def main_lineage(args):
conf_file = pp.filecheck(tbp._ROOT + "/../" + args.db + ".config.json")
conf = json.load(open(conf_file))
pp.filecheck(args.bcf)
bcf = pp.bcf(args.bcf)
mutations = bcf.get_bed_gt(conf["barcode"], conf["ref"])
results = {}
results["barcode"] = pp.barcode(mutations, conf["barcode"])
tbp.barcode2lineage(results)
if args.prefix:
outfile = "%s.lineage.%s" % (args.prefix, args.outfmt)
O = open(outfile, "w")
if args.outfmt == "json":
json.dump(results["lineage"], O)
elif args.outfmt == "txt":
O.write(tbp.text.lineagejson2text(results["lineage"]))
O.close()
def main_profile(args):
if pp.nofolder(args.dir):
os.mkdir(args.dir)
conf = get_conf_dict(sys.base_prefix + "/share/covidprofiler/%s" % args.db)
### Setup prefix for files ###
files_prefix = args.dir + "/" + args.prefix
if args.fasta:
if args.read1 or args.read2:
sys.stderr.write(
"Please use --fasta or --read1/2 but not both... Exiting!\n")
quit()
fasta_obj = pp.fasta(args.fasta)
wg_vcf_obj = pp.vcf(
fasta_obj.get_ref_variants(conf["ref"],
prefix=args.prefix,
file_prefix=files_prefix))
else:
if not args.read1:
sys.stderr.write(
"Please provide assembly using --fasta or at least one read file using --read1... Exiting!\n"
)
quit()
### Create bam file if fastq has been supplied ###
if args.read1 and args.read2 and args.no_trim:
# Paired + no trimming
fastq_obj = pp.fastq(args.read1, args.read2)
elif args.read1 and args.read2 and not args.no_trim:
# Paired + trimming
untrimmed_fastq_obj = pp.fastq(args.read1, args.read2)
fastq_obj = untrimmed_fastq_obj.trim(files_prefix,
threads=args.threads)
elif args.read1 and not args.read2 and args.no_trim:
# Unpaired + trimming
fastq_obj = pp.fastq(args.read1, args.read2)
elif args.read1 and not args.read2 and not args.no_trim:
# Unpaired + trimming
untrimmed_fastq_obj = pp.fastq(args.read1)
fastq_obj = untrimmed_fastq_obj.trim(files_prefix,
threads=args.threads)
bam_obj = fastq_obj.map_to_ref(ref_file=conf["ref"],
prefix=files_prefix,
sample_name=args.prefix,
aligner=args.mapper,
platform=args.platform,
threads=args.threads)
wg_vcf_obj = bam_obj.call_variants(conf["ref"],
args.caller,
remove_missing=True)
cp.vcf2consensus(bam_obj.bam_file, wg_vcf_obj.filename, conf["ref"],
wg_vcf_obj.samples[0],
wg_vcf_obj.prefix + ".consensus.fasta")
if not args.no_trim:
pp.run_cmd("rm -f %s" % " ".join(fastq_obj.files))
refseq = pp.fasta(conf["ref"]).fa_dict
refseqname = list(refseq.keys())[0]
results = {}
barcode_mutations = wg_vcf_obj.get_bed_gt(conf["barcode"], conf["ref"])
barcode = pp.barcode(barcode_mutations, conf["barcode"])
clade = ";".join(sorted([d["annotation"] for d in barcode]))
sys.stdout.write("%s\t%s\n" % (args.prefix, clade))
results["clade"] = clade
variant_data = cp.get_variant_data(wg_vcf_obj.filename, conf["ref"],
conf["gff"], conf["proteins"])
results["variants"] = variant_data
json.dump(results, open("%s.results.json" % files_prefix, "w"))
def profile_vcf(filename, conf):
params = conf.copy()
params["tmpvcf"] = pp.get_random_file(extension=".vcf.gz")
params["tmpcsq"] = pp.get_random_file(extension=".vcf.gz")
params["filename"] = filename
params["tmphdr"] = pp.get_random_file()
params["tmptxt"] = pp.get_random_file()
l = ""
for l in pp.cmd_out(
"bcftools view %(filename)s -h | grep \"^##FORMAT=<ID=AD\"" %
params):
pass
AD_found = False if l == "" else True
if AD_found == False:
open(params["tmphdr"], "w").write(
"##FORMAT=<ID=AD,Number=R,Type=Integer,Description=\"Allelic depths\">\n"
)
pp.run_cmd(
"bcftools query -f '%%CHROM\\t%%POS\\t%%REF\\t%%ALT\\t.[\\t0,100]\\n' %(filename)s > %(tmptxt)s"
% params)
pp.run_cmd("bgzip %(tmptxt)s" % params)
pp.run_cmd("tabix -s 1 -b 2 -p vcf %(tmptxt)s.gz" % params)
pp.run_cmd(
"bcftools view -a %(filename)s | bcftools annotate -a %(tmptxt)s.gz -c CHROM,POS,REF,ALT,-,FMT/AD -h %(tmphdr)s -Oz -o %(tmpvcf)s"
% params)
else:
pp.run_cmd("bcftools view -a %(filename)s -Oz -o %(tmpvcf)s" % params)
pp.run_cmd(
"bcftools view -T %(bed)s %(tmpvcf)s | bcftools csq -f %(ref)s -g %(gff)s -Oz -o %(tmpcsq)s -p a"
% params)
csq_bcf_obj = pp.bcf(params["tmpcsq"])
csq = csq_bcf_obj.load_csq(ann_file=conf["ann"])
results = {
"variants": [],
"missing_pos": [],
"qc": {
"pct_reads_mapped": "NA",
"num_reads_mapped": "NA"
}
}
for sample in csq:
results["variants"] = csq[sample]
all_bcf_obj = pp.bcf(params["tmpvcf"])
mutations = all_bcf_obj.get_bed_gt(conf["barcode"], conf["ref"])
if "C" in mutations["Chromosome"][325505] and mutations["Chromosome"][
325505]["C"] == 50:
mutations["Chromosome"][325505] = {"T": 25}
if "G" in mutations["Chromosome"][599868] and mutations["Chromosome"][
599868]["G"] == 50:
mutations["Chromosome"][599868] = {"A": 25}
if "C" in mutations["Chromosome"][931123] and mutations["Chromosome"][
931123]["C"] == 50:
mutations["Chromosome"][931123] = {"T": 25}
if "T" in mutations["Chromosome"][1759252] and mutations["Chromosome"][
1759252]["T"] == 50:
mutations["Chromosome"][1759252] = {"G": 25}
json.dump(mutations, open("dump.json", "w"))
barcode_mutations = pp.barcode(mutations, conf["barcode"])
results["barcode"] = barcode_mutations
results = pp.db_compare(db_file=conf["json_db"], mutations=results)
bed_regions = pp.load_bed(conf["bed"], [4], 4)
missing_regions = {gene: "NA" for gene in bed_regions}
results["missing_regions"] = missing_regions
if AD_found:
pp.run_cmd("rm %(tmpcsq)s" % params)
else:
pp.run_cmd("rm %(tmpcsq)s %(tmphdr)s %(tmptxt)s*" % params)
return results