9781104697

Committed 03 Jul 2024 03:56PM UTC coverage: 88.33% (-6.4%) from 94.753%

Build Type

github

Committed by kodysy02

Commit Message

Defaulting convert_ucsc_contig_names to True for consistency with past behavior

Pull Request Pull Request #253: Defaulting convert_ucsc_contig_names to True for consistency with past behavior

Run Details

1 of 1 new or added line in 1 file covered. (100.0%)

144 existing lines in 17 files now uncovered.

1544 of 1748 relevant lines covered (88.33%)

2.65 hits per line

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

91.3

/varcode/effects/effect_prediction_coding.py

# 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 .effect_prediction_coding_frameshift import predict_frameshift_coding_effect
from .effect_prediction_coding_in_frame import predict_in_frame_coding_effect


def predict_variant_coding_effect_on_transcript(
        variant,
        transcript,
        trimmed_cdna_ref,
        trimmed_cdna_alt,
        transcript_offset):
    """
    Given a minimal cDNA ref/alt nucleotide string pair and an offset into a
    given transcript, determine the coding effect of this nucleotide substitution
    onto the translated protein.

    Parameters
    ----------
    variant : Variant

    transcript : Transcript

    trimmed_cdna_ref : str
        Reference nucleotides we expect to find in the transcript's CDS

    trimmed_cdna_alt : str
        Alternate nucleotides we're replacing the reference with

    transcript_offset : int
        Offset into the full transcript sequence of the ref->alt substitution
    """
    if not transcript.complete:
        raise ValueError(
            ("Can't annotate coding effect for %s"
             " on incomplete transcript %s" % (variant, transcript)))

    sequence = transcript.sequence

    n_ref = len(trimmed_cdna_ref)
    n_alt = len(trimmed_cdna_alt)

    # reference nucleotides found on the transcript, if these don't match
    # what we were told to expect from the variant then raise an exception
    ref_nucleotides_from_transcript = str(
        sequence[transcript_offset:transcript_offset + n_ref])

    # Make sure that the reference sequence agrees with what we expected
    # from the VCF
    assert ref_nucleotides_from_transcript == trimmed_cdna_ref, \
        "%s: expected ref '%s' at offset %d of %s, transcript has '%s'" % (
            variant,
            trimmed_cdna_ref,
            transcript_offset,
            transcript,
            ref_nucleotides_from_transcript)

    start_codon_offset = transcript.first_start_codon_spliced_offset
    stop_codon_offset = transcript.last_stop_codon_spliced_offset

    cds_len = stop_codon_offset - start_codon_offset + 1

    if cds_len < 3:
        raise ValueError(
            "Coding sequence for %s is too short: '%s'" % (
                transcript,
                transcript.sequence[start_codon_offset:stop_codon_offset + 1]))

    if n_ref == 0 and transcript.strand == "-":
        # By convention, genomic insertions happen *after* their base 1 position on
        # a chromosome. On the reverse strand, however, an insertion has to go
        # before the nucleotide at some transcript offset.
        # Example:
        #    chromosome sequence:
        #        TTT|GATCTCGTA|CCC
        #    transcript on reverse strand:
        #        CCC|ATGCTCTAG|TTT
        #    where the CDS is emphasized:
        #            ATGCTCTAG
        # If we have a genomic insertion g.6insATT
        # the genomic sequence becomes:
        #       TTT|GAT_ATT_CTCGTA|CCC
        # (insert the "ATT" after the "T" at position 6)
        # On the reverse strand this becomes:
        #       CCC|ATGCTC_TTA_TAG|TTT
        # (insert the "ATT" *before* the "T" at position 10)
        #
        # To preserve the interpretation of the start offset as the base
        # before the insertion, need to subtract one
        cds_offset = transcript_offset - start_codon_offset - 1
    else:
        cds_offset = transcript_offset - start_codon_offset

    assert cds_offset < cds_len, \
        "Expected CDS offset (%d) < |CDS| (%d) for %s on %s" % (
            cds_offset, cds_len, variant, transcript)

    sequence_from_start_codon = str(sequence[start_codon_offset:])

    # is this an in-frame mutations?
    if (n_ref - n_alt) % 3 == 0:
        return predict_in_frame_coding_effect(
            variant=variant,
            transcript=transcript,
            trimmed_cdna_ref=trimmed_cdna_ref,
            trimmed_cdna_alt=trimmed_cdna_alt,
            cds_offset=cds_offset,
            sequence_from_start_codon=sequence_from_start_codon)
    else:
        return predict_frameshift_coding_effect(
            variant=variant,
            transcript=transcript,
            trimmed_cdna_ref=trimmed_cdna_ref,
            trimmed_cdna_alt=trimmed_cdna_alt,
            cds_offset=cds_offset,
            sequence_from_start_codon=sequence_from_start_codon)

1	# Licensed under the Apache License, Version 2.0 (the "License");
2	# you may not use this file except in compliance with the License.
3	# You may obtain a copy of the License at
4	#
5	# http://www.apache.org/licenses/LICENSE-2.0
6	#
7	# Unless required by applicable law or agreed to in writing, software
8	# distributed under the License is distributed on an "AS IS" BASIS,
9	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
10	# See the License for the specific language governing permissions and
11	# limitations under the License.
12
13	from .effect_prediction_coding_frameshift import predict_frameshift_coding_effect	3✔
14	from .effect_prediction_coding_in_frame import predict_in_frame_coding_effect	3✔
15
16
17	def predict_variant_coding_effect_on_transcript(	3✔
18	variant,
19	transcript,
20	trimmed_cdna_ref,
21	trimmed_cdna_alt,
22	transcript_offset):
23	"""
24	Given a minimal cDNA ref/alt nucleotide string pair and an offset into a
25	given transcript, determine the coding effect of this nucleotide substitution
26	onto the translated protein.
27
28	Parameters
29	----------
30	variant : Variant
31
32	transcript : Transcript
33
34	trimmed_cdna_ref : str
35	Reference nucleotides we expect to find in the transcript's CDS
36
37	trimmed_cdna_alt : str
38	Alternate nucleotides we're replacing the reference with
39
40	transcript_offset : int
41	Offset into the full transcript sequence of the ref->alt substitution
42	"""
43	if not transcript.complete:	3✔
UNCOV 44	raise ValueError(	×
45	("Can't annotate coding effect for %s"
46	" on incomplete transcript %s" % (variant, transcript)))
47
48	sequence = transcript.sequence	3✔
49
50	n_ref = len(trimmed_cdna_ref)	3✔
51	n_alt = len(trimmed_cdna_alt)	3✔
52
53	# reference nucleotides found on the transcript, if these don't match
54	# what we were told to expect from the variant then raise an exception
55	ref_nucleotides_from_transcript = str(	3✔
56	sequence[transcript_offset:transcript_offset + n_ref])
57
58	# Make sure that the reference sequence agrees with what we expected
59	# from the VCF
60	assert ref_nucleotides_from_transcript == trimmed_cdna_ref, \	3✔
61	"%s: expected ref '%s' at offset %d of %s, transcript has '%s'" % (
62	variant,
63	trimmed_cdna_ref,
64	transcript_offset,
65	transcript,
66	ref_nucleotides_from_transcript)
67
68	start_codon_offset = transcript.first_start_codon_spliced_offset	3✔
69	stop_codon_offset = transcript.last_stop_codon_spliced_offset	3✔
70
71	cds_len = stop_codon_offset - start_codon_offset + 1	3✔
72
73	if cds_len < 3:	3✔
UNCOV 74	raise ValueError(	×
75	"Coding sequence for %s is too short: '%s'" % (
76	transcript,
77	transcript.sequence[start_codon_offset:stop_codon_offset + 1]))
78
79	if n_ref == 0 and transcript.strand == "-":	3✔
80	# By convention, genomic insertions happen after their base 1 position on
81	# a chromosome. On the reverse strand, however, an insertion has to go
82	# before the nucleotide at some transcript offset.
83	# Example:
84	# chromosome sequence:
85	# TTT\|GATCTCGTA\|CCC
86	# transcript on reverse strand:
87	# CCC\|ATGCTCTAG\|TTT
88	# where the CDS is emphasized:
89	# ATGCTCTAG
90	# If we have a genomic insertion g.6insATT
91	# the genomic sequence becomes:
92	# TTT\|GAT_ATT_CTCGTA\|CCC
93	# (insert the "ATT" after the "T" at position 6)
94	# On the reverse strand this becomes:
95	# CCC\|ATGCTC_TTA_TAG\|TTT
96	# (insert the "ATT" before the "T" at position 10)
97	#
98	# To preserve the interpretation of the start offset as the base
99	# before the insertion, need to subtract one
100	cds_offset = transcript_offset - start_codon_offset - 1	3✔
101	else:
102	cds_offset = transcript_offset - start_codon_offset	3✔
103
104	assert cds_offset < cds_len, \	3✔
105	"Expected CDS offset (%d) < \|CDS\| (%d) for %s on %s" % (
106	cds_offset, cds_len, variant, transcript)
107
108	sequence_from_start_codon = str(sequence[start_codon_offset:])	3✔
109
110	# is this an in-frame mutations?
111	if (n_ref - n_alt) % 3 == 0:	3✔
112	return predict_in_frame_coding_effect(	3✔
113	variant=variant,
114	transcript=transcript,
115	trimmed_cdna_ref=trimmed_cdna_ref,
116	trimmed_cdna_alt=trimmed_cdna_alt,
117	cds_offset=cds_offset,
118	sequence_from_start_codon=sequence_from_start_codon)
119	else:
120	return predict_frameshift_coding_effect(	3✔
121	variant=variant,
122	transcript=transcript,
123	trimmed_cdna_ref=trimmed_cdna_ref,
124	trimmed_cdna_alt=trimmed_cdna_alt,
125	cds_offset=cds_offset,
126	sequence_from_start_codon=sequence_from_start_codon)

openvax / varcode / 9781104697

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