Merge pull request #444 from apriltuesday/add-vcv-id

Issue 434: Add VCV IDs to evidence strings
EBIvariation · Oct 17, 2024 · b4fdf36 · b4fdf36
2 parents bd29fe7 + f361ec1
commit b4fdf36
Show file tree

Hide file tree

Showing 14 changed files with 1,110 additions and 1,094 deletions.
diff --git a/OT_SCHEMA_VERSION b/OT_SCHEMA_VERSION
@@ -1 +1 @@
-2.8.0
+2.8.1
diff --git a/README.md b/README.md
@@ -170,3 +170,9 @@ for record in ClinVarDataset('/path/to/clinvar.xml.gz'):
     # e.g. RCV001842692: 3_38633214_G_C => Cardiac arrhythmia
     print(s)
 ```
+
+## Citation
+
+If you find CMAT useful, you can cite the following:
+
+> Shen et al., CMAT: ClinVar Mapping and Annotation Toolkit. _Bioinformatics Advances_, 2024. [doi:10.1093/bioadv/vbae018](https://doi.org/10.1093/bioadv/vbae018)
diff --git a/bin/cmat/VERSION b/bin/cmat/VERSION
@@ -1 +1 @@
-3.3.0
+3.3.1
diff --git a/cmat/clinvar_xml_io/clinvar_measure.py b/cmat/clinvar_xml_io/clinvar_measure.py
@@ -26,9 +26,10 @@ class ClinVarRecordMeasure:
     MS_REPEAT_EXPANSION = 'repeat_expansion'
     MS_NO_COMPLETE_COORDS = 'no_complete_coords'
 
-    def __init__(self, measure_xml, clinvar_record):
+    def __init__(self, measure_xml, clinvar_record, vcv_id):
         self.measure_xml = measure_xml
         self.clinvar_record = clinvar_record
+        self.vcv_id = vcv_id
 
     @property
     def all_names(self):

diff --git a/cmat/clinvar_xml_io/clinvar_record.py b/cmat/clinvar_xml_io/clinvar_record.py
@@ -42,7 +42,7 @@ def __init__(self, record_xml, xsd_version, trait_class=ClinVarTrait, measure_cl
         if not variant_measure:
             self.measure = None
         else:
-            self.measure = measure_class(variant_measure, self)
+            self.measure = measure_class(variant_measure, self, self.vcv_id)
 
     def __str__(self):
         return f'ClinVarRecord object with accession {self.accession}'
@@ -60,6 +60,11 @@ def write(self, output):
     def accession(self):
         return find_mandatory_unique_element(self.record_xml, './ClinVarAccession').attrib['Acc']
 
+    @property
+    def vcv_id(self):
+        """ClinVar's accession for a MeasureSet, present only in RCV records."""
+        return find_mandatory_unique_element(self.record_xml, './MeasureSet').attrib.get('Acc', None)
+
     @property
     def last_updated_date(self):
         """This tracks the latest update date, counting even minor technical updates.

diff --git a/cmat/output_generation/clinvar_to_evidence_strings.py b/cmat/output_generation/clinvar_to_evidence_strings.py
@@ -238,6 +238,7 @@ def generate_evidence_string(clinvar_record, allele_origins, disease_name, disea
         'variantFunctionalConsequenceId': consequence_attributes.so_term.accession,
         'variantId': clinvar_record.measure.vcf_full_coords,  # CHROM_POS_REF_ALT notation.
         'variantRsId': clinvar_record.measure.rs_id,
+        'variantFromSourceId': clinvar_record.vcv_id,
 
         # PHENOTYPE ATTRIBUTES.
         # The alphabetical list of *all* valid disease names from all traits from that ClinVar record, reported as a

diff --git a/data-exploration/clinvar-variant-types/README.md b/data-exploration/clinvar-variant-types/README.md
@@ -9,8 +9,8 @@ The data was last updated on **2022-10-24.** Graphs can be enlarged by clicking
 ## Updating the data
 
 ```bash
-wget https://ftp.ncbi.nlm.nih.gov/pub/clinvar/xml/ClinVarFullRelease_00-latest.xml.gz
-python3 clinvar-variant-types.py --clinvar-xml ClinVarFullRelease_00-latest.xml.gz
+wget -O clinvar.xml.gz https://ftp.ncbi.nlm.nih.gov/pub/clinvar/xml/RCV_release/ClinVarRCVRelease_00-latest.xml.gz
+python3 clinvar-variant-types.py --clinvar-xml clinvar.xml.gz
 ```
 
 The source code for diagrams and tables will be printed to STDOUT. The diagrams can then be built using the website http://sankeymatic.com/build/. Parameters for rendering them will be indicated in the output as well. The tables should be copy-pasted into the [corresponding Markdown file](supplementary-tables.md).

diff --git a/data-exploration/clinvar-variant-types/clinvar-variant-types.py b/data-exploration/clinvar-variant-types/clinvar-variant-types.py
@@ -4,7 +4,7 @@
 from collections import Counter
 import logging
 
-from eva_cttv_pipeline.clinvar_xml_io import clinvar_xml_io
+from cmat import clinvar_xml_io
 
 logging.basicConfig()
 logger = logging.getLogger(__name__)

diff --git a/tests/consequence_prediction/structural_variants/test_structural_pipeline.py b/tests/consequence_prediction/structural_variants/test_structural_pipeline.py
@@ -26,7 +26,6 @@ def run_pipeline(resource_name, include_transcripts=False):
 
 def test_successful_run():
     assert sorted(run_pipeline('precise_genomic.xml.gz')) == sorted([
-        ['NC_000016.10:g.72059151_72063259del', 'ENSG00000140830', 'TXNL4B', 'intron_variant'],
         ['NC_000016.10:g.72059151_72063259del', 'ENSG00000257017', 'HP', 'stop_lost'],
         ['NC_000016.10:g.72059151_72063259del', 'ENSG00000261701', 'HPR', 'feature_truncation'],
         ['NC_000001.11:g.25271785_25329047del', 'ENSG00000117616', 'RSRP1', 'intron_variant'],
@@ -37,7 +36,7 @@ def test_successful_run():
 
 def test_successful_run_with_transcripts():
     results = run_pipeline('precise_genomic.xml.gz', include_transcripts=True)
-    assert len(results) == 28
+    assert len(results) == 27
     assert ['NC_000001.11:g.25271785_25329047del', 'ENSG00000187010', 'RHD', 'stop_lost', 'ENST00000454452'] in results
 
 

diff --git a/tests/output_generation/resources/expected_genetics_evidence_string.json b/tests/output_generation/resources/expected_genetics_evidence_string.json
@@ -22,6 +22,7 @@
   "releaseDate": "2013-04-04",
   "studyId": "RCV000002127",
   "targetFromSourceId": "ENSG00000139988",
+  "variantFromSourceId": "VCV000002046",
   "variantFunctionalConsequenceId": "SO_0001583",
   "variantHgvsId": "NC_000014.9:g.67729209A>G",
   "variantId": "14_67729209_A_G",

diff --git a/tests/output_generation/resources/expected_multiple_names_evidence_string.json b/tests/output_generation/resources/expected_multiple_names_evidence_string.json
@@ -19,6 +19,7 @@
   "releaseDate": "2017-01-13",
   "studyId": "RCV000415158",
   "targetFromSourceId": "ENSG00000139988",
+  "variantFromSourceId": "VCV000374196",
   "variantFunctionalConsequenceId": "SO_0001583",
   "variantHgvsId": "NC_000007.14:g.94423102G>A",
   "variantId": "7_94423102_G_A",

diff --git a/tests/output_generation/resources/expected_somatic_evidence_string.json b/tests/output_generation/resources/expected_somatic_evidence_string.json
@@ -22,6 +22,7 @@
   "releaseDate": "2013-04-04",
   "studyId": "RCV000002127",
   "targetFromSourceId": "ENSG00000139988",
+  "variantFromSourceId": "VCV000002046",
   "variantFunctionalConsequenceId": "SO_0001583",
   "variantHgvsId": "NC_000014.9:g.67729209A>G",
   "variantId": "14_67729209_A_G",

diff --git a/tests/pipelines/resources/expected/consequences_snp.tsv b/tests/pipelines/resources/expected/consequences_snp.tsv
@@ -396,6 +396,7 @@
 17:63957460:A:G	ENSG00000007314	SCN4A	missense_variant
 17:63971780:C:T	ENSG00000007314	SCN4A	missense_variant
 17:64485735:TG:T	ENSG00000256525	POLG2	frameshift_variant
+17:64485735:TG:T	ENSG00000271605	MILR1	intron_variant
 17:6453135:C:T	ENSG00000091622	PITPNM3	3_prime_UTR_variant
 17:65177778:A:G	ENSG00000108370	RGS9	missense_variant
 17:65538242:G:C	ENSG00000168646	AXIN2	missense_variant