def main(args):
bcf = ps.bcf(args.bcf)
bcf.get_mean_genotype()
bcf.get_genesum()
geno_file = bcf.prefix+".geno"
genesum_file = bcf.prefix+".genesum"
meta = {}
for s in bcf.samples:
meta[s] = {}
for row in csv.DictReader(open(args.csv)):
for pheno in row.keys():
if pheno=="id": continue
if row['id'] not in meta: continue
meta[row["id"]][pheno] = row[pheno]
phenos = [x.rstrip() for x in open(args.phenos).readlines()]
cmd_file = ps.get_random_file()
X = open(cmd_file,"w")
for pheno in phenos:
pheno_file = "%s.pheno" % pheno
if pheno not in row:
ps.log("%s not in CSV file"%pheno,True)
P = open(pheno_file,"w")
P.write("\n".join([meta[s][pheno] if pheno in meta[s] else "NA" for s in bcf.samples]))
P.close()
X.write("gemma -p %s -g %s -gk 1 -o %s -maf 0.00005 -miss 0.99 && gemma -lmm 1 -p %s -g %s -k output/%s.cXX.txt -o %s -maf 0.00005 -miss 0.99 && gemma -lmm 1 -p %s -g %s -k output/%s.cXX.txt -o %s.genesum -notsnp\n" % (pheno_file,geno_file,pheno,pheno_file,geno_file,pheno,pheno,pheno_file,genesum_file,pheno,pheno))
X.close()
if args.preprocess:
ps.log("Preprocessing finished\n", True)
else:
ps.run_cmd("cat %s | parallel -j %s" % (cmd_file,args.threads))
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.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):
if not args.r1:
ps.log("Please provide at least one fastq file with -1...Exiting")
quit()
else:
ps.filecheck(args.r1)
if args.r2: ps.filecheck(args.r2)
if not args.prefix:
ps.log("Please provide a file output prefix...Exiting")
quit()
stats = {}
fastqqc = ps.qc_fastq(args.prefix,args.r1,args.r2) if args.r2 else ps.qc_fastq(args.prefix,args.r1)
stats["mean_read_len"] = fastqqc.mean_read_len
stats["read_num"] = fastqqc.read_num
stats_json = "%s.fastq_stats.json" % args.prefix
json.dump(stats,open(stats_json,"w"))
def main(args):
if not args.r1:
ps.log("Please provide at least one fastq file with -1...Exiting")
quit()
else:
ps.filecheck(args.r1)
if args.r2: ps.filecheck(args.r2)
if not args.prefix:
ps.log("Please provide a file output prefix...Exiting")
quit()
stats = {}
fastqqc = ps.qc_fastq(args.prefix, args.r1,
args.r2) if args.r2 else ps.qc_fastq(
args.prefix, args.r1)
stats["mean_read_len"] = fastqqc.mean_read_len
stats["read_num"] = fastqqc.read_num
stats_json = "%s.fastq_stats.json" % args.prefix
json.dump(stats, open(stats_json, "w"))
def main(args):
bcf = ps.bcf(args.bcf)
bcf.get_mean_genotype()
bcf.get_genesum()
geno_file = bcf.prefix + ".geno"
genesum_file = bcf.prefix + ".genesum"
meta = {}
for s in bcf.samples:
meta[s] = {}
for row in csv.DictReader(open(args.csv)):
for pheno in row.keys():
if pheno == "id": continue
if row['id'] not in meta: continue
meta[row["id"]][pheno] = row[pheno]
phenos = [x.rstrip() for x in open(args.phenos).readlines()]
cmd_file = ps.get_random_file()
X = open(cmd_file, "w")
for pheno in phenos:
pheno_file = "%s.pheno" % pheno
if pheno not in row:
ps.log("%s not in CSV file" % pheno, True)
P = open(pheno_file, "w")
P.write("\n".join([
meta[s][pheno] if pheno in meta[s] else "NA" for s in bcf.samples
]))
P.close()
X.write(
"gemma -p %s -g %s -gk 1 -o %s -maf 0.00005 -miss 0.99 && gemma -lmm 1 -p %s -g %s -k output/%s.cXX.txt -o %s -maf 0.00005 -miss 0.99 && gemma -lmm 1 -p %s -g %s -k output/%s.cXX.txt -o %s.genesum -notsnp\n"
% (pheno_file, geno_file, pheno, pheno_file, geno_file, pheno,
pheno, pheno_file, genesum_file, pheno, pheno))
X.close()
if args.preprocess:
ps.log("Preprocessing finished\n", True)
else:
ps.run_cmd("cat %s | parallel -j %s" % (cmd_file, args.threads))
def main(args):
if not args.samples_file and not args.sample:
ps.log("Provide either --sample or --samples_file... Exiting",
ext=True)
if args.samples_file and args.sample:
ps.log(
"Provide either --sample or --samples_file but not both... Exiting",
ext=True)
if args.cram and not args.reference:
ps.log("Provide reference for cram compression... Exiting", ext=True)
if args.sample:
merge_sample(args.sample, args.cram, args.reference)
else:
for l in open(args.samples_file):
merge_sample(l.rstrip(), args.cram, args.reference)
#! /usr/bin/env python
import pathogenseq as ps
import sys
if len(sys.argv)!=5:
ps.log("sambamba_depth.py <ref> <bam> <prefix> <threads>",True)
ref_file = sys.argv[1]
bam_file = sys.argv[2]
prefix = sys.argv[3]
threads = sys.argv[4]
bam = ps.bam(bam_file,prefix,ref_file,threads=threads)
out_file = "%s.sambamba.depth" % prefix
bam.sambamba_depth(out_file)