def main():
args = get_args()
if args.outdir and not os.path.exists(args.outdir):
os.makedirs(args.outdir)
if args.feather:
from nanoget import combine_dfs
from pandas import read_feather
datadf = combine_dfs([read_feather(p) for p in args.feather],
method="simple")
else:
sources = {
"fastq": args.fastq,
"bam": args.bam,
"cram": args.cram,
"summary": args.summary,
"fasta": args.fasta,
"ubam": args.ubam,
}
datadf = nanoget.get_input(source=[n for n, s in sources.items()
if s][0],
files=[f for f in sources.values() if f][0],
threads=args.threads,
readtype=args.readtype,
combine="track",
barcoded=args.barcoded,
keep_supp=not (args.no_supplementary))
if args.barcoded:
barcodes = list(datadf["barcode"].unique())
write_stats(datadfs=[datadf[datadf["barcode"] == b] for b in barcodes],
outputfile=os.path.join(args.outdir, args.name),
names=barcodes)
write_stats(datadfs=[datadf],
outputfile=os.path.join(args.outdir, args.name),
as_tsv=args.tsv)
def main():
'''
Organization function
-setups logging
-gets inputdata
-calls plotting function
'''
settings, args = utils.get_args()
try:
utils.make_output_dir(args.outdir)
utils.init_logs(args)
# args.format = nanoplotter.check_valid_format(args.format)
if args.pickle:
datadf = pickle.load(open(args.pickle, 'rb'))
elif args.feather:
from nanoget import combine_dfs
from pandas import read_feather
datadf = combine_dfs([read_feather(p) for p in args.feather], method="simple")
else:
sources = {
"fastq": args.fastq,
"bam": args.bam,
"cram": args.cram,
"fastq_rich": args.fastq_rich,
"fastq_minimal": args.fastq_minimal,
"summary": args.summary,
"fasta": args.fasta,
"ubam": args.ubam,
}
datadf = get_input(
source=[n for n, s in sources.items() if s][0],
files=[f for f in sources.values() if f][0],
threads=args.threads,
readtype=args.readtype,
combine="simple",
barcoded=args.barcoded,
huge=args.huge,
keep_supp=not (args.no_supplementary))
if args.store:
pickle.dump(
obj=datadf,
file=open(settings["path"] + "NanoPlot-data.pickle", 'wb'))
if args.raw:
datadf.to_csv(settings["path"] + "NanoPlot-data.tsv.gz",
sep="\t",
index=False,
compression="gzip")
settings["statsfile"] = [make_stats(datadf, settings, suffix="", tsv_stats=args.tsv_stats)]
datadf, settings = filter_and_transform_data(datadf, settings)
if settings["filtered"]: # Bool set when filter was applied in filter_and_transform_data()
settings["statsfile"].append(
make_stats(datadf[datadf["length_filter"]], settings,
suffix="_post_filtering", tsv_stats=args.tsv_stats)
)
if args.barcoded:
main_path = settings["path"]
barcodes = list(datadf["barcode"].unique())
plots = []
for barc in barcodes:
logging.info("Processing {}".format(barc))
dfbarc = datadf[datadf["barcode"] == barc]
if len(dfbarc) > 5:
settings["title"] = barc
settings["path"] = path.join(args.outdir, args.prefix + barc + "_")
plots.append(report.BarcodeTitle(barc))
plots.extend(
make_plots(dfbarc, settings)
)
else:
sys.stderr.write("Found barcode {} less than 5x, ignoring...\n".format(barc))
logging.info("Found barcode {} less than 5 times, ignoring".format(barc))
settings["path"] = main_path
else:
plots = make_plots(datadf, settings)
make_report(plots, settings)
logging.info("Finished!")
except Exception as e:
logging.error(e, exc_info=True)
print("\n\n\nIf you read this then NanoPlot {} has crashed :-(".format(__version__))
print("Please try updating NanoPlot and see if that helps...\n")
print("If not, please report this issue at https://github.com/wdecoster/NanoPlot/issues")
print("If you could include the log file that would be really helpful.")
print("Thanks!\n\n\n")
raise
def main():
'''
Organization function
-setups logging
-gets inputdata
-calls plotting function
'''
settings, args = utils.get_args()
try:
utils.make_output_dir(args.outdir)
utils.init_logs(args)
sources = {
"fastq": args.fastq,
"bam": args.bam,
"cram": args.cram,
"summary": args.summary,
"fasta": args.fasta,
"ubam": args.ubam,
}
if args.split_runs:
split_dict = utils.validate_split_runs_file(args.split_runs)
if args.pickle:
from nanoget import combine_dfs
datadf = combine_dfs(
dfs=[pickle.load(open(p, 'rb')) for p in args.pickle],
names=args.names,
method="track")
elif args.feather:
from nanoget import combine_dfs
from pandas import read_feather
datadf = combine_dfs([read_feather(p) for p in args.feather],
names=args.names or args.feather,
method="track")
else:
datadf = nanoget.get_input(
source=[n for n, s in sources.items() if s][0],
files=[f for f in sources.values() if f][0],
threads=args.threads,
readtype=args.readtype,
names=args.names,
barcoded=args.barcoded,
combine="track")
datadf, settings = filter_and_transform_data(datadf, vars(args))
if args.raw:
datadf.to_csv(settings["path"] + "NanoComp-data.tsv.gz",
sep="\t",
index=False,
compression="gzip")
if args.store:
pickle.dump(obj=datadf,
file=open(settings["path"] + "NanoComp-data.pickle",
'wb'))
if args.split_runs:
utils.change_identifiers(datadf, split_dict)
if args.barcoded:
datadf["dataset"] = datadf["barcode"]
identifiers = list(datadf["dataset"].unique())
stats_df = write_stats(
datadfs=[datadf[datadf["dataset"] == i] for i in identifiers],
outputfile=settings["path"] + "NanoStats.txt",
names=identifiers,
as_tsv=args.tsv_stats)
if args.plot != 'false':
plots = make_plots(datadf, settings)
make_report(plots, settings["path"], stats_df=stats_df)
logging.info("Succesfully processed all input.")
except Exception as e:
logging.error(e, exc_info=True)
raise