def main(args):
ref = args.ref
r1 = args.r1
r2 = args.r2
prefix = args.prefix
threads = args.threads
stats = {}
fastqqc = ps.qc_fastq(prefix,r1,r2)
stats["fastq_mean_read_len"] = fastqqc.mean_read_len
stats["fastq_read_num"] = fastqqc.read_num
fastq = ps.fastq(prefix,ref,r1,r2,threads=threads)
fastq.illumina(mapper="bowtie2")
bam_file = "%s.bam" % prefix
bam = ps.bam(bam_file,prefix,ref)
bam.gbcf(vtype="snps",threads=threads,call_method=args.call_method)
bamqc = bam.get_bam_qc()
cov_plot = "%s.cov.png" % (prefix)
bamqc.plot_cov("Chromosome",cov_plot)
stats["bam_pct_reads_mapped"] = bamqc.pct_reads_mapped
stats["bam_med_dp"] = bamqc.med_dp
stats["bam_depth_10"] = bamqc.genome_cov[10]
stats["bam_depth_5"] = bamqc.genome_cov[5]
json.dump(stats,open("%s.stats.json" % prefix,"w"))
O = open("%s.log"%prefix,"w")
for x in ["fastq_mean_read_len","fastq_read_num","bam_pct_reads_mapped","bam_med_dp","bam_depth_5","bam_depth_10"]:
O.write("%s\t%s\n" % (x,stats[x]))
O.close()
def main(args):
if not args.prefix:
ps.log("Please specify prefix with -p")
quit(1)
if not args.ref:
ps.log("Please use --ref to provide a reference... Exiting",ext=T)
x= ps.fastq(args.prefix,args.ref,args.r1,args.r2,threads=args.threads)
x.illumina(mapper=args.mapper)
def main(args):
if not args.prefix:
ps.log("Please specify prefix with -p")
quit(1)
if not args.ref:
ps.log("Please use --ref to provide a reference... Exiting", ext=T)
x = ps.fastq(args.prefix, args.ref, args.r1, args.r2, threads=args.threads)
x.illumina(mapper=args.mapper)
def main(args):
if not args.prefix:
print "Please specify prefix with -p"
quit(1)
x = pathogenseq.fastq(args.prefix,
args.ref,
args.r1,
args.r2,
threads=args.threads)
x.illumina(mapper=args.mapper)
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"))
import argparse
import json
ref = sys.argv[1]
r1 = sys.argv[2]
r2 = sys.argv[3]
prefix = sys.argv[4]
threads = sys.argv[5]
stats = {}
fastqqc = ps.qc_fastq(prefix,r1,r2)
stats["fastq_mean_read_len"] = fastqqc.mean_read_len
stats["fastq_read_num"] = fastqqc.read_num
fastq = ps.fastq(prefix,ref,r1,r2,threads=threads)
fastq.illumina(mapper="minimap2")
bam_file = "%s.bam" % prefix
bam = ps.bam(bam_file,prefix,ref)
bam.gbcf(vtype="snps",threads=threads)
bamqc = bam.get_bam_qc()
cov_plot = "%s.cov.png" % (prefix)
bamqc.plot_cov("Chromosome",cov_plot)
stats["bam_pct_reads_mapped"] = bamqc.pct_reads_mapped
stats["bam_med_dp"] = bamqc.med_dp
stats["bam_depth_10"] = bamqc.genome_cov[10]
stats["bam_depth_5"] = bamqc.genome_cov[5]
prefix = sys.argv[4]
threads = sys.argv[5]
stats = {}
fastqqc = ps.qc_fastq(prefix, r1, r2, threads=threads)
stats["fastq_mean_read_len"] = fastqqc.mean_read_len
stats["fastq_read_num"] = fastqqc.read_num
fr1, fr2, tmp = fastqqc.run_centrifuge("/opt/storage2/jody/software/p+h+v",
mtb_tax, threads)
stats["centrifuge_top_hit"] = tmp[0]
stats["centrifuge_pct_reads"] = tmp[1]
newfastqqc = ps.qc_fastq(prefix, fr1, fr2, threads=threads)
fastq = ps.fastq(prefix, ref, fr1, fr2, threads=threads)
fastq.illumina(mapper="bowtie2")
bam_file = "%s.bam" % prefix
bam = ps.bam(bam_file, prefix, ref, threads=threads)
bam.gbcf(vtype="snps", threads=threads, call_method="low")
bamqc = bam.get_bam_qc()
cov_plot = "%s.cov.png" % (prefix)
bamqc.plot_cov("Chromosome", cov_plot)
stats["bam_pct_reads_mapped"] = bamqc.pct_reads_mapped
stats["bam_med_dp"] = bamqc.med_dp
stats["bam_depth_10"] = bamqc.genome_cov[10]
stats["bam_depth_5"] = bamqc.genome_cov[5]
threads = sys.argv[5]
stats = {}
fastqqc = ps.qc_fastq(prefix,r1,r2,threads=threads)
stats["fastq_mean_read_len"] = fastqqc.mean_read_len
stats["fastq_read_num"] = fastqqc.read_num
fr1,fr2,tmp = fastqqc.run_centrifuge("/opt/storage2/jody/software/p+h+v",mtb_tax,threads)
stats["centrifuge_top_hit"] = tmp[0]
stats["centrifuge_pct_reads"] = tmp[1]
newfastqqc = ps.qc_fastq(prefix,fr1,fr2,threads=threads)
fastq = ps.fastq(prefix,ref,fr1,fr2,threads=threads)
fastq.illumina(mapper="bowtie2")
bam_file = "%s.bam" % prefix
bam = ps.bam(bam_file,prefix,ref,threads=threads)
bam.gbcf(vtype="snps",threads=threads,call_method="low")
bamqc = bam.get_bam_qc()
cov_plot = "%s.cov.png" % (prefix)
bamqc.plot_cov("Chromosome",cov_plot)
stats["bam_pct_reads_mapped"] = bamqc.pct_reads_mapped
stats["bam_med_dp"] = bamqc.med_dp
stats["bam_depth_10"] = bamqc.genome_cov[10]
stats["bam_depth_5"] = bamqc.genome_cov[5]
