cdot 0.2.28__tar.gz → 0.2.30__tar.gz
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.
- {cdot-0.2.28/cdot.egg-info → cdot-0.2.30}/PKG-INFO +19 -18
- {cdot-0.2.28 → cdot-0.2.30}/README.md +17 -17
- {cdot-0.2.28 → cdot-0.2.30}/cdot/__init__.py +1 -1
- {cdot-0.2.28 → cdot-0.2.30}/cdot/hgvs/__init__.py +3 -0
- cdot-0.2.30/cdot/hgvs/_version_replacement_blocklist.py +87 -0
- {cdot-0.2.28 → cdot-0.2.30}/cdot/hgvs/clean.py +152 -60
- {cdot-0.2.28 → cdot-0.2.30}/cdot/hgvs/dataproviders/json_data_provider.py +165 -8
- {cdot-0.2.28 → cdot-0.2.30}/cdot/hgvs/gene_hgvs.py +131 -9
- cdot-0.2.30/cdot/hgvs/version_safety.py +345 -0
- {cdot-0.2.28 → cdot-0.2.30}/cdot/models.py +5 -1
- {cdot-0.2.28 → cdot-0.2.30/cdot.egg-info}/PKG-INFO +19 -18
- {cdot-0.2.28 → cdot-0.2.30}/cdot.egg-info/SOURCES.txt +5 -10
- {cdot-0.2.28 → cdot-0.2.30}/cdot.egg-info/requires.txt +1 -0
- cdot-0.2.30/cdot.egg-info/top_level.txt +1 -0
- {cdot-0.2.28 → cdot-0.2.30}/pyproject.toml +5 -1
- {cdot-0.2.28 → cdot-0.2.30}/tests/test_clean_hgvs.py +243 -3
- {cdot-0.2.28 → cdot-0.2.30}/tests/test_gene_hgvs.py +88 -0
- cdot-0.2.30/tests/test_version_safety.py +331 -0
- cdot-0.2.30/tests/test_version_safety_real_records.py +89 -0
- cdot-0.2.28/analysis/benchmark_resolution.py +0 -332
- cdot-0.2.28/analysis/build_clinvar_pairs.py +0 -101
- cdot-0.2.28/analysis/clean_hgvs_search_csvs.py +0 -116
- cdot-0.2.28/analysis/combine_csv.py +0 -11
- cdot-0.2.28/analysis/compare_providers.py +0 -35
- cdot-0.2.28/analysis/compute_benchmark.py +0 -125
- cdot-0.2.28/analysis/compute_coverage.py +0 -101
- cdot-0.2.28/analysis/inject_and_clean.py +0 -501
- cdot-0.2.28/analysis/investigate_fails.py +0 -59
- cdot-0.2.28/cdot.egg-info/top_level.txt +0 -8
- {cdot-0.2.28 → cdot-0.2.30}/LICENSE +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/cdot/data_release.py +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/cdot/hgvs/dataproviders/__init__.py +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/cdot/hgvs/dataproviders/ensembl_tark_data_provider.py +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/cdot/hgvs/dataproviders/fasta_seqfetcher.py +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/cdot/hgvs/dataproviders/seqfetcher.py +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/cdot/pyhgvs/__init__.py +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/cdot/pyhgvs/pyhgvs_transcript.py +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/cdot.egg-info/dependency_links.txt +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/setup.cfg +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/tests/test_gff_parsers.py +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/tests/test_json_data_provider_ensembl.py +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/tests/test_json_data_provider_refseq.py +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/tests/test_models.py +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/tests/test_pyhgvs.py +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/tests/test_rest_data_provider_prefetch.py +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/tests/test_struct_dict_compat.py +0 -0
- {cdot-0.2.28 → cdot-0.2.30}/tests/test_uta_conversion.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: cdot
|
|
3
|
-
Version: 0.2.
|
|
3
|
+
Version: 0.2.30
|
|
4
4
|
Summary: Transcripts for HGVS libraries
|
|
5
5
|
Author-email: Dave Lawrence <davmlaw@gmail.com>
|
|
6
6
|
License: MIT
|
|
@@ -35,6 +35,7 @@ Requires-Dist: pysam; extra == "test"
|
|
|
35
35
|
Provides-Extra: paper
|
|
36
36
|
Requires-Dist: snakemake; extra == "paper"
|
|
37
37
|
Requires-Dist: vibepaper; extra == "paper"
|
|
38
|
+
Requires-Dist: weasyprint; extra == "paper"
|
|
38
39
|
Dynamic: license-file
|
|
39
40
|
|
|
40
41
|
# cdot
|
|
@@ -57,7 +58,7 @@ files (GTF/GFF3) into compact JSON** and ships fast loaders for the HGVS librari
|
|
|
57
58
|
|
|
58
59
|
Because it reads the released annotation files directly, cdot covers **1.58 million transcript/genome
|
|
59
60
|
alignments**, including historical transcript versions - vs ~141k in UTA (v.20210129) - which matters
|
|
60
|
-
when resolving legacy HGVS. See [cdot vs UTA](docs/cdot_vs_uta.md) for the trade-offs.
|
|
61
|
+
when resolving legacy HGVS. See [cdot vs UTA](https://github.com/SACGF/cdot/blob/main/docs/cdot_vs_uta.md) for the trade-offs.
|
|
61
62
|
|
|
62
63
|
Recent changes are in the [changelog](https://github.com/SACGF/cdot/blob/main/CHANGELOG.md).
|
|
63
64
|
|
|
@@ -70,7 +71,7 @@ pip install cdot
|
|
|
70
71
|
Optional extras:
|
|
71
72
|
|
|
72
73
|
```
|
|
73
|
-
pip install cdot[fasta] # local genome FASTA sequence fetching (pysam) - needed for the PyHGVS example below
|
|
74
|
+
pip install 'cdot[fasta]' # local genome FASTA sequence fetching (pysam) - needed for the PyHGVS example below. Quotes are required in zsh (macOS default).
|
|
74
75
|
```
|
|
75
76
|
|
|
76
77
|
(`hgvs` is a core dependency, so the biocommons HGVS examples work out of the box.)
|
|
@@ -96,16 +97,16 @@ var_c = hp.parse_hgvs_variant('NM_001637.3:c.1582G>A')
|
|
|
96
97
|
am.c_to_g(var_c)
|
|
97
98
|
```
|
|
98
99
|
|
|
99
|
-
[more Biocommons examples](docs/examples_biocommons.md):
|
|
100
|
+
[more Biocommons examples](https://github.com/SACGF/cdot/blob/main/docs/examples_biocommons.md):
|
|
100
101
|
|
|
101
102
|
> **Tip:** cdot provides many transcripts that aren't in SeqRepo, so the default sequence fetcher will
|
|
102
103
|
> raise `HGVSDataNotAvailableError` for them. You almost always want to supply a
|
|
103
|
-
> [`FastaSeqFetcher`](docs/fasta_seqfetcher.md) (chained after SeqRepo) so every cdot transcript
|
|
104
|
+
> [`FastaSeqFetcher`](https://github.com/SACGF/cdot/blob/main/docs/fasta_seqfetcher.md) (chained after SeqRepo) so every cdot transcript
|
|
104
105
|
> resolves against a local genome FASTA.
|
|
105
106
|
|
|
106
|
-
For fixing messy HGVS input and fast bulk processing, see [Advanced usage](docs/advanced_usage.md).
|
|
107
|
+
For fixing messy HGVS input and fast bulk processing, see [Advanced usage](https://github.com/SACGF/cdot/blob/main/docs/advanced_usage.md).
|
|
107
108
|
|
|
108
|
-
[PyHGVS](https://github.com/counsyl/hgvs) example (needs `pip install cdot[fasta]` for pysam):
|
|
109
|
+
[PyHGVS](https://github.com/counsyl/hgvs) example (needs `pip install 'cdot[fasta]'` for pysam):
|
|
109
110
|
|
|
110
111
|
```
|
|
111
112
|
import pyhgvs
|
|
@@ -118,35 +119,35 @@ factory = RESTPyHGVSTranscriptFactory()
|
|
|
118
119
|
pyhgvs.parse_hgvs_name('NM_001637.3:c.1582G>A', genome, get_transcript=factory.get_transcript_grch37)
|
|
119
120
|
```
|
|
120
121
|
|
|
121
|
-
[more PyHGVS examples](docs/examples_pyhgvs.md):
|
|
122
|
+
[more PyHGVS examples](https://github.com/SACGF/cdot/blob/main/docs/examples_pyhgvs.md):
|
|
122
123
|
|
|
123
124
|
## Documentation
|
|
124
125
|
|
|
125
|
-
See [docs/](docs
|
|
126
|
+
See [docs/](https://github.com/SACGF/cdot/tree/main/docs) for reference and how-to guides:
|
|
126
127
|
|
|
127
|
-
* [JSON data format](docs/json_data_format.md) - every field in a cdot JSON(.gz) file
|
|
128
|
-
* [Coordinates & exon alignments](docs/coordinates_and_exons.md) - how exon coordinates and gap strings work
|
|
129
|
-
* [Advanced usage](docs/advanced_usage.md) - fixing messy HGVS input, and bulk read-ahead retrieval
|
|
128
|
+
* [JSON data format](https://github.com/SACGF/cdot/blob/main/docs/json_data_format.md) - every field in a cdot JSON(.gz) file
|
|
129
|
+
* [Coordinates & exon alignments](https://github.com/SACGF/cdot/blob/main/docs/coordinates_and_exons.md) - how exon coordinates and gap strings work
|
|
130
|
+
* [Advanced usage](https://github.com/SACGF/cdot/blob/main/docs/advanced_usage.md) - fixing messy HGVS input, and bulk read-ahead retrieval
|
|
130
131
|
|
|
131
|
-
See the [docs index](docs/README.md) for the full list (examples, FastaSeqFetcher, creating data, cdot vs UTA, …).
|
|
132
|
+
See the [docs index](https://github.com/SACGF/cdot/blob/main/docs/README.md) for the full list (examples, FastaSeqFetcher, creating data, cdot vs UTA, …).
|
|
132
133
|
|
|
133
134
|
## Q. What's the performance like?
|
|
134
135
|
|
|
135
136
|
Resolving real ClinVar c.HGVS to genomic coordinates (GRCh38, biocommons HGVS, local sequence fetching):
|
|
136
137
|
|
|
137
138
|
* UTA public DB: ~1-1.5 seconds / transcript
|
|
138
|
-
* cdot REST service: ~30 HGVS/second sequential, **~500 HGVS/second** with [`prefetch()`](docs/advanced_usage.md) batch cache-warming
|
|
139
|
+
* cdot REST service: ~30 HGVS/second sequential, **~500 HGVS/second** with [`prefetch()`](https://github.com/SACGF/cdot/blob/main/docs/advanced_usage.md) batch cache-warming
|
|
139
140
|
* cdot JSON.gz (local): 500-1k/second
|
|
140
141
|
|
|
141
142
|
`prefetch()` warms every transcript in one batch round-trip up front, so bulk resolution over the REST
|
|
142
143
|
service runs almost entirely from cache - closing most of the gap to local JSON.gz (~16x faster end-to-end
|
|
143
|
-
on 500 variants). Reproduce with `
|
|
144
|
+
on 500 variants). Reproduce with `paper/scripts/benchmark_resolution.py`.
|
|
144
145
|
|
|
145
146
|
## Q. Where can I download the JSON.gz files?
|
|
146
147
|
|
|
147
148
|
[Download from GitHub releases](https://github.com/SACGF/cdot/releases) - RefSeq (37/38) - 72M, Ensembl (37/38) 61M
|
|
148
149
|
|
|
149
|
-
Details on what the files contain [here](docs/release_files.md)
|
|
150
|
+
Details on what the files contain [here](https://github.com/SACGF/cdot/blob/main/docs/release_files.md)
|
|
150
151
|
|
|
151
152
|
## Q. How does this compare to Universal Transcript Archive?
|
|
152
153
|
|
|
@@ -155,11 +156,11 @@ Both projects have similar goals of providing transcripts for loading HGVS, but
|
|
|
155
156
|
* UTA aligns sequences, then stores coordinates in an SQL database.
|
|
156
157
|
* cdot convert existing Ensembl/RefSeq GTFs into JSON
|
|
157
158
|
|
|
158
|
-
See [cdot vs UTA](docs/cdot_vs_uta.md) for more details
|
|
159
|
+
See [cdot vs UTA](https://github.com/SACGF/cdot/blob/main/docs/cdot_vs_uta.md) for more details
|
|
159
160
|
|
|
160
161
|
## Q. How do you store transcripts in JSON?
|
|
161
162
|
|
|
162
|
-
See the **[JSON data format reference](docs/json_data_format.md)** for a full description of every field, with a machine-readable [JSON Schema](docs/cdot-json-schema.json) alongside it. [Coordinates & exon alignments](docs/coordinates_and_exons.md) explains how exon coordinates and the alignment gap strings work. See also [design notes](docs/design_notes.md) on why the format looks the way it does.
|
|
163
|
+
See the **[JSON data format reference](https://github.com/SACGF/cdot/blob/main/docs/json_data_format.md)** for a full description of every field, with a machine-readable [JSON Schema](https://github.com/SACGF/cdot/blob/main/docs/cdot-json-schema.json) alongside it. [Coordinates & exon alignments](https://github.com/SACGF/cdot/blob/main/docs/coordinates_and_exons.md) explains how exon coordinates and the alignment gap strings work. See also [design notes](https://github.com/SACGF/cdot/blob/main/docs/design_notes.md) on why the format looks the way it does.
|
|
163
164
|
|
|
164
165
|
You can also read the data with typed Python objects (no extra install required):
|
|
165
166
|
|
|
@@ -18,7 +18,7 @@ files (GTF/GFF3) into compact JSON** and ships fast loaders for the HGVS librari
|
|
|
18
18
|
|
|
19
19
|
Because it reads the released annotation files directly, cdot covers **1.58 million transcript/genome
|
|
20
20
|
alignments**, including historical transcript versions - vs ~141k in UTA (v.20210129) - which matters
|
|
21
|
-
when resolving legacy HGVS. See [cdot vs UTA](docs/cdot_vs_uta.md) for the trade-offs.
|
|
21
|
+
when resolving legacy HGVS. See [cdot vs UTA](https://github.com/SACGF/cdot/blob/main/docs/cdot_vs_uta.md) for the trade-offs.
|
|
22
22
|
|
|
23
23
|
Recent changes are in the [changelog](https://github.com/SACGF/cdot/blob/main/CHANGELOG.md).
|
|
24
24
|
|
|
@@ -31,7 +31,7 @@ pip install cdot
|
|
|
31
31
|
Optional extras:
|
|
32
32
|
|
|
33
33
|
```
|
|
34
|
-
pip install cdot[fasta] # local genome FASTA sequence fetching (pysam) - needed for the PyHGVS example below
|
|
34
|
+
pip install 'cdot[fasta]' # local genome FASTA sequence fetching (pysam) - needed for the PyHGVS example below. Quotes are required in zsh (macOS default).
|
|
35
35
|
```
|
|
36
36
|
|
|
37
37
|
(`hgvs` is a core dependency, so the biocommons HGVS examples work out of the box.)
|
|
@@ -57,16 +57,16 @@ var_c = hp.parse_hgvs_variant('NM_001637.3:c.1582G>A')
|
|
|
57
57
|
am.c_to_g(var_c)
|
|
58
58
|
```
|
|
59
59
|
|
|
60
|
-
[more Biocommons examples](docs/examples_biocommons.md):
|
|
60
|
+
[more Biocommons examples](https://github.com/SACGF/cdot/blob/main/docs/examples_biocommons.md):
|
|
61
61
|
|
|
62
62
|
> **Tip:** cdot provides many transcripts that aren't in SeqRepo, so the default sequence fetcher will
|
|
63
63
|
> raise `HGVSDataNotAvailableError` for them. You almost always want to supply a
|
|
64
|
-
> [`FastaSeqFetcher`](docs/fasta_seqfetcher.md) (chained after SeqRepo) so every cdot transcript
|
|
64
|
+
> [`FastaSeqFetcher`](https://github.com/SACGF/cdot/blob/main/docs/fasta_seqfetcher.md) (chained after SeqRepo) so every cdot transcript
|
|
65
65
|
> resolves against a local genome FASTA.
|
|
66
66
|
|
|
67
|
-
For fixing messy HGVS input and fast bulk processing, see [Advanced usage](docs/advanced_usage.md).
|
|
67
|
+
For fixing messy HGVS input and fast bulk processing, see [Advanced usage](https://github.com/SACGF/cdot/blob/main/docs/advanced_usage.md).
|
|
68
68
|
|
|
69
|
-
[PyHGVS](https://github.com/counsyl/hgvs) example (needs `pip install cdot[fasta]` for pysam):
|
|
69
|
+
[PyHGVS](https://github.com/counsyl/hgvs) example (needs `pip install 'cdot[fasta]'` for pysam):
|
|
70
70
|
|
|
71
71
|
```
|
|
72
72
|
import pyhgvs
|
|
@@ -79,35 +79,35 @@ factory = RESTPyHGVSTranscriptFactory()
|
|
|
79
79
|
pyhgvs.parse_hgvs_name('NM_001637.3:c.1582G>A', genome, get_transcript=factory.get_transcript_grch37)
|
|
80
80
|
```
|
|
81
81
|
|
|
82
|
-
[more PyHGVS examples](docs/examples_pyhgvs.md):
|
|
82
|
+
[more PyHGVS examples](https://github.com/SACGF/cdot/blob/main/docs/examples_pyhgvs.md):
|
|
83
83
|
|
|
84
84
|
## Documentation
|
|
85
85
|
|
|
86
|
-
See [docs/](docs
|
|
86
|
+
See [docs/](https://github.com/SACGF/cdot/tree/main/docs) for reference and how-to guides:
|
|
87
87
|
|
|
88
|
-
* [JSON data format](docs/json_data_format.md) - every field in a cdot JSON(.gz) file
|
|
89
|
-
* [Coordinates & exon alignments](docs/coordinates_and_exons.md) - how exon coordinates and gap strings work
|
|
90
|
-
* [Advanced usage](docs/advanced_usage.md) - fixing messy HGVS input, and bulk read-ahead retrieval
|
|
88
|
+
* [JSON data format](https://github.com/SACGF/cdot/blob/main/docs/json_data_format.md) - every field in a cdot JSON(.gz) file
|
|
89
|
+
* [Coordinates & exon alignments](https://github.com/SACGF/cdot/blob/main/docs/coordinates_and_exons.md) - how exon coordinates and gap strings work
|
|
90
|
+
* [Advanced usage](https://github.com/SACGF/cdot/blob/main/docs/advanced_usage.md) - fixing messy HGVS input, and bulk read-ahead retrieval
|
|
91
91
|
|
|
92
|
-
See the [docs index](docs/README.md) for the full list (examples, FastaSeqFetcher, creating data, cdot vs UTA, …).
|
|
92
|
+
See the [docs index](https://github.com/SACGF/cdot/blob/main/docs/README.md) for the full list (examples, FastaSeqFetcher, creating data, cdot vs UTA, …).
|
|
93
93
|
|
|
94
94
|
## Q. What's the performance like?
|
|
95
95
|
|
|
96
96
|
Resolving real ClinVar c.HGVS to genomic coordinates (GRCh38, biocommons HGVS, local sequence fetching):
|
|
97
97
|
|
|
98
98
|
* UTA public DB: ~1-1.5 seconds / transcript
|
|
99
|
-
* cdot REST service: ~30 HGVS/second sequential, **~500 HGVS/second** with [`prefetch()`](docs/advanced_usage.md) batch cache-warming
|
|
99
|
+
* cdot REST service: ~30 HGVS/second sequential, **~500 HGVS/second** with [`prefetch()`](https://github.com/SACGF/cdot/blob/main/docs/advanced_usage.md) batch cache-warming
|
|
100
100
|
* cdot JSON.gz (local): 500-1k/second
|
|
101
101
|
|
|
102
102
|
`prefetch()` warms every transcript in one batch round-trip up front, so bulk resolution over the REST
|
|
103
103
|
service runs almost entirely from cache - closing most of the gap to local JSON.gz (~16x faster end-to-end
|
|
104
|
-
on 500 variants). Reproduce with `
|
|
104
|
+
on 500 variants). Reproduce with `paper/scripts/benchmark_resolution.py`.
|
|
105
105
|
|
|
106
106
|
## Q. Where can I download the JSON.gz files?
|
|
107
107
|
|
|
108
108
|
[Download from GitHub releases](https://github.com/SACGF/cdot/releases) - RefSeq (37/38) - 72M, Ensembl (37/38) 61M
|
|
109
109
|
|
|
110
|
-
Details on what the files contain [here](docs/release_files.md)
|
|
110
|
+
Details on what the files contain [here](https://github.com/SACGF/cdot/blob/main/docs/release_files.md)
|
|
111
111
|
|
|
112
112
|
## Q. How does this compare to Universal Transcript Archive?
|
|
113
113
|
|
|
@@ -116,11 +116,11 @@ Both projects have similar goals of providing transcripts for loading HGVS, but
|
|
|
116
116
|
* UTA aligns sequences, then stores coordinates in an SQL database.
|
|
117
117
|
* cdot convert existing Ensembl/RefSeq GTFs into JSON
|
|
118
118
|
|
|
119
|
-
See [cdot vs UTA](docs/cdot_vs_uta.md) for more details
|
|
119
|
+
See [cdot vs UTA](https://github.com/SACGF/cdot/blob/main/docs/cdot_vs_uta.md) for more details
|
|
120
120
|
|
|
121
121
|
## Q. How do you store transcripts in JSON?
|
|
122
122
|
|
|
123
|
-
See the **[JSON data format reference](docs/json_data_format.md)** for a full description of every field, with a machine-readable [JSON Schema](docs/cdot-json-schema.json) alongside it. [Coordinates & exon alignments](docs/coordinates_and_exons.md) explains how exon coordinates and the alignment gap strings work. See also [design notes](docs/design_notes.md) on why the format looks the way it does.
|
|
123
|
+
See the **[JSON data format reference](https://github.com/SACGF/cdot/blob/main/docs/json_data_format.md)** for a full description of every field, with a machine-readable [JSON Schema](https://github.com/SACGF/cdot/blob/main/docs/cdot-json-schema.json) alongside it. [Coordinates & exon alignments](https://github.com/SACGF/cdot/blob/main/docs/coordinates_and_exons.md) explains how exon coordinates and the alignment gap strings work. See also [design notes](https://github.com/SACGF/cdot/blob/main/docs/design_notes.md) on why the format looks the way it does.
|
|
124
124
|
|
|
125
125
|
You can also read the data with typed Python objects (no extra install required):
|
|
126
126
|
|
|
@@ -18,8 +18,11 @@ from cdot.hgvs.gene_hgvs import (
|
|
|
18
18
|
consortium_of,
|
|
19
19
|
DEFAULT_CONSORTIUM,
|
|
20
20
|
DEFAULT_TAG_PRIORITY,
|
|
21
|
+
DEFAULT_UNSAFE_VERSION_POLICY,
|
|
21
22
|
fix_hgvs,
|
|
22
23
|
rank_transcripts_for_gene,
|
|
23
24
|
resolve_gene_hgvs,
|
|
24
25
|
resolve_transcript_version,
|
|
26
|
+
UnsafeVersionPolicy,
|
|
25
27
|
)
|
|
28
|
+
from cdot.hgvs.version_safety import intrinsic_cds_structure
|
|
@@ -0,0 +1,87 @@
|
|
|
1
|
+
"""Transcript-version re-placement blocklist (GENERATED - do not edit).
|
|
2
|
+
|
|
3
|
+
Regenerate with generate_transcript_data/generate_version_replacement_blocklist.py.
|
|
4
|
+
Source: cdot-0.2.33.all-builds-refseq-grch37_grch38_t2t-chm13v2.0.json.gz (builds: GRCh37, GRCh38).
|
|
5
|
+
|
|
6
|
+
Each (accession, requested_version, substitute_version) is a substitution whose
|
|
7
|
+
intrinsic CDS structure and alignment gaps match (so the structural safety check
|
|
8
|
+
would call it coordinate-safe) but whose genomic CDS placement differs, so it is
|
|
9
|
+
refused by is_version_substitution_safe even when the requested version is absent
|
|
10
|
+
from the loaded data (the case the provider cannot recompute).
|
|
11
|
+
"""
|
|
12
|
+
KNOWN_REPLACEMENT_SUBSTITUTIONS = frozenset({
|
|
13
|
+
('NM_000910', 2, 3),
|
|
14
|
+
('NM_000910', 2, 4),
|
|
15
|
+
('NM_000910', 3, 2),
|
|
16
|
+
('NM_000910', 4, 2),
|
|
17
|
+
('NM_001005567', 2, 3),
|
|
18
|
+
('NM_001005567', 3, 2),
|
|
19
|
+
('NM_001011553', 2, 4),
|
|
20
|
+
('NM_001011553', 3, 4),
|
|
21
|
+
('NM_001011553', 4, 2),
|
|
22
|
+
('NM_001011553', 4, 3),
|
|
23
|
+
('NM_001012276', 1, 3),
|
|
24
|
+
('NM_001012276', 3, 1),
|
|
25
|
+
('NM_001021', 3, 4),
|
|
26
|
+
('NM_001021', 3, 5),
|
|
27
|
+
('NM_001021', 3, 6),
|
|
28
|
+
('NM_001021', 4, 3),
|
|
29
|
+
('NM_001021', 5, 3),
|
|
30
|
+
('NM_001021', 6, 3),
|
|
31
|
+
('NM_001024661', 1, 2),
|
|
32
|
+
('NM_001024661', 2, 1),
|
|
33
|
+
('NM_001081450', 1, 2),
|
|
34
|
+
('NM_001081450', 1, 3),
|
|
35
|
+
('NM_001081450', 2, 1),
|
|
36
|
+
('NM_001081450', 3, 1),
|
|
37
|
+
('NM_001142273', 1, 2),
|
|
38
|
+
('NM_001142273', 2, 1),
|
|
39
|
+
('NM_001142274', 1, 2),
|
|
40
|
+
('NM_001142274', 2, 1),
|
|
41
|
+
('NM_001146181', 1, 2),
|
|
42
|
+
('NM_001146181', 1, 3),
|
|
43
|
+
('NM_001146181', 1, 4),
|
|
44
|
+
('NM_001146181', 2, 1),
|
|
45
|
+
('NM_001146181', 3, 1),
|
|
46
|
+
('NM_001146181', 4, 1),
|
|
47
|
+
('NM_001207051', 1, 2),
|
|
48
|
+
('NM_001207051', 2, 1),
|
|
49
|
+
('NM_001276343', 1, 2),
|
|
50
|
+
('NM_001276343', 1, 3),
|
|
51
|
+
('NM_001276343', 2, 1),
|
|
52
|
+
('NM_001276343', 3, 1),
|
|
53
|
+
('NM_001365429', 1, 2),
|
|
54
|
+
('NM_001365429', 2, 1),
|
|
55
|
+
('NM_004066', 1, 2),
|
|
56
|
+
('NM_004066', 1, 3),
|
|
57
|
+
('NM_004066', 2, 1),
|
|
58
|
+
('NM_004066', 3, 1),
|
|
59
|
+
('NM_006864', 2, 3),
|
|
60
|
+
('NM_006864', 2, 4),
|
|
61
|
+
('NM_006864', 3, 2),
|
|
62
|
+
('NM_006864', 4, 2),
|
|
63
|
+
('NM_015282', 2, 3),
|
|
64
|
+
('NM_015282', 3, 2),
|
|
65
|
+
('NM_018263', 4, 6),
|
|
66
|
+
('NM_018263', 5, 6),
|
|
67
|
+
('NM_018263', 6, 4),
|
|
68
|
+
('NM_018263', 6, 5),
|
|
69
|
+
('NM_022661', 2, 3),
|
|
70
|
+
('NM_022661', 2, 4),
|
|
71
|
+
('NM_022661', 3, 2),
|
|
72
|
+
('NM_022661', 4, 2),
|
|
73
|
+
('NM_024318', 2, 3),
|
|
74
|
+
('NM_024318', 3, 2),
|
|
75
|
+
('NM_024318', 3, 4),
|
|
76
|
+
('NM_024318', 4, 3),
|
|
77
|
+
('NM_032461', 2, 3),
|
|
78
|
+
('NM_032461', 2, 4),
|
|
79
|
+
('NM_032461', 3, 2),
|
|
80
|
+
('NM_032461', 4, 2),
|
|
81
|
+
('NM_183372', 4, 5),
|
|
82
|
+
('NM_183372', 4, 6),
|
|
83
|
+
('NM_183372', 5, 4),
|
|
84
|
+
('NM_183372', 6, 4),
|
|
85
|
+
('XM_003846302', 1, 2),
|
|
86
|
+
('XM_003846302', 2, 1),
|
|
87
|
+
})
|