Merge pull request #51 from cancervariants/issue-50

Remove duplicates
cancervariants · Feb 26, 2021 · 23c1e8b · 23c1e8b
2 parents b9aa617 + 2cb0287
commit 23c1e8b
Show file tree

Hide file tree

Showing 4 changed files with 31 additions and 2 deletions.
diff --git a/main.py b/main.py
@@ -67,7 +67,9 @@ def translate(q: str = Query(..., description=q_description)):
 
     translations = []
     for valid_variant in validations.valid_results:
-        translations.append(translator.perform(valid_variant))
+        result = translator.perform(valid_variant)
+        if result not in translations:
+            translations.append(result)
     return TranslationResponseSchema(
         search_term=q,
         variants=translations

diff --git a/tests/fixtures/translators.yml b/tests/fixtures/translators.yml
@@ -37,6 +37,26 @@ amino_acid_substitution:
           "type": "Allele"
         }
       ]
+    - query: NP_004324.2:p.Val600Glu
+      variants: [
+        {
+          "id": "ga4gh:VA.mJbjSsW541oOsOtBoX36Mppr6hMjbjFr",
+          "location": {
+            "interval": {
+              "end": 600,
+              "start": 599,
+              "type": "SimpleInterval"
+            },
+            "sequence_id": "ga4gh:SQ.cQvw4UsHHRRlogxbWCB8W-mKD4AraM9y",
+            "type": "SequenceLocation"
+          },
+          "state": {
+            "sequence": "E",
+            "type": "SequenceState"
+          },
+          "type": "Allele"
+        }
+      ]
 
 
 polypeptide_truncation:

diff --git a/tests/fixtures/validators.yml b/tests/fixtures/validators.yml
@@ -3,6 +3,7 @@ amino_acid_substitution:
     - query: BRAF V600E
     - query: NP_004324.2:p.Val600Glu
     - query: NP_005219.2:p.Thr790Met
+    - query: EGFR Leu858Arg
   should_not_match:
     - query: NP_004324.2:p.Val600000000000Glu
     - query: NP_004324.2:p.Glu600Val

diff --git a/variant/validators/polypeptide_sequence_variant_base.py b/variant/validators/polypeptide_sequence_variant_base.py
@@ -96,6 +96,13 @@ def get_vrs_allele(self, sequence_id, s) -> dict:
         )
 
         state = models.SequenceState(sequence=s.alt_protein)
+        state_dict = state.as_dict()
+        if len(state_dict['sequence']) == 3:
+            for one, three in \
+                    self._amino_acid_cache._amino_acid_code_conversion.items():
+                if three == state_dict['sequence']:
+                    state.sequence = one
+
         allele = models.Allele(location=seq_location,
                                state=state)
         allele['_id'] = ga4gh_identify(allele)
@@ -133,7 +140,6 @@ def get_valid_invalid_results(self, classification_tokens, transcripts,
             tokens
         :param list results: A list to store validation result objects
         """
-
         for s in classification_tokens:
             for t in transcripts:
                 valid = True