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): bam = ps.bam(bam_file=args.bam,ref_file=args.ref,prefix=args.prefix,threads=args.threads) if args.high_cov_as_missing: bamqc = bam.get_bam_qc() max_dp = bamqc.med_dp*3 else: max_dp = None bam.gbcf(threads=args.threads,max_dp=max_dp,platform=args.platform,primers=args.primers,call_method=args.method,vtype=args.vtype,min_dp=args.min_dp,mpileup_options=args.mpileup_options)
def main(args): bam = ps.bam(bam_file=args.bam, ref_file=args.ref, prefix=args.prefix, threads=args.threads) bam.gbcf(threads=args.threads, platform=args.platform, primers=args.primers, call_method=args.method, vtype=args.vtype, min_dp=args.min_dp)
def main(args): bam = ps.bam(args.bam, args.prefix, args.ref, threads=args.threads) bcf = bam.call_variants(call_method=args.call_method, gff_file=args.gff, bed_file=args.bed, mixed_as_missing=True, threads=args.threads, min_dp=args.min_depth) csq = bcf.load_csq(ann_file=args.ann, changes=True) tmp_bcf = "%s.missing.bcf" % args.prefix missing_pos = ps.get_missing_positions(tmp_bcf) outfile = "%s.results.json" % args.prefix results = {"variants": {}, "missing": missing_pos} for gene in csq: results["variants"][gene] = [] for var in csq[gene]: results["variants"][gene].append(var.values()[0]) json.dump(results, open(outfile, "w"))
def main(args): bam = ps.bam(args.bam,args.prefix,args.ref,threads=args.threads) bcf = bam.call_variants(call_method=args.call_method,gff_file=args.gff,bed_file=args.bed,mixed_as_missing=False,threads=args.threads,min_dp=args.min_depth) csq = bcf.load_csq_alt(ann_file=args.ann,changes=True) tmp_bcf = "%s.missing.bcf" % args.prefix missing_pos = ps.get_missing_positions(tmp_bcf) outfile = "%s.results.json" % args.prefix results = {"variants":[],"missing":missing_pos} for sample in csq: results["variants"] = csq[sample] if args.barcode: mutations = bam.get_bed_gt(args.barcode) barcode = ps.barcode(mutations,"lineages.bed") results["barcode"] = barcode bcf.bed_consensus(args.bed,args.ref) json.dump(results,open(outfile,"w"))
def main(args): bam = ps.bam(bam_file=args.bam, ref_file=args.ref, prefix=args.prefix, threads=args.threads) if args.high_cov_as_missing: bamqc = bam.get_bam_qc() max_dp = bamqc.med_dp * 3 else: max_dp = None bam.gbcf(threads=args.threads, max_dp=max_dp, platform=args.platform, primers=args.primers, call_method=args.method, vtype=args.vtype, min_dp=args.min_dp, mpileup_options=args.mpileup_options)
def main(args): bam = ps.bam(args.bam, args.prefix, args.ref, threads=args.threads) bcf = bam.call_variants(call_method=args.call_method, gff_file=args.gff, bed_file=args.bed, mixed_as_missing=False, threads=args.threads, min_dp=args.min_depth) csq = bcf.load_csq_alt(ann_file=args.ann, changes=True) tmp_bcf = "%s.missing.bcf" % args.prefix missing_pos = ps.get_missing_positions(tmp_bcf) outfile = "%s.results.json" % args.prefix results = {"variants": [], "missing": missing_pos} for sample in csq: results["variants"] = csq[sample] if args.barcode: mutations = bam.get_bed_gt(args.barcode) barcode = ps.barcode(mutations, "lineages.bed") results["barcode"] = barcode if args.seq: bcf.bed_consensus(args.bed, args.ref) json.dump(results, open(outfile, "w"))
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] 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()
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] 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", "centrifuge_top_hit", "centrifuge_pct_reads", "bam_pct_reads_mapped", "bam_med_dp",
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] 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","centrifuge_top_hit","centrifuge_pct_reads","bam_pct_reads_mapped","bam_med_dp","bam_depth_5","bam_depth_10"]: O.write("%s\t%s\n" % (x,stats[x])) O.close()