Merge pull request #89 from cancervariants/issue-84

Issue 84

Pipfile

@@ -14,6 +14,8 @@ flake8-docstrings = "*"
 pre-commit = "*"
 variant-normalization = {editable = true, path = "."}
 pyyaml = "*"
+jupyter = "*"
+ipykernel = "*"
 
 [packages]
 hgvs = "*"

README.md

@@ -5,6 +5,8 @@ Services and guidelines for normalizing variant terms
 Variant Normalization relies on some local data caches which you will need to set up. It uses pipenv to manage its environment, which you will also need to install.
 
 ### Installation
+Variant Normalization relies on [seqrepo](https://github.com/biocommons/biocommons.seqrepo), which you must download yourself.
+
 From the _variant_ directory of the repository:
 ```
 pipenv sync
@@ -18,8 +20,6 @@ sudo mv $seqrepo_date_dir latest
 ```
 
 ### Data
-Variant Normalization relies on [seqrepo](https://github.com/biocommons/biocommons.seqrepo). We are currently using version `2021-01-29`.
-
 Variant Normalization uses [Ensembl BioMart](http://www.ensembl.org/biomart/martview) to retrieve `variant/data/transcript_mappings.tsv`. We currently use `Human Genes (GRCh38.p13)` for the dataset and the following attributes we use are: Gene stable ID, Gene stable ID version, Transcript stable ID, Transcript stable ID version, Protein stable ID, Protein stable ID version, RefSeq match transcript (MANE Select), Gene name. 
 
 ![image](biomart.png)

tests/classifiers/test_coding_dna_delins.py

@@ -0,0 +1,16 @@
+"""Module for testing Coding DNA DelIns Classifier."""
+import unittest
+from variant.classifiers import CodingDNADelInsClassifier
+from .classifier_base import ClassifierBase
+
+
+class TestCodingDNADelInsClassifier(ClassifierBase, unittest.TestCase):
+    """A class to test the Coding DNA DelIns Classifier."""
+
+    def classifier_instance(self):
+        """Return CodingDNADelInsClassifier instance."""
+        return CodingDNADelInsClassifier()
+
+    def fixture_name(self):
+        """Return CodingDNADelInsClassifier fixture name."""
+        return 'coding_dna_delins'

tests/classifiers/test_coding_dna_silent_mutation.py

@@ -0,0 +1,16 @@
+"""Module for testing Coding DNA Silent Mutation Classifier."""
+import unittest
+from variant.classifiers import CodingDNASilentMutationClassifier
+from .classifier_base import ClassifierBase
+
+
+class TestCodingDNASilentMutationClassifier(ClassifierBase, unittest.TestCase):
+    """A class to test the Coding DNA Silent Mutation Classifier."""
+
+    def classifier_instance(self):
+        """Return CodingDNASilentMutationClassifier instance."""
+        return CodingDNASilentMutationClassifier()
+
+    def fixture_name(self):
+        """Return CodingDNASilentMutationClassifier fixture name."""
+        return 'coding_dna_silent_mutation'

tests/classifiers/test_coding_dna_substitution.py

@@ -0,0 +1,16 @@
+"""Module for testing Coding DNA Substitution Classifier."""
+import unittest
+from variant.classifiers import CodingDNASubstitutionClassifier
+from .classifier_base import ClassifierBase
+
+
+class TestCodingDNASubstitutionClassifier(ClassifierBase, unittest.TestCase):
+    """A class to test the Coding DNA Substitution Classifier."""
+
+    def classifier_instance(self):
+        """Return CodingDNASubstitutionClassifier instance."""
+        return CodingDNASubstitutionClassifier()
+
+    def fixture_name(self):
+        """Return CodingDNASubstitutionClassifier fixture name."""
+        return 'coding_dna_substitution'

tests/classifiers/test_genomic_delins.py

@@ -0,0 +1,16 @@
+"""Module for testing Genomic DelIns Classifier."""
+import unittest
+from variant.classifiers import GenomicDelInsClassifier
+from .classifier_base import ClassifierBase
+
+
+class TestGenomicDelInsClassifier(ClassifierBase, unittest.TestCase):
+    """A class to test the Genomic DelIns Classifier."""
+
+    def classifier_instance(self):
+        """Return GenomicDelInsClassifier instance."""
+        return GenomicDelInsClassifier()
+
+    def fixture_name(self):
+        """Return GenomicDelInsClassifier fixture name."""
+        return 'genomic_delins'

tests/classifiers/test_genomic_silent_mutation.py

@@ -0,0 +1,16 @@
+"""Module for testing Genomic Silent Mutation Classifier."""
+import unittest
+from variant.classifiers import GenomicSilentMutationClassifier
+from .classifier_base import ClassifierBase
+
+
+class TestGenomicSilentMutationClassifier(ClassifierBase, unittest.TestCase):
+    """A class to test the Genomic Silent Mutation Classifier."""
+
+    def classifier_instance(self):
+        """Return GenomicSilentMutationClassifier instance."""
+        return GenomicSilentMutationClassifier()
+
+    def fixture_name(self):
+        """Return GenomicSilentMutationClassifier fixture name."""
+        return 'genomic_silent_mutation'

tests/classifiers/test_genomic_substitution.py

@@ -0,0 +1,16 @@
+"""Module for testing Genomic Substitution Classifier."""
+import unittest
+from variant.classifiers import GenomicSubstitutionClassifier
+from .classifier_base import ClassifierBase
+
+
+class TestGenomicSubstitutionClassifier(ClassifierBase, unittest.TestCase):
+    """A class to test the Coding DNA Substitution Classifier."""
+
+    def classifier_instance(self):
+        """Return GenomicSubstitutionClassifier instance."""
+        return GenomicSubstitutionClassifier()
+
+    def fixture_name(self):
+        """Return GenomicSubstitutionClassifier fixture name."""
+        return 'genomic_substitution'

tests/fixtures/classifiers.yml

@@ -17,7 +17,6 @@ fusion:
     - query: fused
     - query: fusio
 
-
 amino_acid_substitution:
   should_match:
     - query: BRAF V600E
@@ -63,3 +62,97 @@ silent_mutation:
       confidence: ConfidenceRating.INTERSECTION
   should_not_match:
     - query: Leu862==
+
+coding_dna_substitution:
+  should_match:
+    - query: V170D (c.509T>A)
+      confidence: ConfidenceRating.SUPERSET
+    - query: NM_000551.3:c.292T>C
+      confidence: ConfidenceRating.EXACT
+    - query: NM_000551.3:c.292TC
+      confidence: ConfidenceRating.INTERSECTION
+    - query: foo Y98H (c.292T>C)
+      confidence: ConfidenceRating.SUPERSET
+    - query: BRAF V600E c.23T>A
+      confidence: ConfidenceRating.EXACT
+    - query: LRG_199t1:c.54G>H
+      confidence: ConfidenceRating.EXACT
+  should_not_match:
+    - query: V170 (c.509F>A)
+    - query: RX_:g.292TC
+
+genomic_substitution:
+  should_match:
+    - query: V170D (g.509T>A)
+      confidence: ConfidenceRating.SUPERSET
+    - query:  NC_000017.10:g.292T>C
+      confidence: ConfidenceRating.EXACT
+    - query:  NC_000017.10:g.292TC
+      confidence: ConfidenceRating.INTERSECTION
+    - query: foo Y98H (g.292T>C)
+      confidence: ConfidenceRating.SUPERSET
+    - query: BRAF V600E g.23T>A
+      confidence: ConfidenceRating.EXACT
+  should_not_match:
+    - query: V170 (g.509F>A)
+    - query: RX_:c.292TC
+
+coding_dna_silent_mutation:
+  should_match:
+    - query: NM_004006.2:c.123=
+      confidence: ConfidenceRating.EXACT
+    - query: foo VHL c.123=
+      confidence: ConfidenceRating.SUPERSET
+  should_not_match:
+    - query: CODING_DNA_:c.123=
+    - query: g.123=
+
+genomic_silent_mutation:
+  should_match:
+    - query: NC_000017.10:g.123=
+      confidence: ConfidenceRating.EXACT
+    - query: foo VHL g.123=
+      confidence: ConfidenceRating.SUPERSET
+  should_not_match:
+    - query: GENOMIC_:g.123=
+    - query: c.123=
+
+coding_dna_delins:
+  should_match:
+    - query: NM_005157.6:c.1423_1424delinsGT
+      confidence: ConfidenceRating.EXACT
+    - query: ENST00000277541.6:c.7330delinsACA
+      confidence: ConfidenceRating.EXACT
+    - query: NM_000797.3:c.812_829delins908_925
+      confidence: ConfidenceRating.INTERSECTION
+    - query: foo c.131_234delinsA
+      confidence: ConfidenceRating.SUPERSET
+    - query: foo NM_005157.6:c.1423_1424delinsGT
+      confidence: ConfidenceRating.INTERSECTION
+    - query: NM_000551.3:c.615delinsAA
+      confidence: ConfidenceRating.EXACT
+    - query: LRG_199t1:c.79_80delinsTT
+      confidence: ConfidenceRating.EXACT
+    - query: LRG_199:c.79_80delinsTT
+      confidence: ConfidenceRating.EXACT
+  should_not_match:
+    - query: N_005157.6:g.1423_1424delinsGT
+    - query: c.1423delinsX
+
+genomic_delins:
+  should_match:
+    - query: NC_000017.10:g.1423_1424delinsGT
+      confidence: ConfidenceRating.EXACT
+    - query:  NC_000017.10:g.7330delinsACA
+      confidence: ConfidenceRating.EXACT
+    - query:  NC_000017.10:g.812_829delins908_925
+      confidence: ConfidenceRating.INTERSECTION
+    - query: foo g.131_234delinsA
+      confidence: ConfidenceRating.SUPERSET
+    - query: foo  NC_000017.10:g.1423_1424delinsGT
+      confidence: ConfidenceRating.INTERSECTION
+    - query: NC_000003.12:g.10149938delinsAA
+      confidence: ConfidenceRating.EXACT
+  should_not_match:
+    - query:  N_000017.10:c.1423_1424delinsGT
+    - query: g.1423delinsX

tests/fixtures/tokenizers.yml

@@ -89,8 +89,144 @@ silent_mutation:
 hgvs:
   should_match:
     - token: NC_000007.13:g.36561662C>T
-    - token: LRG_199p1:p.Trp24Cys
     - token: NM_01234.5:c.22+1A>T
     - token: NP_000918.2:p.Ile1145=
   should_not_match:
     - token: NP004324.2
+    - token: ERBB2:c.2326_2327delinsCT
+
+coding_dna_substitution:
+  should_match:
+    - token: (c.292T>C)
+    - token: c.292T>C
+    - token: (c.233A>G)
+    - token: c.509T>A
+    - token: c.54G>H
+  should_not_match:
+    - token: (c.292T>C
+    - token: g.292T>C
+    - token: c.292T<C
+    - token: c.292Z>C
+    - token: c.j324T<C
+    - token: 292T<C
+    - token: c.509T>
+    - token: c.509>A
+    - token: c.T>A
+
+genomic_substition:
+  should_match:
+    - token: (g.292T>C)
+    - token: g.292T>C
+    - token: (g.233A>G)
+    - token: g.509T>A
+    - token: g.54G>H
+  should_not_match:
+    - token: (g.292T>C
+    - token: c.292T>C
+    - token: g.292T<C
+    - token: g.292Z>C
+    - token: g.j324T<C
+    - token: 292T<C
+    - token: g.509T>
+    - token: g.509>A
+    - token: g.T>A
+
+coding_dna_silent_mutation:
+  should_match:
+    - token: c.123=
+    - token: (c.123=)
+  should_not_match:
+    - token: c.292T>C
+    - token: g.292T>C
+    - token: g.123
+    - token: (c.123=
+    - token: c.123=)
+    - token: c.123
+    - token: c.123==
+
+genomic_silent_mutation:
+  should_match:
+    - token: g.123=
+    - token: (g.123=)
+  should_not_match:
+    - token: c.292T>C
+    - token: c.292T>C
+    - token: c.123
+    - token: (g.123=
+    - token: g.123=)
+    - token: g.123
+    - token: g.123==
+
+
+coding_dna_delins:
+  should_match:
+    - token: c.32386323delinsGA
+    - token: c.6775_6777delinsC
+    - token: c.145_147delinsTGG
+    - token: c.9002_9009delinsTTT
+    - token: c.850_901delinsTTCCTCGATGCCTG
+#    - token: c.42522624_42522669delins42536337_42536382
+#    - token: c.812_829delins908_925
+    - token: (c.301_302delinsGG)
+    - token: c.615delinsAA
+  should_not_match:
+    - token: c.150_147delinsTGG
+    - token: 32386323delinsGA
+    - token: c.145_147delinsTGGS
+    - token: c.145_147delTGG
+    - token: g.32386323delinsGA
+    - token: NM_000797.3:c.812_829delins908_
+    - token: c.42522624_42522669delins_42536382
+    - token: c.delinsGA
+    - token: c.32386323delins
+    - token: (c.301_302delinsGG
+    - token: c.delins
+    - token: delins
+    - token: c._147delinsTGG
+    - token: c.145_delinsTGG
+    - token: c.delinsTGG
+    - token: c.d_delinsTG
+
+
+genomic_delins:
+  should_match:
+    - token: g.32386323delinsGA
+    - token: g.6775_6777delinsC
+    - token: g.145_147delinsTGG
+    - token: g.9002_9009delinsTTT
+    - token: g.850_901delinsTTCCTCGATGCCTG
+#    - token: g.42522624_42522669delins42536337_42536382
+#    - token: g.812_829delins908_925
+    - token: (g.301_302delinsGG)
+    - token: g.10149938delinsAA
+  should_not_match:
+    - token: g.150_147delinsTGG
+    - token: 32386323delinsGA
+    - token: g.145_147delinsTGGS
+    - token: g.145_147delTGG
+    - token: c.32386323delinsGA
+    - token: NM_000797.3:g.812_829delins908_
+    - token: g.42522624_42522669delins_42536382
+    - token: g.delinsGA
+    - token: g.32386323delins
+    - token: (g.301_302delinsGG
+    - token: g.delins
+    - token: delins
+    - token: g._147delinsTGG
+    - token: g.145_delinsTGG
+    - token: g.delinsTGG
+    - token: g.d_delinsTG
+
+locus_reference_genomic:
+  should_match:
+    - token: LRG_199
+    - token: LRG_199t1
+    - token: LRG_199p1
+  should_not_match:
+    - token: LRG_199t1p1
+    - token: LRG_199p1t1
+    - token: LRG_
+    - token: LRG_t1
+    - token: LRG_p1
+    - token: LRGt1
+    - token: LRGp1