biofile-kit 0.0.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- biofile_kit/bin/fasta_tools.py +53 -0
- biofile_kit/bin/gff_tools.py +33 -0
- biofile_kit/bin/gtf_tools.py +30 -0
- biofile_kit/fasta_utils/ORF_finder.py +94 -0
- biofile_kit/fasta_utils/SSR_finder.py +58 -0
- biofile_kit/fasta_utils/__init__.py +30 -0
- biofile_kit/fasta_utils/fa2tab.py +42 -0
- biofile_kit/fasta_utils/format_fasta.py +91 -0
- biofile_kit/fasta_utils/gap_location.py +38 -0
- biofile_kit/fasta_utils/generate_random_nucl.py +66 -0
- biofile_kit/fasta_utils/get_longest_seq_for_gene.py +46 -0
- biofile_kit/fasta_utils/get_reverse_complementary_seq.py +43 -0
- biofile_kit/fasta_utils/get_seq_len.py +41 -0
- biofile_kit/fasta_utils/id_index_seq.py +76 -0
- biofile_kit/fasta_utils/motif_finder.py +67 -0
- biofile_kit/fasta_utils/seq_rename.py +50 -0
- biofile_kit/gff_utils/__init__.py +18 -0
- biofile_kit/gff_utils/get_feature_density.py +52 -0
- biofile_kit/gff_utils/gff2bed.py +43 -0
- biofile_kit/gff_utils/gff2gtf.py +38 -0
- biofile_kit/gff_utils/gff_extract_seq.py +81 -0
- biofile_kit/gff_utils/gff_sort.py +34 -0
- biofile_kit/gff_utils/rename.py +73 -0
- biofile_kit/gtf_utils/__init__.py +12 -0
- biofile_kit/gtf_utils/gtf2bed.py +38 -0
- biofile_kit/gtf_utils/gtf_extract_seq.py +41 -0
- biofile_kit/gtf_utils/gtf_sort.py +35 -0
- biofile_kit-0.0.0.dist-info/LICENSE +21 -0
- biofile_kit-0.0.0.dist-info/METADATA +50 -0
- biofile_kit-0.0.0.dist-info/RECORD +32 -0
- biofile_kit-0.0.0.dist-info/WHEEL +4 -0
- biofile_kit-0.0.0.dist-info/entry_points.txt +5 -0
|
@@ -0,0 +1,53 @@
|
|
|
1
|
+
#!/usr/bin/env python
|
|
2
|
+
"""
|
|
3
|
+
File: gff_tools.py
|
|
4
|
+
Description: Fasta file tools.
|
|
5
|
+
CreateDate: 2025/7/2
|
|
6
|
+
Author: xuwenlin
|
|
7
|
+
E-mail: wenlinxu.njfu@outlook.com
|
|
8
|
+
"""
|
|
9
|
+
import click
|
|
10
|
+
from biofile_kit.fasta_utils import (
|
|
11
|
+
fa2tab,
|
|
12
|
+
format_fasta,
|
|
13
|
+
gap_location,
|
|
14
|
+
generate_random_nucl,
|
|
15
|
+
get_longest_seq_for_gene,
|
|
16
|
+
get_reverse_complementary_seq,
|
|
17
|
+
get_seq_len,
|
|
18
|
+
id_index_seq,
|
|
19
|
+
motif_finder,
|
|
20
|
+
ORF_finder,
|
|
21
|
+
seq_rename,
|
|
22
|
+
SSR_finder,
|
|
23
|
+
__version__
|
|
24
|
+
)
|
|
25
|
+
from pybioinformatic import Displayer
|
|
26
|
+
|
|
27
|
+
displayer = Displayer(__file__.split('/')[-1], version=__version__)
|
|
28
|
+
|
|
29
|
+
|
|
30
|
+
@click.group(context_settings=dict(help_option_names=['-h', '--help']))
|
|
31
|
+
@click.option('-V', '--version', 'version', help='Show author and version information.',
|
|
32
|
+
is_flag=True, is_eager=True, expose_value=False, callback=displayer.version_info)
|
|
33
|
+
def fasta_tools():
|
|
34
|
+
"""Fasta file tools."""
|
|
35
|
+
pass
|
|
36
|
+
|
|
37
|
+
|
|
38
|
+
fasta_tools.add_command(fa2tab, 'fa2tab')
|
|
39
|
+
fasta_tools.add_command(format_fasta, 'format_fasta')
|
|
40
|
+
fasta_tools.add_command(gap_location, 'gap_location')
|
|
41
|
+
fasta_tools.add_command(generate_random_nucl, 'random_nucl')
|
|
42
|
+
fasta_tools.add_command(get_longest_seq_for_gene, 'get_longest_seq_for_gene')
|
|
43
|
+
fasta_tools.add_command(get_reverse_complementary_seq, 'get_reverse_complementary_seq')
|
|
44
|
+
fasta_tools.add_command(get_seq_len, 'get_seq_len')
|
|
45
|
+
fasta_tools.add_command(id_index_seq, 'id_index_seq')
|
|
46
|
+
fasta_tools.add_command(motif_finder, 'motif_finder')
|
|
47
|
+
fasta_tools.add_command(ORF_finder, 'ORF_finder')
|
|
48
|
+
fasta_tools.add_command(seq_rename, 'seq_rename')
|
|
49
|
+
fasta_tools.add_command(SSR_finder, 'SSR_finder')
|
|
50
|
+
|
|
51
|
+
|
|
52
|
+
if __name__ == '__main__':
|
|
53
|
+
fasta_tools()
|
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
#!/usr/bin/env python
|
|
2
|
+
"""
|
|
3
|
+
File: gff_tools.py
|
|
4
|
+
Description: Gff file tools.
|
|
5
|
+
CreateDate: 2025/7/2
|
|
6
|
+
Author: xuwenlin
|
|
7
|
+
E-mail: wenlinxu.njfu@outlook.com
|
|
8
|
+
"""
|
|
9
|
+
import click
|
|
10
|
+
from biofile_kit.gff_utils import get_feature_density, gff2bed, gff2gtf, gff_extract_seq, gff_sort, rename, __version__
|
|
11
|
+
from pybioinformatic import Displayer
|
|
12
|
+
|
|
13
|
+
displayer = Displayer(__file__.split('/')[-1], version=__version__)
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
@click.group(context_settings=dict(help_option_names=['-h', '--help']))
|
|
17
|
+
@click.option('-V', '--version', 'version', help='Show author and version information.',
|
|
18
|
+
is_flag=True, is_eager=True, expose_value=False, callback=displayer.version_info)
|
|
19
|
+
def gff_tools():
|
|
20
|
+
"""Gff file tools."""
|
|
21
|
+
pass
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
gff_tools.add_command(get_feature_density, 'get_feature_density')
|
|
25
|
+
gff_tools.add_command(gff2bed, 'to_bed')
|
|
26
|
+
gff_tools.add_command(gff2gtf, 'to_gtf')
|
|
27
|
+
gff_tools.add_command(gff_extract_seq, 'extract_seq')
|
|
28
|
+
gff_tools.add_command(gff_sort, 'sort')
|
|
29
|
+
gff_tools.add_command(rename, 'rename')
|
|
30
|
+
|
|
31
|
+
|
|
32
|
+
if __name__ == '__main__':
|
|
33
|
+
gff_tools()
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
#!/usr/bin/env python
|
|
2
|
+
"""
|
|
3
|
+
File: gff_tools.py
|
|
4
|
+
Description: Gtf file tools.
|
|
5
|
+
CreateDate: 2025/7/2
|
|
6
|
+
Author: xuwenlin
|
|
7
|
+
E-mail: wenlinxu.njfu@outlook.com
|
|
8
|
+
"""
|
|
9
|
+
import click
|
|
10
|
+
from biofile_kit.gtf_utils import gtf2bed, gtf_extract_seq, gtf_sort, __version__
|
|
11
|
+
from pybioinformatic import Displayer
|
|
12
|
+
|
|
13
|
+
displayer = Displayer(__file__.split('/')[-1], version=__version__)
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
@click.group(context_settings=dict(help_option_names=['-h', '--help']))
|
|
17
|
+
@click.option('-V', '--version', 'version', help='Show author and version information.',
|
|
18
|
+
is_flag=True, is_eager=True, expose_value=False, callback=displayer.version_info)
|
|
19
|
+
def gtf_tools():
|
|
20
|
+
"""Gtf file tools."""
|
|
21
|
+
pass
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
gtf_tools.add_command(gtf_sort, 'sort')
|
|
25
|
+
gtf_tools.add_command(gtf_extract_seq, 'extract_seq')
|
|
26
|
+
gtf_tools.add_command(gtf2bed, 'to_bed')
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
if __name__ == '__main__':
|
|
30
|
+
gtf_tools()
|
|
@@ -0,0 +1,94 @@
|
|
|
1
|
+
#!/usr/bin/env python
|
|
2
|
+
"""
|
|
3
|
+
File: ORF_finder.py
|
|
4
|
+
Description: Search for open reading frames (ORFs) in the nucleotide sequence you enter, and return maximum length ORF of each nucleotide sequence.
|
|
5
|
+
CreateDate: 2022/3/25
|
|
6
|
+
Author: xuwenlin
|
|
7
|
+
E-mail: wenlinxu.njfu@outlook.com
|
|
8
|
+
"""
|
|
9
|
+
from tqdm import tqdm
|
|
10
|
+
from io import TextIOWrapper
|
|
11
|
+
from typing import Tuple, Union
|
|
12
|
+
from os import name
|
|
13
|
+
from natsort import natsort_key
|
|
14
|
+
import click
|
|
15
|
+
from pybioinformatic import Fasta, Nucleotide, TaskManager, Timer, Displayer
|
|
16
|
+
displayer = Displayer(__file__.split('/')[-1], version='0.1.0')
|
|
17
|
+
|
|
18
|
+
|
|
19
|
+
def sub_processing(nucl_obj: Nucleotide, min_len: int, complete: bool, only_plus: bool):
|
|
20
|
+
ORF = nucl_obj.ORF_prediction(min_len, complete, only_plus)
|
|
21
|
+
return ORF
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
@Timer('ORF predicting.')
|
|
25
|
+
def main(fasta_files: Tuple[Union[str, TextIOWrapper]],
|
|
26
|
+
parse_seqids: bool = True,
|
|
27
|
+
min_len: int = 30,
|
|
28
|
+
complete: bool = True,
|
|
29
|
+
only_plus: bool = False,
|
|
30
|
+
log_file: TextIOWrapper = None,
|
|
31
|
+
output_path: str = None,
|
|
32
|
+
num_processes: int = 1):
|
|
33
|
+
tkm = TaskManager(num_processing=num_processes)
|
|
34
|
+
for fasta_file in fasta_files:
|
|
35
|
+
with Fasta(fasta_file) as fa:
|
|
36
|
+
tkm.params = ((nucl_obj, min_len, complete, only_plus) for nucl_obj in fa.parse(parse_seqids))
|
|
37
|
+
# Set output prefix
|
|
38
|
+
if name == 'posix': # linux
|
|
39
|
+
output_prefix = fa.name.split('/')[-1].replace('.gz', '').replace('<', '').replace('>', '')
|
|
40
|
+
else: # windows
|
|
41
|
+
output_prefix = fa.name.split('\\')[-1].replace('.gz', '').replace('<', '').replace('>', '')
|
|
42
|
+
output_prefix = '.'.join(output_prefix.split('.')[:-1])
|
|
43
|
+
# Show the progress bar on the command line.
|
|
44
|
+
if (log_file is not None) and (output_path is not None) and ('stdin' not in fa.name):
|
|
45
|
+
with open(f'{output_path}/{output_prefix}_pep.fa', 'w') as output_file:
|
|
46
|
+
with tqdm(total=fa.seq_num, unit=' sequence', desc=f'[Processing {fa.name}]') as pbar:
|
|
47
|
+
results = tkm.parallel_run_func(sub_processing, lambda _: pbar.update(1))
|
|
48
|
+
results = [i.get() for i in results]
|
|
49
|
+
log = '\n'.join([i for i in results if isinstance(i, str)])
|
|
50
|
+
click.echo(log, log_file, err=True)
|
|
51
|
+
ORFs = [ORF for ORF in results if not isinstance(ORF, str)]
|
|
52
|
+
ORFs.sort(key=lambda i: natsort_key(i.id))
|
|
53
|
+
for ORF in ORFs:
|
|
54
|
+
click.echo(ORF, output_file)
|
|
55
|
+
# Do not show the progress bar on the command line.
|
|
56
|
+
else:
|
|
57
|
+
output_file = open(f'{output_path}/{output_prefix}_pep.fa', 'w') if output_path else None
|
|
58
|
+
tkm.parallel_run_func(sub_processing,
|
|
59
|
+
lambda ORF: click.echo(ORF, log_file, err=True) if isinstance(ORF, str) else
|
|
60
|
+
click.echo(ORF, output_file))
|
|
61
|
+
|
|
62
|
+
|
|
63
|
+
@click.command(context_settings=dict(help_option_names=['-h', '--help']))
|
|
64
|
+
@click.argument('fasta_files', nargs=-1, metavar='<fasta files|stdin>', type=click.File('r'), required=True)
|
|
65
|
+
@click.option('-l', '--min-len', 'min_len',
|
|
66
|
+
metavar='<int>', type=int, default=30, show_default=True,
|
|
67
|
+
help='Minimal ORF length.')
|
|
68
|
+
@click.option('-p', '--parse-seqids', 'parse_seqids',
|
|
69
|
+
is_flag=True, flag_value=True,
|
|
70
|
+
help='Parse sequence id.')
|
|
71
|
+
@click.option('-c', '--completed', 'completed',
|
|
72
|
+
is_flag=True, flag_value=True,
|
|
73
|
+
help='Remain completed ORF.')
|
|
74
|
+
@click.option('-F', '--forward', 'forward',
|
|
75
|
+
is_flag=True, flag_value=True,
|
|
76
|
+
help='Only predict forward chain.')
|
|
77
|
+
@click.option('-log', '--logfile', 'log_file',
|
|
78
|
+
metavar='<file|stderr>', type=click.File('w'),
|
|
79
|
+
help='Write the sequence that not found ORF to logfile, stderr by default.')
|
|
80
|
+
@click.option('-o', '--output-path', 'output_path',
|
|
81
|
+
metavar='<path|stdout>',
|
|
82
|
+
help='Output path, stdout by default.')
|
|
83
|
+
@click.option('-n', '--num_processes', 'num_processes',
|
|
84
|
+
metavar='<int>', type=int, default=1, show_default=True,
|
|
85
|
+
help='Number of processes.')
|
|
86
|
+
@click.option('-V', '--version', 'version', help='Show author and version information.',
|
|
87
|
+
is_flag=True, is_eager=True, expose_value=False, callback=displayer.version_info)
|
|
88
|
+
def run(fasta_files, parse_seqids, min_len, completed, forward, log_file, output_path, num_processes):
|
|
89
|
+
"""Search for open reading frames (ORFs) in the nucleotide sequence you enter, and return maximum length ORF of each nucleotide sequence."""
|
|
90
|
+
main(fasta_files, parse_seqids, min_len, completed, forward, log_file, output_path, num_processes)
|
|
91
|
+
|
|
92
|
+
|
|
93
|
+
if __name__ == '__main__':
|
|
94
|
+
run()
|
|
@@ -0,0 +1,58 @@
|
|
|
1
|
+
#!/usr/bin/env python
|
|
2
|
+
"""
|
|
3
|
+
File: SSR_finder.py
|
|
4
|
+
Description: Find simple sequence repeat (SSR) in the DNA sequences.
|
|
5
|
+
CreateDate: 2023/9/9
|
|
6
|
+
Author: xuwenlin
|
|
7
|
+
E-mail: wenlinxu.njfu@outlook.com
|
|
8
|
+
"""
|
|
9
|
+
from io import TextIOWrapper
|
|
10
|
+
from typing import Union
|
|
11
|
+
import click
|
|
12
|
+
from pybioinformatic import Fasta, Nucleotide, TaskManager, Displayer
|
|
13
|
+
displayer = Displayer(__file__.split('/')[-1], version='0.1.0')
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
def sub_processing(nucl: Nucleotide):
|
|
17
|
+
return nucl.find_SSR()
|
|
18
|
+
|
|
19
|
+
|
|
20
|
+
def main(fasta_file: Union[str, TextIOWrapper],
|
|
21
|
+
parse_seqids: bool,
|
|
22
|
+
quiet: bool,
|
|
23
|
+
num_processing: int,
|
|
24
|
+
output_file: TextIOWrapper = None):
|
|
25
|
+
click.echo('# Seq_id\tStart\tEnd\tSSR_unit\tSSR_seq', output_file)
|
|
26
|
+
with Fasta(fasta_file) as fa:
|
|
27
|
+
params = ((nucl,) for nucl in fa.parse(parse_seqids))
|
|
28
|
+
tkm = TaskManager(num_processing=num_processing, params=params)
|
|
29
|
+
tkm.parallel_run_func(sub_processing,
|
|
30
|
+
lambda i: click.echo(i.strip(), err=True) if not quiet and 'not found' in i else
|
|
31
|
+
click.echo(i.strip(), output_file))
|
|
32
|
+
|
|
33
|
+
|
|
34
|
+
@click.command(context_settings=dict(help_option_names=['-h', '--help']))
|
|
35
|
+
@click.option('-i', '--fasta_file', 'fasta_file',
|
|
36
|
+
metavar='<fasta file|stdin>', type=click.File('r'), required=True,
|
|
37
|
+
help='Input FASTA file.')
|
|
38
|
+
@click.option('-p', '--parse_seqids', 'parse_seqids',
|
|
39
|
+
is_flag=True, flag_value=True,
|
|
40
|
+
help='Parse sequence IDs.')
|
|
41
|
+
@click.option('-q', '--quiet', 'quiet',
|
|
42
|
+
is_flag=True, flag_value=True,
|
|
43
|
+
help='Do not report sequence that not found SSR motif.')
|
|
44
|
+
@click.option('-n', '--num_processing', 'num_processing',
|
|
45
|
+
metavar='<int>', type=int, default=1, show_default=True,
|
|
46
|
+
help='Number of processing.')
|
|
47
|
+
@click.option('-o', '--output_file', 'output_file',
|
|
48
|
+
metavar='<file|stdout>', type=click.File('w'),
|
|
49
|
+
help='Output file, stdout by default.')
|
|
50
|
+
@click.option('-V', '--version', 'version', help='Show author and version information.',
|
|
51
|
+
is_flag=True, is_eager=True, expose_value=False, callback=displayer.version_info)
|
|
52
|
+
def run(fasta_file, parse_seqids, quiet, num_processing, output_file):
|
|
53
|
+
"""Find simple sequence repeat (SSR) in the DNA sequences."""
|
|
54
|
+
main(fasta_file, parse_seqids, quiet, num_processing, output_file)
|
|
55
|
+
|
|
56
|
+
|
|
57
|
+
if __name__ == '__main__':
|
|
58
|
+
run()
|
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
from biofile_kit.fasta_utils.fa2tab import run as fa2tab
|
|
2
|
+
from biofile_kit.fasta_utils.format_fasta import run as format_fasta
|
|
3
|
+
from biofile_kit.fasta_utils.gap_location import run as gap_location
|
|
4
|
+
from biofile_kit.fasta_utils.generate_random_nucl import run as generate_random_nucl
|
|
5
|
+
from biofile_kit.fasta_utils.get_longest_seq_for_gene import run as get_longest_seq_for_gene
|
|
6
|
+
from biofile_kit.fasta_utils.get_reverse_complementary_seq import run as get_reverse_complementary_seq
|
|
7
|
+
from biofile_kit.fasta_utils.get_seq_len import run as get_seq_len
|
|
8
|
+
from biofile_kit.fasta_utils.id_index_seq import run as id_index_seq
|
|
9
|
+
from biofile_kit.fasta_utils.motif_finder import run as motif_finder
|
|
10
|
+
from biofile_kit.fasta_utils.ORF_finder import run as ORF_finder
|
|
11
|
+
from biofile_kit.fasta_utils.seq_rename import run as seq_rename
|
|
12
|
+
from biofile_kit.fasta_utils.SSR_finder import run as SSR_finder
|
|
13
|
+
|
|
14
|
+
__version__ = '0.1.0'
|
|
15
|
+
|
|
16
|
+
__all__ = [
|
|
17
|
+
'fa2tab',
|
|
18
|
+
'format_fasta',
|
|
19
|
+
'gap_location',
|
|
20
|
+
'generate_random_nucl',
|
|
21
|
+
'get_longest_seq_for_gene',
|
|
22
|
+
'get_reverse_complementary_seq',
|
|
23
|
+
'get_seq_len',
|
|
24
|
+
'id_index_seq',
|
|
25
|
+
'motif_finder',
|
|
26
|
+
'ORF_finder',
|
|
27
|
+
'seq_rename',
|
|
28
|
+
'SSR_finder',
|
|
29
|
+
'__version__'
|
|
30
|
+
]
|
|
@@ -0,0 +1,42 @@
|
|
|
1
|
+
#!/usr/bin/env python
|
|
2
|
+
"""
|
|
3
|
+
File: fa2tab.py
|
|
4
|
+
Description:
|
|
5
|
+
CreateDate: 2023/10/14
|
|
6
|
+
Author: xuwenlin
|
|
7
|
+
E-mail: wenlinxu.njfu@outlook.com
|
|
8
|
+
"""
|
|
9
|
+
from typing import Union
|
|
10
|
+
from io import TextIOWrapper
|
|
11
|
+
import click
|
|
12
|
+
from pybioinformatic import Fasta, Displayer
|
|
13
|
+
displayer = Displayer(__file__.split('/')[-1], version='0.1.0')
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
def main(fasta_file: Union[str, TextIOWrapper],
|
|
17
|
+
parse_seqids: bool = True,
|
|
18
|
+
output_file: TextIOWrapper = None):
|
|
19
|
+
with Fasta(fasta_file) as fa:
|
|
20
|
+
for ret in fa.fa2tab(parse_seqids):
|
|
21
|
+
click.echo(ret, output_file)
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
@click.command(context_settings=dict(help_option_names=['-h', '--help']))
|
|
25
|
+
@click.option('-i', '--fasta_file', 'fasta_file',
|
|
26
|
+
metavar='<fasta file|stdin>', type=click.File('r'), required=True,
|
|
27
|
+
help='Input FASTA file.')
|
|
28
|
+
@click.option('-p', '--parse_seqids', 'parse_seqids',
|
|
29
|
+
is_flag=True, flag_value=True,
|
|
30
|
+
help='Parse sequence id.')
|
|
31
|
+
@click.option('-o', '--output_file', 'output_file',
|
|
32
|
+
metavar='<file|stdout>', type=click.File('w'),
|
|
33
|
+
help='Output tab delimited text file, stdout by default.')
|
|
34
|
+
@click.option('-V', '--version', 'version', help='Show author and version information.',
|
|
35
|
+
is_flag=True, is_eager=True, expose_value=False, callback=displayer.version_info)
|
|
36
|
+
def run(fasta_file, parse_seqids, output_file):
|
|
37
|
+
"""Description."""
|
|
38
|
+
main(fasta_file, parse_seqids, output_file)
|
|
39
|
+
|
|
40
|
+
|
|
41
|
+
if __name__ == '__main__':
|
|
42
|
+
run()
|
|
@@ -0,0 +1,91 @@
|
|
|
1
|
+
#!/usr/bin/env python
|
|
2
|
+
"""
|
|
3
|
+
File: format_fasta.py
|
|
4
|
+
Description: Make each sequence to be displayed in a single line or in multiple lines and sort sequence by length or ID.
|
|
5
|
+
CreateDate: 2022/3/23
|
|
6
|
+
Author: xuwenlin
|
|
7
|
+
E-mail: wenlinxu.njfu@outlook.com
|
|
8
|
+
"""
|
|
9
|
+
from typing import Union
|
|
10
|
+
from io import TextIOWrapper
|
|
11
|
+
from re import findall
|
|
12
|
+
from natsort import natsort_key
|
|
13
|
+
import click
|
|
14
|
+
from pybioinformatic import Fasta, Displayer
|
|
15
|
+
displayer = Displayer(__file__.split('/')[-1], version='0.2.0')
|
|
16
|
+
|
|
17
|
+
|
|
18
|
+
def main(fasta_file: Union[str, TextIOWrapper],
|
|
19
|
+
parse_seqids: bool = True,
|
|
20
|
+
char_num: int = 60,
|
|
21
|
+
sort_by_len: bool = True,
|
|
22
|
+
sort_by_id: bool = True,
|
|
23
|
+
reverse_id: bool = False,
|
|
24
|
+
reverse_len: bool = False,
|
|
25
|
+
out_file: TextIOWrapper = None):
|
|
26
|
+
with Fasta(fasta_file) as fa:
|
|
27
|
+
seq_obj_generator = fa.merge_sequence(parse_seqids) if char_num == 0 else \
|
|
28
|
+
fa.split_sequence(parse_seqids, char_num)
|
|
29
|
+
seq_obj_list = [seq_obj for seq_obj in seq_obj_generator]
|
|
30
|
+
if sort_by_len and not sort_by_id:
|
|
31
|
+
seq_obj_list.sort(key=lambda i: i.len, reverse=reverse_len)
|
|
32
|
+
elif not sort_by_len and sort_by_id:
|
|
33
|
+
seq_obj_list.sort(key=lambda seq_obj: natsort_key(seq_obj.id), reverse=reverse_id)
|
|
34
|
+
elif sort_by_len and sort_by_id:
|
|
35
|
+
if reverse_len:
|
|
36
|
+
seq_obj_list.sort(
|
|
37
|
+
key=lambda seq_obj: (-seq_obj.len, natsort_key(seq_obj.id), int(findall(r'\d+', seq_obj.id)[0])),
|
|
38
|
+
reverse=reverse_id
|
|
39
|
+
)
|
|
40
|
+
else:
|
|
41
|
+
seq_obj_list.sort(
|
|
42
|
+
key=lambda seq_obj: (seq_obj.len, natsort_key(seq_obj.id), int(findall(r'\d+', seq_obj.id)[0])),
|
|
43
|
+
reverse=reverse_id
|
|
44
|
+
)
|
|
45
|
+
for seq_obj in seq_obj_list:
|
|
46
|
+
click.echo(seq_obj, out_file)
|
|
47
|
+
|
|
48
|
+
|
|
49
|
+
@click.command(context_settings=dict(help_option_names=['-h', '--help']))
|
|
50
|
+
@click.argument('fasta_file', metavar='<fasta file|stdin>', nargs=1, required=True, type=click.File('r'))
|
|
51
|
+
@click.option('-p', '--parse_seqids', 'parse_seqids',
|
|
52
|
+
is_flag=True, flag_value=True,
|
|
53
|
+
help='Parse sequence id.')
|
|
54
|
+
@click.option('-n', '--char_num', 'char_num',
|
|
55
|
+
metavar='<int>', type=int, default=60, show_default=True,
|
|
56
|
+
help='Specify how many character show in per line, 0 presents one line show per sequence.')
|
|
57
|
+
@click.option('-l', '--sort_by_len', 'sort_by_len',
|
|
58
|
+
is_flag=True, flag_value=True,
|
|
59
|
+
help='Sort sequence by length. If both "-L, --sort_by_len" and "-I, --sort_by_id" options are specified, '
|
|
60
|
+
'sort by length first then id by default.')
|
|
61
|
+
@click.option('-i', '--sort_by_id', 'sort_by_id',
|
|
62
|
+
is_flag=True, flag_value=True,
|
|
63
|
+
help='Sort sequence by id. If both "-L, --sort_by_len" and "-I, --sort_by_id" options are specified, '
|
|
64
|
+
'sort by length first then id by default.')
|
|
65
|
+
@click.option('-r', '--reverse-id', 'reverse_id',
|
|
66
|
+
is_flag=True, flag_value=True,
|
|
67
|
+
help='Reverse the result of sort by id.')
|
|
68
|
+
@click.option('-R', '--reverse-len', 'reverse_len',
|
|
69
|
+
is_flag=True, flag_value=True,
|
|
70
|
+
help='Reverse the result of sort by length.')
|
|
71
|
+
@click.option('-o', '--output_file', 'outfile',
|
|
72
|
+
metavar='<fasta file|stdout>', type=click.File('w'),
|
|
73
|
+
help='Output file, stdout by default.')
|
|
74
|
+
@click.option('-V', '--version', 'version', help='Show author and version information.',
|
|
75
|
+
is_flag=True, is_eager=True, expose_value=False, callback=displayer.version_info)
|
|
76
|
+
def run(fasta_file, parse_seqids, char_num, sort_by_len, sort_by_id, reverse_id, reverse_len, outfile):
|
|
77
|
+
"""Make each sequence to be displayed in a single line or in multiple lines and sort sequence by length or ID."""
|
|
78
|
+
main(
|
|
79
|
+
fasta_file=fasta_file,
|
|
80
|
+
parse_seqids=parse_seqids,
|
|
81
|
+
char_num=char_num,
|
|
82
|
+
sort_by_len=sort_by_len,
|
|
83
|
+
sort_by_id=sort_by_id,
|
|
84
|
+
reverse_id=reverse_id,
|
|
85
|
+
reverse_len=reverse_len,
|
|
86
|
+
out_file=outfile
|
|
87
|
+
)
|
|
88
|
+
|
|
89
|
+
|
|
90
|
+
if __name__ == '__main__':
|
|
91
|
+
run()
|
|
@@ -0,0 +1,38 @@
|
|
|
1
|
+
#!/usr/bin/env python
|
|
2
|
+
"""
|
|
3
|
+
File: gap_location.py
|
|
4
|
+
Description: Gap location.
|
|
5
|
+
CreateDate: 2025/5/26
|
|
6
|
+
Author: xuwenlin
|
|
7
|
+
E-mail: wenlinxu.njfu@outlook.com
|
|
8
|
+
"""
|
|
9
|
+
from typing import Union
|
|
10
|
+
from io import TextIOWrapper
|
|
11
|
+
import click
|
|
12
|
+
from pybioinformatic import Fasta, Displayer
|
|
13
|
+
|
|
14
|
+
displayer = Displayer(__file__.split('/')[-1], version='0.1.0')
|
|
15
|
+
|
|
16
|
+
|
|
17
|
+
def main(asm_file: Union[str, TextIOWrapper],
|
|
18
|
+
output_file: TextIOWrapper = None):
|
|
19
|
+
with Fasta(asm_file) as fa:
|
|
20
|
+
for seq_obj in fa.parse():
|
|
21
|
+
for gap in seq_obj.locate_gap():
|
|
22
|
+
click.echo(gap, output_file)
|
|
23
|
+
|
|
24
|
+
|
|
25
|
+
@click.command(context_settings=dict(help_option_names=['-h', '--help']))
|
|
26
|
+
@click.argument('asm_file', metavar='<assembly fasta file | stdin>', required=True, nargs=1)
|
|
27
|
+
@click.option('-o', '--output-file', 'output_file',
|
|
28
|
+
metavar='<file|stdout>', type=click.File('w'),
|
|
29
|
+
help='Output file, stdout by default.')
|
|
30
|
+
@click.option('-V', '--version', 'version', help='Show author and version information.',
|
|
31
|
+
is_flag=True, is_eager=True, expose_value=False, callback=displayer.version_info)
|
|
32
|
+
def run(asm_file, output_file):
|
|
33
|
+
"""Gap location."""
|
|
34
|
+
main(asm_file, output_file)
|
|
35
|
+
|
|
36
|
+
|
|
37
|
+
if __name__ == '__main__':
|
|
38
|
+
run()
|
|
@@ -0,0 +1,66 @@
|
|
|
1
|
+
#!/usr/bin/env python
|
|
2
|
+
"""
|
|
3
|
+
File: generate_random_nucl.py
|
|
4
|
+
Description: Generate random nucleotide sequence.
|
|
5
|
+
CreateDate: 2025/5/16
|
|
6
|
+
Author: xuwenlin
|
|
7
|
+
E-mail: wenlinxu.njfu@outlook.com
|
|
8
|
+
"""
|
|
9
|
+
from io import TextIOWrapper
|
|
10
|
+
from typing import Union, List
|
|
11
|
+
import click
|
|
12
|
+
from pybioinformatic import Nucleotide, Displayer
|
|
13
|
+
|
|
14
|
+
displayer = Displayer(__file__.split('/')[-1], version='0.1.0')
|
|
15
|
+
|
|
16
|
+
|
|
17
|
+
def check_params(
|
|
18
|
+
names: Union[List[str], str, None],
|
|
19
|
+
length: Union[List[int], int, None]
|
|
20
|
+
):
|
|
21
|
+
if all([isinstance(names, list), isinstance(length, list)]) and len(names) != len(length):
|
|
22
|
+
click.echo('\033[31mError: The name and the quantity of the length do not match.\033[0m', err=True)
|
|
23
|
+
exit()
|
|
24
|
+
|
|
25
|
+
|
|
26
|
+
def main(names: Union[List[str], str, None],
|
|
27
|
+
length: Union[List[int], str, None],
|
|
28
|
+
bias: Union[List[float], str, None],
|
|
29
|
+
output_file: TextIOWrapper = None):
|
|
30
|
+
check_params(names, length)
|
|
31
|
+
if isinstance(names, list) and isinstance(length, list):
|
|
32
|
+
for i in range(len(names)):
|
|
33
|
+
click.echo(Nucleotide.random_nucl(name=names[i], length=length[i], bias=bias), output_file)
|
|
34
|
+
else:
|
|
35
|
+
click.echo(Nucleotide.random_nucl(name=names, length=length, bias=bias), output_file)
|
|
36
|
+
|
|
37
|
+
|
|
38
|
+
@click.command(context_settings=dict(help_option_names=['-h', '--help']))
|
|
39
|
+
@click.option('-n', '--names', 'names', metavar='<str>',
|
|
40
|
+
help='Nucleotide sequence name. Multiple names should be separated by commas (eg. seq1,se2),'
|
|
41
|
+
'and the number of names should be consistent with the "-l, --length" option values.')
|
|
42
|
+
@click.option('-l', '--length', 'length', metavar='<str>',
|
|
43
|
+
help='Nucleotide sequence length. Multiple length should be separated by commas,'
|
|
44
|
+
'and the number of length should be consistent with the "-n, --names" option values (eg. 100,200).')
|
|
45
|
+
@click.option('-b', '--bias', 'bias', metavar='<str>',
|
|
46
|
+
help='Nucleotide sequence bias of AGCT. Multiple bias should be separated by commas (eg. 0.25,0.5,0.1,0.15).')
|
|
47
|
+
@click.option('-o', '--output-file', 'output_file',
|
|
48
|
+
metavar='<file|stdout>', type=click.File('w'),
|
|
49
|
+
help='Output file, stdout by default.')
|
|
50
|
+
@click.option('-V', '--version', 'version', help='Show author and version information.',
|
|
51
|
+
is_flag=True, is_eager=True, expose_value=False, callback=displayer.version_info)
|
|
52
|
+
def run(names, length, bias, output_file):
|
|
53
|
+
"""Generate random nucleotide sequence."""
|
|
54
|
+
if names is not None and ',' in names:
|
|
55
|
+
names = names.split(',')
|
|
56
|
+
if length is not None and ',' in length:
|
|
57
|
+
length = [int(i) for i in length.split(',')]
|
|
58
|
+
elif isinstance(length, str):
|
|
59
|
+
length = int(length)
|
|
60
|
+
if bias is not None and ',' in bias:
|
|
61
|
+
bias = [float(i) for i in bias.split(',')]
|
|
62
|
+
main(names, length, bias, output_file)
|
|
63
|
+
|
|
64
|
+
|
|
65
|
+
if __name__ == '__main__':
|
|
66
|
+
run()
|
|
@@ -0,0 +1,46 @@
|
|
|
1
|
+
#!/usr/bin/env python
|
|
2
|
+
"""
|
|
3
|
+
File: get_longest_seq_for_gene.py
|
|
4
|
+
Description: Get the longest transcript of each gene locus.
|
|
5
|
+
CreateDate: 2022/3/26
|
|
6
|
+
Author: xuwenlin
|
|
7
|
+
E-mail: wenlinxu.njfu@outlook.com
|
|
8
|
+
"""
|
|
9
|
+
from typing import Union
|
|
10
|
+
from io import TextIOWrapper
|
|
11
|
+
import click
|
|
12
|
+
from pybioinformatic import Fasta, Displayer
|
|
13
|
+
displayer = Displayer(__file__.split('/')[-1], version='0.1.0')
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
def main(fasta_file: Union[str, TextIOWrapper],
|
|
17
|
+
regula_exp: str,
|
|
18
|
+
inplace_id: bool = False,
|
|
19
|
+
out_file: TextIOWrapper = None):
|
|
20
|
+
with Fasta(fasta_file) as fa:
|
|
21
|
+
for seq_obj in fa.get_longest_seq(regula_exp, inplace_id):
|
|
22
|
+
click.echo(seq_obj, out_file)
|
|
23
|
+
|
|
24
|
+
|
|
25
|
+
@click.command(context_settings=dict(help_option_names=['-h', '--help']))
|
|
26
|
+
@click.option('-i', '--fasta_file', 'fasta_file',
|
|
27
|
+
metavar='<fasta file|stdin>', type=click.File('r'), required=True,
|
|
28
|
+
help='Input FASTA file.')
|
|
29
|
+
@click.option('-r', '--regular_expression', 'regular_expression',
|
|
30
|
+
metavar='<str>', required=True,
|
|
31
|
+
help='The name of a gene locus represented by a regular expression.')
|
|
32
|
+
@click.option('-I', '--inplace_id', 'inplace_id',
|
|
33
|
+
is_flag=True, flag_value=True,
|
|
34
|
+
help='Replace the longest sequence ID with unique ID.')
|
|
35
|
+
@click.option('-o', '--output_file', 'outfile',
|
|
36
|
+
metavar='<file|stdout>', type=click.File('w'),
|
|
37
|
+
help='Output file, stdout by default.')
|
|
38
|
+
@click.option('-V', '--version', 'version', help='Show author and version information.',
|
|
39
|
+
is_flag=True, is_eager=True, expose_value=False, callback=displayer.version_info)
|
|
40
|
+
def run(fasta_file, regular_expression, inplace_id, outfile):
|
|
41
|
+
"""Get the longest transcript of each gene locus."""
|
|
42
|
+
main(fasta_file, regular_expression, inplace_id, outfile)
|
|
43
|
+
|
|
44
|
+
|
|
45
|
+
if __name__ == '__main__':
|
|
46
|
+
run()
|
|
@@ -0,0 +1,43 @@
|
|
|
1
|
+
#!/usr/bin/env python
|
|
2
|
+
"""
|
|
3
|
+
File: get_reverse_complementary_seq.py
|
|
4
|
+
Description: Get reverse complementary sequence.
|
|
5
|
+
CreateDate: 2022/6/8
|
|
6
|
+
Author: xuwenlin
|
|
7
|
+
E-mail: wenlinxu.njfu@outlook.com
|
|
8
|
+
"""
|
|
9
|
+
from typing import Union
|
|
10
|
+
from io import TextIOWrapper
|
|
11
|
+
import click
|
|
12
|
+
from pybioinformatic import Fasta, Displayer
|
|
13
|
+
displayer = Displayer(__file__.split('/')[-1], version='0.1.0')
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
def main(fasta_file: Union[str, TextIOWrapper],
|
|
17
|
+
parse_seqids: bool = True,
|
|
18
|
+
out_file: TextIOWrapper = None):
|
|
19
|
+
with Fasta(fasta_file) as fa:
|
|
20
|
+
for nucl_obj in fa.parse(parse_seqids):
|
|
21
|
+
rev_com_seq = -nucl_obj
|
|
22
|
+
click.echo(rev_com_seq, out_file)
|
|
23
|
+
|
|
24
|
+
|
|
25
|
+
@click.command(context_settings=dict(help_option_names=['-h', '--help']))
|
|
26
|
+
@click.option('-i', '--fasta_file', 'fasta_file',
|
|
27
|
+
metavar='<fasta file|stdin>', type=click.File('r'), required=True,
|
|
28
|
+
help='Input FASTA file.')
|
|
29
|
+
@click.option('-p', '--parse_seqids', 'parse_seqids',
|
|
30
|
+
is_flag=True, flag_value=True,
|
|
31
|
+
help='Parse sequence IDs.')
|
|
32
|
+
@click.option('-o', '--output_file', 'outfile',
|
|
33
|
+
metavar='<file|stdout>', type=click.File('w'),
|
|
34
|
+
help='Output file, stdout by default.')
|
|
35
|
+
@click.option('-V', '--version', 'version', help='Show author and version information.',
|
|
36
|
+
is_flag=True, is_eager=True, expose_value=False, callback=displayer.version_info)
|
|
37
|
+
def run(fasta_file, parse_seqids, outfile):
|
|
38
|
+
"""Get reverse complementary sequence."""
|
|
39
|
+
main(fasta_file, parse_seqids, outfile)
|
|
40
|
+
|
|
41
|
+
|
|
42
|
+
if __name__ == '__main__':
|
|
43
|
+
run()
|