8415015115

Committed 25 Mar 2024 04:17AM UTC coverage: 96.061% (+9.4%) from 86.616%

Build # 8415015115

Build Type

push

github

Committed by

iskandr

Commit Message

skip IEDB tests

Run Details

1585 of 1650 relevant lines covered (96.06%)

2.85 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

78.57

/mhctools/cli/script.py

# Copyright (c) 2016. Mount Sinai School of Medicine
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from __future__ import print_function, division, absolute_import
import logging
import logging.config
import pkg_resources
import sys

import pandas as pd
from pyensembl.fasta import parse_fasta_dictionary

from .args import make_mhc_arg_parser, mhc_binding_predictor_from_args
from mhctools.logging import get_logger


logger = logging.getLogger(__name__)


arg_parser = make_mhc_arg_parser(
    prog="mhctools",
    description=("Predict MHC ligands from protein sequences."))

def add_input_args(arg_parser):
    input_group = arg_parser.add_argument_group("Inputs")
    input_group.add_argument(
        "--sequence",
        nargs="*",
        help=(
            "Peptide sequences"))
    input_group.add_argument(
        "--extract-subsequences",
        default=False,
        action="store_true",
        help=(
            "Extract subsequences from peptides supplied by --sequence or "
            "--input-peptides-file, lengths specified by "
            "--mhc-peptide-lengths argument."))
    input_group.add_argument(
        "--input-peptides-file",
        help="Path to file with one peptide per line")
    input_group.add_argument(
        "--input-fasta-file",
        help="Path to FASTA file which contains protein sequences")
    return input_group

def add_output_args(parser):
    output_group = arg_parser.add_argument_group("Outputs")
    output_group.add_argument("--output-csv", default=None)
    return output_group

add_input_args(arg_parser)
add_output_args(arg_parser)

def parse_args(args_list=None):
    if args_list is None:
        args_list = sys.argv[1:]
    return arg_parser.parse_args(args_list)

def run_predictor(args):
    predictor = mhc_binding_predictor_from_args(args)

    if args.input_fasta_file:
        input_dictionary = parse_fasta_dictionary(args.input_fasta_file)
        if not input_dictionary:
            raise ValueError(
                "No sequences could be parsed from fasta file: %s" % (
                    args.input_fasta_file))
        # Capitalize sequences
        input_dictionary = dict(
            (key, value.upper()) for (key, value) in input_dictionary.items())
        binding_predictions = predictor.predict_subsequences(input_dictionary)
    elif args.sequence:
        if args.extract_subsequences:
            binding_predictions = predictor.predict_subsequences(args.sequence)
        else:
            binding_predictions = predictor.predict_peptides(args.sequence)
    elif args.input_peptides_file:
        with open(args.input_peptides_file) as f:
            peptides = [line.strip() for line in f if line]
        if args.extract_subsequences:
            binding_predictions = predictor.predict_subsequences(peptides)
        else:
            binding_predictions = predictor.predict_peptides(peptides)
    else:
        raise ValueError(
            ("No input sequences provided, "
             "use --sequence, --input-fasta-file, or input-peptides-file"))
    return binding_predictions

def main(args_list=None):
    """
    Script to make pMHC binding predictions from amino acid sequences.

    Usage example:
        mhctools
            --sequence SFFPIQQQQQAAALLLI \
            --sequence SILQQQAQAQQAQAASSSC \
            --extract-subsequences \
            --mhc-predictor netmhc \
            --mhc-alleles HLA-A0201 H2-Db \
            --mhc-predictor netmhc \
            --output-csv epitope.csv
    """
    args = parse_args(args_list)
    binding_predictions = run_predictor(args)
    df = binding_predictions.to_dataframe()
    pd.set_option('display.max_columns', None)
    logger.info('\n%s', df)
    if args.output_csv:
        df.to_csv(args.output_csv, index=False)
        print("Wrote: %s" % args.output_csv)

1	# Copyright (c) 2016. Mount Sinai School of Medicine
2	#
3	# Licensed under the Apache License, Version 2.0 (the "License");
4	# you may not use this file except in compliance with the License.
5	# You may obtain a copy of the License at
6	#
7	# http://www.apache.org/licenses/LICENSE-2.0
8	#
9	# Unless required by applicable law or agreed to in writing, software
10	# distributed under the License is distributed on an "AS IS" BASIS,
11	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12	# See the License for the specific language governing permissions and
13	# limitations under the License.
14
15	from __future__ import print_function, division, absolute_import	3✔
16	import logging	3✔
17	import logging.config	3✔
18	import pkg_resources	3✔
19	import sys	3✔
20
21	import pandas as pd	3✔
22	from pyensembl.fasta import parse_fasta_dictionary	3✔
23
24	from .args import make_mhc_arg_parser, mhc_binding_predictor_from_args	3✔
25	from mhctools.logging import get_logger	3✔
26
27
28	logger = logging.getLogger(__name__)	3✔
29
30
31	arg_parser = make_mhc_arg_parser(	3✔
32	prog="mhctools",	3✔
33	description=("Predict MHC ligands from protein sequences."))	3✔
34
35	def add_input_args(arg_parser):	3✔
36	input_group = arg_parser.add_argument_group("Inputs")	3✔
37	input_group.add_argument(	3✔
38	"--sequence",	3✔
39	nargs="*",	3✔
40	help=(
41	"Peptide sequences"))	3✔
42	input_group.add_argument(	3✔
43	"--extract-subsequences",	3✔
44	default=False,	3✔
45	action="store_true",	3✔
46	help=(
47	"Extract subsequences from peptides supplied by --sequence or "	3✔
48	"--input-peptides-file, lengths specified by "
49	"--mhc-peptide-lengths argument."))
50	input_group.add_argument(	3✔
51	"--input-peptides-file",	3✔
52	help="Path to file with one peptide per line")	3✔
53	input_group.add_argument(	3✔
54	"--input-fasta-file",	3✔
55	help="Path to FASTA file which contains protein sequences")	3✔
56	return input_group	3✔
57
58	def add_output_args(parser):	3✔
59	output_group = arg_parser.add_argument_group("Outputs")	3✔
60	output_group.add_argument("--output-csv", default=None)	3✔
61	return output_group	3✔
62
63	add_input_args(arg_parser)	3✔
64	add_output_args(arg_parser)	3✔
65
66	def parse_args(args_list=None):	3✔
67	if args_list is None:	3✔
68	args_list = sys.argv[1:]	×
69	return arg_parser.parse_args(args_list)	3✔
70
71	def run_predictor(args):	3✔
72	predictor = mhc_binding_predictor_from_args(args)	3✔
73
74	if args.input_fasta_file:	3✔
75	input_dictionary = parse_fasta_dictionary(args.input_fasta_file)	×
76	if not input_dictionary:	×
77	raise ValueError(
78	"No sequences could be parsed from fasta file: %s" % (
79	args.input_fasta_file))
80	# Capitalize sequences
81	input_dictionary = dict(
82	(key, value.upper()) for (key, value) in input_dictionary.items())
83	binding_predictions = predictor.predict_subsequences(input_dictionary)	×
84	elif args.sequence:	3✔
85	if args.extract_subsequences:	3✔
86	binding_predictions = predictor.predict_subsequences(args.sequence)	3✔
87	else:	×
88	binding_predictions = predictor.predict_peptides(args.sequence)	3✔
89	elif args.input_peptides_file:	3✔
90	with open(args.input_peptides_file) as f:	3✔
91	peptides = [line.strip() for line in f if line]	3✔
92	if args.extract_subsequences:	3✔
93	binding_predictions = predictor.predict_subsequences(peptides)	3✔
94	else:	×
95	binding_predictions = predictor.predict_peptides(peptides)	3✔
96	else:	×
97	raise ValueError(
98	("No input sequences provided, "
99	"use --sequence, --input-fasta-file, or input-peptides-file"))
100	return binding_predictions	3✔
101
102	def main(args_list=None):	3✔
103	"""
104	Script to make pMHC binding predictions from amino acid sequences.
105
106	Usage example:
107	mhctools
108	--sequence SFFPIQQQQQAAALLLI \
109	--sequence SILQQQAQAQQAQAASSSC \
110	--extract-subsequences \
111	--mhc-predictor netmhc \
112	--mhc-alleles HLA-A0201 H2-Db \
113	--mhc-predictor netmhc \
114	--output-csv epitope.csv
115	"""
116	args = parse_args(args_list)	×
117	binding_predictions = run_predictor(args)	×
118	df = binding_predictions.to_dataframe()	×
119	pd.set_option('display.max_columns', None)	×
120	logger.info('\n%s', df)	×
121	if args.output_csv:	×
122	df.to_csv(args.output_csv, index=False)	×
123	print("Wrote: %s" % args.output_csv)	×

openvax / mhctools / 8415015115

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous