Merge pull request #138 from cancervariants/issue-114

Issue 121

Author: korikuzma

.ebextensions/01_download_data.config

@@ -10,10 +10,6 @@ container_commands:
         test: test ! -d "./variation/data/seqrepo"
         command: "yum install -y unzip"
 
-    04_hgnc_gene_symbol_download:
-        test: test ! -f "./variation/data/hgnc_gene_symbols.txt"
-        command: "aws s3 cp s3://${AWS_BUCKET_NAME}/variation/hgnc_gene_symbols.txt ./variation/data/hgnc_gene_symbols.txt --region us-east-2"
-
     05_refseq_gene_symbol_download:
         test: test ! -f "./variation/data/refseq_gene_symbols.txt"
         command: "aws s3 cp s3://${AWS_BUCKET_NAME}/variation/refseq_gene_symbols.txt ./variation/data/refseq_gene_symbols.txt --region us-east-2"

README.md

@@ -71,7 +71,7 @@ Variation Normalization uses [Ensembl BioMart](http://www.ensembl.org/biomart/ma
 ![image](biomart.png)
 
 ### Setting up Gene Normalizer
-Variation Normalization `normalize` endpoint relies on data from [Gene Normalization](https://github.com/cancervariants/gene-normalization. You must have Gene Normalization's DynamoDB running for the `normalizer` endpoint to work.
+Variation Normalization relies on data from [Gene Normalization](https://github.com/cancervariants/gene-normalization. You must have Gene Normalization's DynamoDB running for the application to work.
 
 To setup, follow the instructions from the [README](https://github.com/cancervariants/gene-normalization/blob/main/README.md). 
 

tests/classifiers/classifier_base.py

@@ -2,6 +2,9 @@
 import yaml
 from variation.tokenizers import Tokenize
 from tests import PROJECT_ROOT
+from variation.tokenizers.caches import AminoAcidCache
+from variation.tokenizers import GeneSymbol
+from gene.query import QueryHandler as GeneQueryHandler
 
 
 class ClassifierBase:
@@ -16,7 +19,8 @@ def setUp(self):
             {'should_match': [], 'should_not_match': []}
         )
         self.classifier = self.classifier_instance()
-        self.tokenizer = Tokenize()
+        self.tokenizer = Tokenize(AminoAcidCache(),
+                                  GeneSymbol(GeneQueryHandler()))
 
     def classifier_instance(self):
         """Check that the classifier_instance method is implemented."""

tests/classifiers/test_fusion.py

@@ -97,8 +97,8 @@ coding_dna_delins:
   should_not_match:
     - query: NM_005228:c.2237_2253delinsTTGCT
     - query: ENST00000277541.6:c.7330479587395delinsACA
-    - query: NM_000551.3:c.4560delinsAA
-    - query: NM_000551.3:c.4559_4560delinsAA
+    - query: NM_000551.3:c.4561delinsAA
+    - query: NM_000551.3:c.4561_4562delinsAA
     - query: NM_000551.3:c.4560_4561delinsAA
 
 genomic_delins:
@@ -182,4 +182,4 @@ genomic_insertion:
     - query: ERBB2 g.37880993_37880994insGCTTACGTGATG
   should_not_match:
     - query: NC_000022.10:g.51304566_51304567insT
-    - query: NC_000022.10:g.51304565_51304566insT
+    - query: NC_000022.10:g.51304567_51304568insT

tests/fixtures/validators.yml

@@ -1,22 +1,10 @@
 """Module for testing the normalize endpoint."""
 import pytest
-from ga4gh.vrs.dataproxy import SeqRepoDataProxy
-from ga4gh.vrs.extras.translator import Translator
-from variation.normalize import Normalize
+from variation.query import QueryHandler
 from variation.schemas.ga4gh_vrsatile import VariationDescriptor
-from variation.to_vrs import ToVRS
-from variation.main import normalize as normalize_get_response
-from variation.main import translate as to_vrs_get_response
-from variation.classifiers import Classify
-from variation.tokenizers import Tokenize
-from variation.validators import Validate
-from variation.translators import Translate
-from variation.data_sources import SeqRepoAccess, TranscriptMappings, \
-    UTA, MANETranscriptMappings
-from variation.mane_transcript import MANETranscript
-from variation.tokenizers import GeneSymbol
-from variation.tokenizers.caches import GeneSymbolCache, AminoAcidCache
 from datetime import datetime
+from variation.main import normalize as normalize_get_response
+from variation.main import to_vrs as to_vrs_get_response
 import copy
 
 
@@ -26,40 +14,13 @@ def test_normalize():
     class TestNormalize:
 
         def __init__(self):
-            tokenizer = Tokenize()
-            classifier = Classify()
-            seqrepo_access = SeqRepoAccess()
-            transcript_mappings = TranscriptMappings()
-            gene_symbol = GeneSymbol(GeneSymbolCache())
-            amino_acid_cache = AminoAcidCache()
-            uta = UTA()
-            mane_transcript_mappings = MANETranscriptMappings()
-            dp = SeqRepoDataProxy(seqrepo_access.seq_repo_client)
-            tlr = Translator(data_proxy=dp)
-            mane_transcript = MANETranscript(seqrepo_access,
-                                             transcript_mappings,
-                                             mane_transcript_mappings, uta)
-            validator = Validate(seqrepo_access, transcript_mappings,
-                                 gene_symbol, mane_transcript, uta,
-                                 dp, tlr, amino_acid_cache)
-            translator = Translate()
-
-            self.to_vrs = ToVRS(tokenizer, classifier, seqrepo_access,
-                                transcript_mappings, gene_symbol,
-                                amino_acid_cache, uta,
-                                mane_transcript_mappings, mane_transcript,
-                                validator, translator)
-            self.test_normalize = Normalize(seqrepo_access, uta)
+            self.query_handler = QueryHandler()
+
+        def to_vrs(self, q):
+            return self.query_handler.to_vrs(q)
 
         def normalize(self, q):
-            validations, warnings = self.to_vrs.get_validations(
-                q, normalize_endpoint=True
-            )
-            resp = \
-                self.test_normalize.normalize(q,
-                                              validations,
-                                              warnings)
-            return resp
+            return self.query_handler.normalize(q)
 
     return TestNormalize()
 

tests/test_normalize.py

@@ -1,17 +1,16 @@
 """A module for testing the Gene Pair Tokenizer."""
 import unittest
 from variation.tokenizers import GeneSymbol
-from variation.tokenizers.caches import GeneSymbolCache
 from .tokenizer_base import TokenizerBase
+from gene.query import QueryHandler as GeneQueryHandler
 
 
 class TestGenePairTokenizer(TokenizerBase, unittest.TestCase):
     """The Gene Pair Tokenizer class."""
 
     def tokenizer_instance(self):
         """Return the Gene Pair tokenizer instance."""
-        gene_cache = GeneSymbolCache()
-        return GeneSymbol(gene_cache)
+        return GeneSymbol(GeneQueryHandler())
 
     def token_type(self):
         """Return the Gene Pair token type."""

tests/tokenizers/test_gene.py

@@ -1,7 +1,6 @@
 """Module for testing gene pair tokenization."""
 import unittest
 from variation.tokenizers import GenePair
-from variation.tokenizers.caches import GeneSymbolCache
 from .tokenizer_base import TokenizerBase
 
 
@@ -10,7 +9,7 @@ class TestGenePairTokenizer(TokenizerBase, unittest.TestCase):
 
     def tokenizer_instance(self):
         """Return Gene Pair Tokenizer instance."""
-        return GenePair(GeneSymbolCache())
+        return GenePair()
 
     def token_type(self):
         """Return Gene Pair token type."""

tests/tokenizers/test_gene_pair.py

@@ -5,12 +5,13 @@
 from variation.validators import AminoAcidDeletion as AAD_V
 from .translator_base import TranslatorBase
 from variation.tokenizers import GeneSymbol
-from variation.tokenizers.caches import GeneSymbolCache, AminoAcidCache
+from variation.tokenizers.caches import AminoAcidCache
 from variation.data_sources import TranscriptMappings, SeqRepoAccess, \
     MANETranscriptMappings, UTA
 from variation.mane_transcript import MANETranscript
 from ga4gh.vrs.dataproxy import SeqRepoDataProxy
 from ga4gh.vrs.extras.translator import Translator
+from gene.query import QueryHandler as GeneQueryHandler
 
 
 class TestAminoAcidDeletionTranslator(TranslatorBase, unittest.TestCase):
@@ -28,7 +29,8 @@ def validator_instance(self):
         dp = SeqRepoDataProxy(seqrepo_access.seq_repo_client)
         tlr = Translator(data_proxy=dp)
         return AAD_V(
-            seqrepo_access, transcript_mappings, GeneSymbol(GeneSymbolCache()),
+            seqrepo_access, transcript_mappings,
+            GeneSymbol(GeneQueryHandler()),
             MANETranscript(seqrepo_access, transcript_mappings,
                            MANETranscriptMappings(), uta),
             uta, dp, tlr, AminoAcidCache())

tests/translators/test_amino_acid_deletion.py

@@ -5,12 +5,13 @@
 from variation.validators import AminoAcidDelIns as AAD_V
 from .translator_base import TranslatorBase
 from variation.tokenizers import GeneSymbol
-from variation.tokenizers.caches import GeneSymbolCache, AminoAcidCache
+from variation.tokenizers.caches import AminoAcidCache
 from variation.data_sources import TranscriptMappings, SeqRepoAccess, \
     MANETranscriptMappings, UTA
 from variation.mane_transcript import MANETranscript
 from ga4gh.vrs.dataproxy import SeqRepoDataProxy
 from ga4gh.vrs.extras.translator import Translator
+from gene.query import QueryHandler as GeneQueryHandler
 
 
 class TestAminoAcidDelInsTranslator(TranslatorBase, unittest.TestCase):
@@ -28,7 +29,8 @@ def validator_instance(self):
         dp = SeqRepoDataProxy(seqrepo_access.seq_repo_client)
         tlr = Translator(data_proxy=dp)
         return AAD_V(
-            seqrepo_access, transcript_mappings, GeneSymbol(GeneSymbolCache()),
+            seqrepo_access, transcript_mappings,
+            GeneSymbol(GeneQueryHandler()),
             MANETranscript(seqrepo_access, transcript_mappings,
                            MANETranscriptMappings(), uta),
             uta, dp, tlr, AminoAcidCache())