def main(args):
if not args.bam:
ps.log("Please provide bam file")
quit()
else:
ps.filecheck(args.bam)
if not args.ref:
ps.log("Please provide reference")
quit()
else:
ps.filecheck(args.ref)
fasta = ps.fasta(args.ref)
if not args.prefix:
ps.log("Please provide prefix")
quit()
if args.gff and args.bed:
ps.log(
"Please provide either a GFF file or BED file but not both...Exiting!"
)
quit()
if args.gff:
if not args.gffkey:
ps.log(
"Please provide the key to look for in the GFF file...Exiting!"
)
quit()
else:
ps.filecheck(args.gff)
if args.bed: ps.filecheck(args.bed)
cov_json = "%s.cov.json" % args.prefix
stats_json = "%s.bam_stats.json" % args.prefix
region_json = "%s.regions.cov.json" % args.prefix
stats = {}
bamqc = ps.qc_bam(args.bam, args.ref)
for s in fasta.fa_dict:
cov_plot = "%s.%s.cov.png" % (args.prefix, s)
bamqc.plot_cov(s, cov_plot)
bamqc.save_cov(cov_json)
stats["pct_reads_mapped"] = bamqc.pct_reads_mapped
stats["med_dp"] = bamqc.med_dp
region_cov = {}
if args.gff:
region_cov = bamqc.gff_cov(args.gff, args.gffkey)
elif args.bed:
region_cov = bamqc.bed_cov(args.bed)
json.dump(stats, open(stats_json, "w"))
json.dump(region_cov, open(region_json, "w"))
def main(args):
if not args.bam:
ps.log("Please provide bam file")
quit()
else:
ps.filecheck(args.bam)
if not args.ref:
ps.log("Please provide reference")
quit()
else:
ps.filecheck(args.ref)
fasta = ps.fasta(args.ref)
if not args.prefix:
ps.log("Please provide prefix")
quit()
if args.gff and args.bed:
ps.log("Please provide either a GFF file or BED file but not both...Exiting!")
quit()
if args.gff:
if not args.gffkey:
ps.log("Please provide the key to look for in the GFF file...Exiting!")
quit()
else:
ps.filecheck(args.gff)
if args.bed: ps.filecheck(args.bed)
cov_json = "%s.cov.json" % args.prefix
stats_json = "%s.bam_stats.json" % args.prefix
region_json = "%s.regions.cov.json" % args.prefix
stats = {}
bamqc = ps.qc_bam(args.bam,args.ref)
for s in fasta.fa_dict:
cov_plot = "%s.%s.cov.png" % (args.prefix,s)
bamqc.plot_cov(s,cov_plot)
bamqc.save_cov(cov_json)
stats["pct_reads_mapped"] = bamqc.pct_reads_mapped
stats["med_dp"] = bamqc.med_dp
region_cov = {}
if args.gff:
region_cov = bamqc.gff_cov(args.gff,args.gffkey)
elif args.bed:
region_cov = bamqc.bed_cov(args.bed)
json.dump(stats,open(stats_json,"w"))
json.dump(region_cov,open(region_json,"w"))
def main(args):
ref = args.ref
r1 = args.r1
r2 = args.r2
prefix = args.prefix
threads = args.threads
stats_file = "%s.stats.json" % prefix
gc_file = "%s.gc_skew.json" % prefix
cov_file = "%s.regions.cov.json" % prefix
stats = OrderedDict()
fq = ps.fastq(prefix, ref, r1, r2, threads=threads)
fq_qc = fq.get_fastq_qc()
if args.centrifuge:
t1, t2 = fq_qc.run_centrifuge(args.centrifuge, False, threads)
stats["centrifuge_top_hit"] = t1
stats["centrifuge_top_hit_num_reads"] = t2
stats["mean_read_len"] = fq_qc.mean_read_len
stats["median_read_len"] = fq_qc.median_read_len
stats["read_num"] = fq_qc.read_num
bam = fq.illumina(mapper=args.mapper)
if not args.nobamstats:
bam_qc = bam.get_bam_qc()
stats["med_dp"] = bam_qc.med_dp
stats["pct_reads_mapped"] = bam_qc.pct_reads_mapped
stats["genome_cov_1"] = bam_qc.genome_cov[1]
stats["genome_cov_10"] = bam_qc.genome_cov[10]
fasta = ps.fasta(ref).fa_dict
for seq in fasta:
cov_png = "%s.%s.cov.png" % (prefix, seq)
bam_qc.plot_cov(seq, cov_png, primers=args.primers)
if args.bed_cov: bam_qc.save_cov(cov_file, args.bed_cov)
bam_qc.extract_gc_skew(gc_file)
variants = bam.gbcf(primers=args.primers,
chunk_size=args.window,
call_method=args.call_method)
bcfstats = variants.load_stats()
stats["hom_variants"] = bcfstats["PSC"][prefix]["nNonRefHom"]
stats["het_variants"] = bcfstats["PSC"][prefix]["nHets"]
stats["hom_ref"] = bcfstats["PSC"][prefix]["nRefHom"]
json.dump(stats, open(stats_file, "w"))
def main(args):
ref = args.ref
r1 = args.reads
prefix = args.prefix
threads = args.threads
stats_file = "%s.stats.json" % prefix
gc_file = "%s.gc_skew.json" % prefix
cov_file = "%s.regions.cov.json" % prefix
stats = OrderedDict()
fq = ps.fastq(prefix, ref, r1, threads=threads)
fq_qc = fq.get_fastq_qc()
stats["mean_read_len"] = fq_qc.mean_read_len
stats["median_read_len"] = fq_qc.median_read_len
stats["read_num"] = fq_qc.read_num
if args.centrifuge:
t1, t2 = fq_qc.run_centrifuge(args.centrifuge, False, threads)
stats["centrifuge_top_hit"] = t1
stats["centrifuge_top_hit_num_reads"] = t2
bam = fq.minION()
bam_qc = bam.get_bam_qc()
stats["med_dp"] = bam_qc.med_dp
stats["pct_reads_mapped"] = bam_qc.pct_reads_mapped
stats["genome_cov_1"] = bam_qc.genome_cov[1]
stats["genome_cov_10"] = bam_qc.genome_cov[10]
fasta = ps.fasta(ref).fa_dict
for seq in fasta:
cov_png = "%s.%s.cov.png" % (prefix, seq)
bam_qc.plot_cov(seq, cov_png, primers=args.primers)
bam_qc.extract_gc_skew(gc_file)
if args.bed_cov: bam_qc.save_cov(cov_file, args.bed_cov)
variants = bam.pileup2vcf(indels=False)
bcf = bam.gbcf(threads=threads,
primers=args.primers,
chunk_size=args.window)
bcf.generate_consensus(ref)
bcfstats = bcf.load_stats()
stats["hom_variants"] = bcfstats["PSC"][prefix]["nNonRefHom"]
stats["het_variants"] = bcfstats["PSC"][prefix]["nHets"]
stats["hom_ref"] = bcfstats["PSC"][prefix]["nRefHom"]
json.dump(stats, open(stats_file, "w"))
def main(args): ref = args.ref r1 = args.r1 r2 = args.r2 prefix = args.prefix threads = args.threads stats_file = "%s.stats.json" % prefix gc_file = "%s.gc_skew.json" % prefix cov_file = "%s.regions.cov.json" % prefix stats = OrderedDict() fq = ps.fastq(prefix,ref,r1,r2,threads=threads) fq_qc = fq.get_fastq_qc() if args.centrifuge: t1,t2 = fq_qc.run_centrifuge(args.centrifuge,False,threads) stats["centrifuge_top_hit"] = t1 stats["centrifuge_top_hit_num_reads"] = t2 stats["mean_read_len"] = fq_qc.mean_read_len stats["median_read_len"] = fq_qc.median_read_len stats["read_num"] = fq_qc.read_num bam = fq.illumina(mapper=args.mapper) if not args.nobamstats: bam_qc = bam.get_bam_qc() stats["med_dp"] = bam_qc.med_dp stats["pct_reads_mapped"] = bam_qc.pct_reads_mapped stats["genome_cov_1"] = bam_qc.genome_cov[1] stats["genome_cov_10"] = bam_qc.genome_cov[10] fasta = ps.fasta(ref).fa_dict for seq in fasta: cov_png = "%s.%s.cov.png" % (prefix,seq) bam_qc.plot_cov(seq,cov_png,primers=args.primers) if args.bed_cov: bam_qc.save_cov(cov_file,args.bed_cov) bam_qc.extract_gc_skew(gc_file) variants = bam.gbcf(primers=args.primers,chunk_size=args.window,call_method=args.call_method) bcfstats = variants.load_stats() stats["hom_variants"] = bcfstats["PSC"][prefix]["nNonRefHom"] stats["het_variants"] = bcfstats["PSC"][prefix]["nHets"] stats["hom_ref"] = bcfstats["PSC"][prefix]["nRefHom"] json.dump(stats,open(stats_file,"w"))
args["fasta_db"] = sys.argv[5]
args["threads"] = sys.argv[6]
args["fq_report"] = ps.get_random_file()
args["log"] = ps.get_random_file()
cmd = "centrifuge -x %(centrifuge_db)s -1 %(r1)s -2 %(r2)s -S %(log)s --report-file %(fq_report)s -p %(threads)s" % args
ps.run_cmd(cmd)
best_ref = ""
best_score = 0
best_species = ""
best_species_score = 0
for l in open(args["fq_report"]):
row = l.rstrip().split("\t")
if row[4] == "numReads": continue
if row[2] == "leaf" and int(row[4]) > best_score:
best_ref = row[0]
best_score = int(row[4])
elif row[2] == "species" and int(row[4]) > best_species_score:
best_species = row[0]
best_species_score = int(row[4])
fasta = ps.fasta(args["fasta_db"]).fa_dict
open("%s.fa" % best_ref, "w").write(">%s\n%s\n" % (best_ref, fasta[best_ref]))
ps.rm_files([args["fq_report"], args["log"]])
json.dump(
{
"sample": args["prefix"],
"best_ref": best_ref,
"best_species": best_species
}, open("%(prefix)s.centrifuge.json" % args, "w"))
def main(args): fasta = ps.fasta(args.fasta) fasta.add_meta_data(args.data_file,args.outfile,args.delimiter)
def main(args): if args.bed: ps.split_bed(args.bed,args.size,reformat=args.reformat) else: fasta = ps.fasta(args.fasta) fasta.splitchr(args.size,reformat=args.reformat)
import sys
import pathogenseq as ps
infile = sys.argv[1]
bcf = ps.bcf(infile)
stats = bcf.load_stats()
#stats = {'PSC': {'barcode07_run1_batch1': {'nHets': 798,'nNonRefHom': 38,'nRefHom': 276198}}}
if len(sys.argv)>2:
genome_len = sum([len(x) for x in ps.fasta(sys.argv[2]).fa_dict.values()])
if len(sys.argv)>2:
print "sample\tnRefHom\tnNonRefHom\tnHets\tnMissing"
else:
print "sample\tnRefHom\tnNonRefHom\tnHets"
for sample in stats["PSC"]:
s = stats["PSC"][sample]
if len(sys.argv)>2:
tot_sum = s["nRefHom"]+s["nNonRefHom"]+s["nHets"]
print "%s\t%s\t%s\t%s\t%s" % (sample,s["nRefHom"],s["nNonRefHom"],s["nHets"],genome_len-tot_sum)
else:
print "%s\t%s\t%s\t%s" % (sample,s["nRefHom"],s["nNonRefHom"],s["nHets"])
args["r1"] = sys.argv[1]
args["r2"] = sys.argv[2]
args["prefix"] = sys.argv[3]
args["centrifuge_db"] = sys.argv[4]
args["fasta_db"] = sys.argv[5]
args["threads"] = sys.argv[6]
args["fq_report"] = ps.get_random_file()
args["log"] = ps.get_random_file()
cmd = "centrifuge -x %(centrifuge_db)s -1 %(r1)s -2 %(r2)s -S %(log)s --report-file %(fq_report)s -p %(threads)s" % args
ps.run_cmd(cmd)
best_ref = ""
best_score = 0
best_species = ""
best_species_score = 0
for l in open(args["fq_report"]):
row = l.rstrip().split("\t")
if row[4]=="numReads": continue
if row[2]=="leaf" and int(row[4])>best_score:
best_ref = row[0]
best_score = int(row[4])
elif row[2]=="species" and int(row[4])>best_species_score:
best_species = row[0]
best_species_score = int(row[4])
fasta = ps.fasta(args["fasta_db"]).fa_dict
open("%s.fa" % best_ref,"w").write(">%s\n%s\n" % (best_ref,fasta[best_ref]))
ps.rm_files([args["fq_report"],args["log"]])
json.dump({"sample":args["prefix"],"best_ref":best_ref,"best_species":best_species},open("%(prefix)s.centrifuge.json" % args,"w"))
def main(args):
fasta = ps.fasta(args.fasta)
fasta.add_meta_data(args.data_file, args.outfile, args.delimiter)
#! /usr/bin/env python
import sys
import pathogenseq as ps
import json
infile = sys.argv[1]
ref = sys.argv[2]
outfile = sys.argv[3]
bcf = ps.bcf(infile)
stats = bcf.load_stats(convert=True, ref=ref)
genome_len = sum([len(x) for x in ps.fasta(ref).fa_dict.values()])
print("sample\tnRefHom\tnNonRefHom\tnHets\tnMissing")
for sample in stats["PSC"]:
s = stats["PSC"][sample]
s["id"] = sample
tot_sum = s["nRefHom"] + s["nNonRefHom"] + s["nHets"]
s["missing"] = genome_len - tot_sum
print("%s\t%s\t%s\t%s\t%s" %
(sample, s["nRefHom"], s["nNonRefHom"], s["nHets"], s["missing"]))
json.dump(s, open(outfile, "w"))
#! /usr/bin/env python
import sys
import pathogenseq as ps
import json
infile = sys.argv[1]
ref = sys.argv[2]
outfile = sys.argv[3]
bcf = ps.bcf(infile)
stats = bcf.load_stats(convert=True,ref=ref)
genome_len = sum([len(x) for x in ps.fasta(ref).fa_dict.values()])
print("sample\tnRefHom\tnNonRefHom\tnHets\tnMissing")
for sample in stats["PSC"]:
s = stats["PSC"][sample]
s["id"] = sample
tot_sum = s["nRefHom"]+s["nNonRefHom"]+s["nHets"]
s["missing"] = genome_len-tot_sum
print("%s\t%s\t%s\t%s\t%s" % (sample,s["nRefHom"],s["nNonRefHom"],s["nHets"],s["missing"]))
json.dump(s,open(outfile,"w"))