Merge pull request #137 from cancervariants/issue-126-vrsatile

Issue 126 vrsatile

Author: korikuzma

Pipfile

@@ -32,6 +32,6 @@ pydantic = "*"
 uvloop = "*"
 httptools = "*"
 "ga4gh.vrs" = {version = "==0.7.0rc3", extras = ["extras"]}
-gene-normalizer = "*"
+gene-normalizer = ">=0.1.17"
 pyliftover = "*"
 boto3 = "*"

requirements-dev.txt

@@ -28,8 +28,8 @@ beautifulsoup4==4.9.3
 biocommons.seqrepo==0.6.4
 bioutils==0.5.5; python_version >= '3.6'
 bleach==4.0.0; python_version >= '3.6'
-boto3==1.18.17
-botocore==1.21.17; python_version >= '3.6'
+boto3==1.18.20
+botocore==1.21.20; python_version >= '3.6'
 bs4==0.0.1
 canonicaljson==1.4.0; python_version ~= '3.5'
 certifi==2021.5.30
@@ -58,20 +58,20 @@ fastapi==0.68.0
 filelock==3.0.12
 flake8-docstrings==1.6.0
 flake8==3.9.2
-frozendict==2.0.4; python_version >= '3.6'
+frozendict==2.0.5; python_version >= '3.6'
 ga4gh.vrs[extras]==0.7.0rc3
-gene-normalizer==0.1.15
+gene-normalizer==0.1.17
 gffutils==0.10.1
 h11==0.12.0; python_version >= '3.6'
 hgvs==1.5.1
-httptools==0.2.0
+httptools==0.3.0
 humanfriendly==9.2; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
 identify==2.2.13; python_full_version >= '3.6.1'
 idna==3.2; python_version >= '3'
 importlib-metadata==4.6.3; python_version >= '3.6'
 inflection==0.5.1; python_version >= '3.5'
 iniconfig==1.1.1
-ipykernel==6.0.3
+ipykernel==6.1.0
 ipython-genutils==0.2.0
 ipython==7.26.0; python_version >= '3.7'
 ipywidgets==7.6.3
@@ -86,16 +86,16 @@ jupyter-core==4.7.1; python_version >= '3.6'
 jupyter-server==1.10.2; python_version >= '3.6'
 jupyter==1.0.0
 jupyterlab-pygments==0.1.2
-jupyterlab-server==2.6.2; python_version >= '3.6'
+jupyterlab-server==2.7.0; python_version >= '3.6'
 jupyterlab-widgets==1.0.0; python_version >= '3.6'
-jupyterlab==3.1.4
+jupyterlab==3.1.6
 keyring==23.0.1; python_version >= '3.6'
 kiwisolver==1.3.1; python_version >= '3.6'
 lxml==4.6.3
 markdown==3.3.4; python_version >= '3.6'
 markupsafe==2.0.1; python_version >= '3.6'
 matplotlib-inline==0.1.2; python_version >= '3.5'
-matplotlib==3.4.2
+matplotlib==3.4.3
 mccabe==0.6.1
 mistune==0.8.4
 nbclassic==0.3.1; python_version >= '3.6'
@@ -105,7 +105,7 @@ nbformat==5.1.3; python_version >= '3.5'
 nest-asyncio==1.5.1; python_version >= '3.5'
 networkx==2.6.2; python_version >= '3.7'
 nodeenv==1.6.0
-notebook==6.4.2; python_version >= '3.6'
+notebook==6.4.3; python_version >= '3.6'
 numpy==1.21.1; python_version >= '3.7'
 obonet==0.3.0; python_version >= '3.5'
 packaging==21.0; python_version >= '3.6'
@@ -165,7 +165,7 @@ soupsieve==2.2.1; python_version >= '3'
 sqlparse==0.4.1; python_version >= '3.5'
 starlette==0.14.2; python_version >= '3.6'
 tabulate==0.8.9
-terminado==0.10.1; python_version >= '3.6'
+terminado==0.11.0; python_version >= '3.6'
 testpath==0.5.0; python_version >= '3.5'
 toml==0.10.2; python_version >= '2.6' and python_version not in '3.0, 3.1, 3.2, 3.3'
 tornado==6.1; python_version >= '3.5'
@@ -175,13 +175,13 @@ twine==3.4.2
 typing-extensions==3.10.0.0
 urllib3==1.26.6; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4' and python_version < '4'
 uvicorn==0.14.0
-uvloop==0.15.3
+uvloop==0.16.0
 vcfpy==0.13.3
-virtualenv==20.7.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
+virtualenv==20.7.2; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
 w3lib==1.22.0
 wcwidth==0.2.5
 webencodings==0.5.1
-websocket-client==1.1.1; python_version >= '3.6'
+websocket-client==1.2.1; python_version >= '3.6'
 websockets==8.1
 widgetsnbextension==3.5.1
 yoyo-migrations==7.3.2

requirements.txt

@@ -17,8 +17,8 @@ backports-datetime-fromisoformat==1.0.0
 beautifulsoup4==4.9.3
 biocommons.seqrepo==0.6.4
 bioutils==0.5.5; python_version >= '3.6'
-boto3==1.18.17
-botocore==1.21.17; python_version >= '3.6'
+boto3==1.18.20
+botocore==1.21.20; python_version >= '3.6'
 bs4==0.0.1
 canonicaljson==1.4.0; python_version ~= '3.5'
 certifi==2021.5.30
@@ -32,13 +32,13 @@ decorator==5.0.9; python_version >= '3.5'
 deprecation==2.1.0
 fake-useragent==0.1.11
 fastapi==0.68.0
-frozendict==2.0.4; python_version >= '3.6'
+frozendict==2.0.5; python_version >= '3.6'
 ga4gh.vrs[extras]==0.7.0rc3
-gene-normalizer==0.1.15
+gene-normalizer==0.1.17
 gffutils==0.10.1
 h11==0.12.0; python_version >= '3.6'
 hgvs==1.5.1
-httptools==0.2.0
+httptools==0.3.0
 humanfriendly==9.2; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
 idna==3.2; python_version >= '3'
 inflection==0.5.1; python_version >= '3.5'
@@ -91,7 +91,7 @@ traitlets==5.0.5; python_version >= '3.7'
 typing-extensions==3.10.0.0
 urllib3==1.26.6; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4' and python_version < '4'
 uvicorn==0.14.0
-uvloop==0.15.3
+uvloop==0.16.0
 vcfpy==0.13.3
 w3lib==1.22.0
 wcwidth==0.2.5

tests/test_normalize.py

@@ -464,7 +464,7 @@ def braf_v600e(braf_gene_context):
         },
         "molecule_context": "protein",
         "structural_type": "SO:0001606",
-        "ref_allele_seq": "V",
+        "vrs_ref_allele_seq": "V",
         "gene_context": braf_gene_context
     }
     return VariationDescriptor(**params)
@@ -495,7 +495,7 @@ def vhl(vhl_gene_context):
         },
         "molecule_context": "protein",
         "structural_type": "SO:0001617",
-        "ref_allele_seq": "Y",
+        "vrs_ref_allele_seq": "Y",
         "gene_context": vhl_gene_context
     }
     return VariationDescriptor(**params)
@@ -526,7 +526,7 @@ def vhl_silent(vhl_gene_context):
         },
         "molecule_context": "protein",
         "structural_type": "SO:0001017",
-        "ref_allele_seq": "P",
+        "vrs_ref_allele_seq": "P",
         "gene_context": vhl_gene_context
     }
     return VariationDescriptor(**params)
@@ -542,7 +542,7 @@ def braf_v600e_nucleotide(braf_gene_context, braf_nuc_value):
         "value": braf_nuc_value,
         "molecule_context": "transcript",
         "structural_type": "SO:0001483",
-        "ref_allele_seq": "T",
+        "vrs_ref_allele_seq": "T",
         "gene_context": braf_gene_context
     }
     return VariationDescriptor(**params)
@@ -573,7 +573,7 @@ def nm_004448_coding_dna_delins(erbb2_context):
         },
         "molecule_context": "transcript",
         "structural_type": "SO:1000032",
-        "ref_allele_seq": "GG",
+        "vrs_ref_allele_seq": "GG",
         "gene_context": erbb2_context
     }
     return VariationDescriptor(**params)
@@ -604,7 +604,7 @@ def nc_000007_genomic_delins(braf_gene_context):
         },
         "molecule_context": "transcript",
         "structural_type": "SO:1000032",
-        "ref_allele_seq": "TG",
+        "vrs_ref_allele_seq": "TG",
         "gene_context": braf_gene_context
     }
     return VariationDescriptor(**params)
@@ -614,7 +614,7 @@ def nc_000007_genomic_delins(braf_gene_context):
 def nm_000551(vhl_gene_context):
     """Create test fixture for NM_000551.4:c.615delinsAA."""
     params = {
-        "id": 'temp_id',
+        "id": 'normalize.variation:temp',
         "type": "VariationDescriptor",
         "value_id": "ga4gh:VA.SjJnUcJL1EyRFUb6f8PSJA4u3fyin2Wj",
         "value": {
@@ -635,7 +635,7 @@ def nm_000551(vhl_gene_context):
         },
         "molecule_context": "transcript",
         "structural_type": "SO:1000032",
-        "ref_allele_seq": "C",
+        "vrs_ref_allele_seq": "C",
         "gene_context": vhl_gene_context
     }
     return VariationDescriptor(**params)
@@ -674,7 +674,7 @@ def coding_dna_silent_mutation(braf_gene_context, braf_nuc_value):
         "value": value,
         "molecule_context": "transcript",
         "structural_type": "SO:0002073",
-        "ref_allele_seq": "T",
+        "vrs_ref_allele_seq": "T",
         "gene_context": braf_gene_context
     }
     return VariationDescriptor(**params)
@@ -692,7 +692,7 @@ def nc_000007_silent_mutation(braf_gene_context, braf_nuc_value):
         "value": value,
         "molecule_context": "transcript",
         "structural_type": "SO:0002073",
-        "ref_allele_seq": "T",
+        "vrs_ref_allele_seq": "T",
         "gene_context": braf_gene_context
     }
     return VariationDescriptor(**params)
@@ -723,7 +723,7 @@ def amino_acid_delins(egfr_context):
         },
         "molecule_context": "protein",
         "structural_type": "SO:1000032",
-        "ref_allele_seq": "LREAT",
+        "vrs_ref_allele_seq": "LREAT",
         "gene_context": egfr_context
     }
     return VariationDescriptor(**params)
@@ -756,7 +756,7 @@ def amino_acid_deletion_np_range(erbb2_context):
         },
         "molecule_context": "protein",
         "structural_type": "SO:0001604",
-        "ref_allele_seq": "LRENT",
+        "vrs_ref_allele_seq": "LRENT",
         "gene_context": erbb2_context
     }
     return VariationDescriptor(**params)
@@ -789,7 +789,7 @@ def coding_dna_deletion(erbb2_context):
         },
         "molecule_context": "transcript",
         "structural_type": "SO:0000159",
-        "ref_allele_seq": "TTGAGGGAAAACACAT",
+        "vrs_ref_allele_seq": "TTGAGGGAAAACACAT",
         "gene_context": erbb2_context
     }
     return VariationDescriptor(**params)
@@ -820,7 +820,7 @@ def genomic_deletion(vhl_gene_context):
         },
         "molecule_context": "transcript",
         "structural_type": "SO:0000159",
-        "ref_allele_seq": "ATGTTGACGGACAGCCTAT",
+        "vrs_ref_allele_seq": "ATGTTGACGGACAGCCTAT",
         "gene_context": vhl_gene_context
     }
     return VariationDescriptor(**params)
@@ -911,7 +911,7 @@ def genomic_insertion(erbb2_context):
         },
         "molecule_context": "transcript",
         "structural_type": "SO:0000667",
-        "ref_allele_seq": "TACGTGATGGCT",
+        "vrs_ref_allele_seq": "TACGTGATGGCT",
         "gene_context": erbb2_context
     }
     return VariationDescriptor(**params)
@@ -942,7 +942,7 @@ def genomic_substitution(egfr_context):
         },
         "molecule_context": "transcript",
         "structural_type": "SO:0001483",
-        "ref_allele_seq": "C",
+        "vrs_ref_allele_seq": "C",
         "gene_context": egfr_context
     }
     return VariationDescriptor(**params)
@@ -973,7 +973,7 @@ def genomic_sub_grch38():
         },
         "molecule_context": "genomic",
         "structural_type": "SO:0001483",
-        "ref_allele_seq": "C"
+        "vrs_ref_allele_seq": "C"
     }
     return VariationDescriptor(**params)
 
@@ -1003,7 +1003,7 @@ def egfr_grch38_sub(genomic_sub_grch38, egfr_context):
         },
         "molecule_context": "genomic",
         "structural_type": "SO:0001483",
-        "ref_allele_seq": "C",
+        "vrs_ref_allele_seq": "C",
         "gene_context": egfr_context
     }
     return VariationDescriptor(**params)
@@ -1017,7 +1017,8 @@ def assertion_checks(normalize_response, test_variation):
     assert normalize_response.molecule_context == \
            test_variation.molecule_context
     assert normalize_response.structural_type == test_variation.structural_type
-    assert normalize_response.ref_allele_seq == test_variation.ref_allele_seq
+    assert normalize_response.vrs_ref_allele_seq == \
+           test_variation.vrs_ref_allele_seq
 
     resp_gene_context = normalize_response.gene_context
     test_variation_context = test_variation.gene_context
@@ -1338,11 +1339,11 @@ def test_no_matches(test_normalize):
     for q in queries:
         resp = test_normalize.normalize(q)
         assert resp.type == 'VariationDescriptor'
-        assert resp.value['type'] == 'Text'
+        assert resp.value.type == 'Text'
 
     resp = test_normalize.normalize('clinvar:10')
     assert resp.type == 'VariationDescriptor'
-    assert resp.value['definition'] == 'clinvar:10'
+    assert resp.value.definition == 'clinvar:10'
 
     resp = test_normalize.normalize('   ')
     assert resp is None

tests/translators/translator_base.py

@@ -49,6 +49,8 @@ def test_translator(self):
             for vr in validation_results:
                 if vr.is_valid:
                     loc = (self.translator.translate(vr)).__dict__
+                    loc['location'] = loc['location'].dict()
+                    del loc['location']['id']
                     if loc not in found:
                         found.append(loc)
                         num_valid += 1

variation/normalize.py

@@ -46,7 +46,7 @@ def normalize(self, q, validations, warnings):
                 allele = valid_result.allele
                 allele_id = allele.pop('_id')
                 identifier = valid_result.identifier
-                ref_allele_seq = self.get_ref_allele_seq(
+                vrs_ref_allele_seq = self.get_ref_allele_seq(
                     allele, identifier
                 )
 
@@ -62,7 +62,7 @@ def normalize(self, q, validations, warnings):
                     value=allele,
                     molecule_context=valid_result.classification_token.molecule_context,  # noqa: E501
                     structural_type=valid_result.classification_token.so_id,
-                    ref_allele_seq=ref_allele_seq,
+                    vrs_ref_allele_seq=vrs_ref_allele_seq,
                     gene_context=gene_context
                 )
             else:
@@ -102,38 +102,6 @@ def get_gene_descriptor(self, gene_token):
             return response['gene_descriptor']
         return None
 
-    def get_extensions(self, record, record_location):
-        """Return a list of ga4gh extensions.
-
-        :param gene.schemas.Gene record: The record from the normalization
-            service
-        :param gene.schemas.ChromosomeLocation record_location: The record's
-            location
-        :return: List of extensions providing additional information
-        """
-        extensions = list()
-        self.add_extension(extensions, 'strand', record.strand)
-        self.add_extension(extensions, 'symbol_status', record.symbol_status)
-        self.add_extension(extensions, 'associated_with',
-                           record.associated_with)
-        self.add_extension(extensions, 'chromosome_location',
-                           record_location.dict(by_alias=True))
-        return extensions
-
-    def add_extension(self, extensions, name, value):
-        """Add extension to list of extensions.
-
-        :param list extensions: List of ga4gh extensions
-        :param str name: name of extension
-        :param any value: value of extension
-        """
-        if value:
-            extensions.append({
-                'type': 'Extension',
-                'name': name,
-                'value': value
-            })
-
     def get_ref_allele_seq(self, allele, identifier) -> Optional[str]:
         """Return ref allele seq for transcript.