1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
|
#! /usr/bin/env python
# wdecoster
from argparse import ArgumentParser
from nanoget import get_input
import os
def main():
'''
Organization function
-setups logging
-gets inputdata
-calls plotting function
'''
args = get_args()
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,
}
if os.path.isfile(args.output) and not args.force:
print("Output file {} already exists.".format(args.output))
else:
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)) \
.to_feather(args.output)
def get_args():
parser = ArgumentParser(
description="Creates various plots for long read sequencing data.".upper(),
add_help=False)
general = parser.add_argument_group(
title='General options')
general.add_argument("-h", "--help",
action="help",
help="show the help and exit")
general.add_argument("-t", "--threads",
help="Set the allowed number of threads to be used by the script",
default=4,
type=int)
general.add_argument("--huge",
help="Input data is one very large file.",
action="store_true")
general.add_argument("-o", "--output",
help="Specify name of feather file.",
default="NanoPlot-data.feather")
general.add_argument("--readtype",
help="Which read type to extract information about from summary. \
Options are 1D, 2D, 1D2",
default="1D",
choices=['1D', '2D', '1D2'])
general.add_argument("--barcoded",
help="Use if you want to split the summary file by barcode",
action="store_true")
general.add_argument("--no_supplementary",
help="Use if you want to remove supplementary alignments",
action="store_true",
default=False)
general.add_argument("--force",
help="Overwrite existing feather files",
action="store_true",
default=False)
target = parser.add_argument_group(
title="Input data sources, one of these is required.")
mtarget = target.add_mutually_exclusive_group(
required=True)
mtarget.add_argument("--fastq",
help="Data is in one or more default fastq file(s).",
nargs='+',
metavar="file")
mtarget.add_argument("--fasta",
help="Data is in one or more fasta file(s).",
nargs='+',
metavar="file")
mtarget.add_argument("--fastq_rich",
help="Data is in one or more fastq file(s) generated by albacore, \
MinKNOW or guppy with additional information \
concerning channel and time.",
nargs='+',
metavar="file")
mtarget.add_argument("--fastq_minimal",
help="Data is in one or more fastq file(s) generated by albacore, \
MinKNOW or guppy with additional information concerning channel \
and time. Is extracted swiftly without elaborate checks.",
nargs='+',
metavar="file")
mtarget.add_argument("--summary",
help="Data is in one or more summary file(s) generated by albacore \
or guppy.",
nargs='+',
metavar="file")
mtarget.add_argument("--bam",
help="Data is in one or more sorted bam file(s).",
nargs='+',
metavar="file")
mtarget.add_argument("--ubam",
help="Data is in one or more unmapped bam file(s).",
nargs='+',
metavar="file")
mtarget.add_argument("--cram",
help="Data is in one or more sorted cram file(s).",
nargs='+',
metavar="file")
return parser.parse_args()
if __name__ == '__main__':
main()
|
