for f in in_files:
for ref in refs:
if not os.path.isdir("{}/{}".format(args.output, ref)):
os.makedirs("{}/{}".format(args.output, ref))
fq_path = os.path.join(args.input, f)
if args.filesfile:
if not fq_path in files:
skipped = open(
"{}/{}/skippedfiles.txt".format(args.output, ref), "a")
skipped.write("{}\n".format(f))
skipped.close()
elif not os.path.isfile(fq_path):
continue
workflow.add_task_gridable(cmd,
reference=ref,
depend=fq_path,
target="{}{}_panphlan_map.csv.bz2".format(
args.output,
os.path.basename(f.strip(".fastq.gz"))),
folder=args.output,
threads=args.threads,
cores=args.threads,
db=args.dbfolder,
time=4 * 60,
mem=8 * 1000)
workflow.go()
workflow.add_argument(
"refs",
default=None,
desc="file with list of references (relative to dbfolder)")
args = workflow.parse_args()
cmd = "panphlan_profile.py -c {0} -i {0}/ --o_dna [target] --add_strains"
if args.dbfolder:
cmd += " --i_bowtie2_indexes {}".format(args.dbfolder)
if args.ref:
refs = [args.ref]
elif args.refs:
r = open(args.refs, "r")
refs = [l.strip() for l in r]
r.close()
for ref in refs:
if os.path.isdir(ref):
workflow.add_task_gridable(cmd.format(ref,
os.path.join(args.input, ref)),
target="{}profiles/{}_pa.tsv".format(
args.output, ref),
cores=1,
time=30,
mem=1000)
workflow.go()
