b[1m" + "\n• Identifying outlier contigs" + "\u001b[0m")
flagged = [
contig.id for contig in contigs.values()
if contig.values["delta"] > args["cutoff"]
]
out = f"{args['tmp_dir']}/flagged_contigs"
print(f" {len(flagged)} flagged contigs: {out}")
with open(out, "w") as f:
for contig in flagged:
f.write(contig + "\n")
def main(args):
utilities.check_input(args)
print("\u001b[1m" + "• Reading genome bin" + "\u001b[0m")
bin = {id: seq for id, seq in utilities.parse_fasta(args["fna"])}
bin_length = round(sum(len(_) for _ in bin.values()) / 1000, 2)
print(f" genome length: {len(bin)} contigs, {bin_length} Kbp")
print("\u001b[1m" + "\n• Reading flagged contigs" + "\u001b[0m")
flagged_contigs = []
programs = [
"phylo-markers",
"clade-markers",
"conspecific",
"tetra-freq",
"gc-content",
"coverage",
"known-contam",
]
for program in programs:
path = f"{args['out']}/{program}/flagged_contigs"
if not os.path.exists(path):
print(f" {program}: no output file found")
else:
contigs = [_.rstrip() for _ in open(path)]
bases = round(sum(len(bin[id]) for id in contigs) / 1000, 2)
flagged_contigs += contigs
print(f" {program}: {len(contigs)} contigs, {bases} Kbp")
flagged_contigs = list(set(flagged_contigs))
flagged_length = round(
sum(len(bin[id]) for id in flagged_contigs) / 1000, 2)
print("\u001b[1m" + "\n• Removing flagged contigs" + "\u001b[0m")
clean = bin.copy()
for id in flagged_contigs:
del clean[id]
clean_length = round(sum(len(_) for _ in clean.values()) / 1000, 2)
print(f" removed: {len(flagged_contigs)} contigs, {flagged_length} Kbp")
print(f" remains: {len(clean)} contigs, {clean_length} Kbp")
with open(args['out_fna'], "w") as f:
for id, seq in clean.items():
f.write(">" + id + "\n" + textwrap.fill(seq, 70) + "\n")
print(f" cleaned bin: {args['out_fna']}")
def main(args):
utilities.add_tmp_dir(args)
utilities.check_input(args)
utilities.check_dependencies(["mash"])
if not os.path.exists(args["mash_sketch"]):
sys.exit(f"\nError: mash sketch '{args['mash_sketch']}' not found\n")
print("\u001b[1m" + "• Finding conspecific genomes in database" +
"\u001b[0m")
run_mash(args["mash_sketch"], args["fna"], args["tmp_dir"],
args["threads"])
genomes = find_conspecific(args["tmp_dir"], args["mash_dist"],
args["exclude"])
print(f" {len(genomes)} genomes within {args['mash_dist']} mash-dist")
out = f"{args['tmp_dir']}/conspecific.list"
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(f" list of genomes: {out}")
print(f" mash output: {args['tmp_dir']}/mash.dist")
if len(genomes) < args["min_genomes"]:
sys.exit("\nError: insufficient number of conspecific genomes\n")
if len(genomes) > args["max_genomes"]:
print("\u001b[1m" +
f"\n• Selecting top {args['max_genomes']} most-similar genomes" +
"\u001b[0m")
genomes = genomes[0:args["max_genomes"]]
out = f"{args['tmp_dir']}/conspecific_subset.list"
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(f" list of genomes: {out}")
print(
"\u001b[1m" +
"\n• Performing pairwise alignment of contigs in bin to database genomes"
+ "\u001b[0m")
alignments = align_contigs(args, genomes)
num_alns = sum(len(_.split("\n")) for _ in alignments)
print(f" total alignments: {num_alns}")
print("\u001b[1m" + "\n• Summarizing alignments" + "\u001b[0m")
contigs = find_contig_targets(args, genomes, alignments)
out = f"{args['tmp_dir']}/contig_hits.tsv"
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"]), f"{values['hits']}/{len(genomes)}"
]
f.write("\t".join(row) + "\n")
print(f" contig features: {out}")
print("\u001b[1m" +
"\n• Identifying contigs with no conspecific alignments" +
"\u001b[0m")
flagged = flag_contigs(args, contigs)
out = f"{args['tmp_dir']}/flagged_contigs"
with open(out, "w") as f:
for contig in flagged:
f.write(contig + "\n")
print(f" {len(flagged)} flagged contigs: {out}")
def main(args):
utilities.add_tmp_dir(args)
utilities.check_input(args)
utilities.check_database(args)
print("\u001b[1m" + "• Reading database info" + "\u001b[0m")
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("\u001b[1m" + "\n• Calling genes with Prodigal" + "\u001b[0m")
utilities.run_prodigal(args["fna"], args["tmp_dir"])
print(f" all genes: {args['tmp_dir']}/genes.[ffn|faa]")
print(
"\u001b[1m"
+ "\n• Performing pairwise alignment of genes against MetaPhlan2 database of clade-specific genes"
+ "\u001b[0m"
)
utilities.run_lastal(args["db"], args["tmp_dir"], args["threads"])
print(f" alignments: {args['tmp_dir']}/genes.m8")
print("\u001b[1m" + "\n• Finding top hits to database" + "\u001b[0m")
genes = {}
for aln in utilities.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"]
):
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("\u001b[1m" + "\n• Classifying genes at each taxonomic rank" + "\u001b[0m")
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(f" {rank_names[rank]}: {counts[rank]} classified genes")
print("\u001b[1m" + "\n• Taxonomically classifying contigs" + "\u001b[0m")
contigs = {}
for id, seq in utilities.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(f" {rank_names[rank]}: {counts[rank]} classified contigs")
print("\u001b[1m" + "\n• Taxonomically classifying genome" + "\u001b[0m")
bin = Bin()
bin.classify(
contigs,
args["min_bin_fract"],
args["min_contig_fract"],
args["min_gene_fract"],
args["min_genes"],
args["lowest_rank"],
)
print(f" consensus taxon: {bin.cons_taxon}")
print("\u001b[1m" + "\n• Identifying taxonomically discordant contigs" + "\u001b[0m")
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 = [contig.id for contig in contigs.values() if contig.flagged]
out = f"{args['tmp_dir']}/flagged_contigs"
print(f" {len(flagged)} flagged contigs: {out}")
with open(out, "w") as f:
for contig in flagged:
f.write(contig + "\n")
def main(args):
utilities.add_tmp_dir(args)
utilities.check_input(args)
utilities.check_dependencies(["blastn"])
print("\u001b[1m" + "• Counting tetranucleotides" + "\u001b[0m")
# init data
contigs = {}
contig_length_list = []
for id, seq in utilities.parse_fasta(args["fna"]):
contig = Contig()
contig.id = id
contig.seq = str(seq)
contig.kmers = init_kmers()
contigs[id] = contig
contig_length_list.append(len(seq))
# count kmers
for contig in contigs.values():
for i in range(len(contig.seq) - 3):
kmer_fwd = contig.seq[i : i + 4]
if kmer_fwd in contig.kmers:
contig.kmers[kmer_fwd] += 1
else:
kmer_rev = utilities.reverse_complement(kmer_fwd)
contig.kmers[kmer_rev] += 1
print("\u001b[1m" + "\n• Normalizing counts" + "\u001b[0m")
for contig in contigs.values():
total = float(sum(contig.kmers.values()))
for kmer, count in contig.kmers.items():
contig.kmers[kmer] = 100 * count / total if total > 0 else 0.0
print("\u001b[1m" + "\n• Performing PCA" + "\u001b[0m")
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]
if args["weighted_mean"]:
print(
"\u001b[1m"
+ "\n• Computing per-contig deviation from the weighted mean along the first principal component"
+ "\u001b[0m"
)
reference_pc = np.average(pc1, weights=contig_length_list)
else:
print(
"\u001b[1m"
+ "\n• Computing per-contig deviation from the mean along the first principal component"
+ "\u001b[0m"
)
reference_pc = np.average(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["delta"] = abs(contig_pc - reference_pc)
print("\u001b[1m" + "\n• Identifying outlier contigs" + "\u001b[0m")
flagged = [
contig.id
for contig in contigs.values()
if contig.values["delta"] > args["cutoff"]
]
out = f"{args['tmp_dir']}/flagged_contigs"
print(f" {len(flagged)} flagged contigs: {out}")
with open(out, "w") as f:
for contig in flagged:
f.write(contig + "\n")
