Merge pull request #56 from GeneDx/develop

update master

.github/workflows/pythonpackage.yml

@@ -26,4 +26,4 @@ jobs:
 
     - name: Test with unittest
       run: |
-        pytest tests
+        python -m unittest

Pipfile

@@ -9,7 +9,7 @@ pytest = "*"
 pytest-cov = "*"
 
 [packages]
-nltk = "==3.4.5"
+nltk = "==3.6.5"
 spacy = "==2.2.4"
 scispacy = "==0.2.4"
 negspacy = "==0.1.9"

README.md

@@ -52,8 +52,8 @@ print(result.hpids)
 ```
 
 `txt2hpo` handles negation using [negspaCy](https://spacy.io/universe/project/negspacy). To remove negated phenotypes set `remove_negated` flag to True.
+ Both the extracted and negated HPO terms can be retrieved.
 
-
 ```python 
 from txt2hpo.extract import Extractor
 extract = Extractor(remove_negated=True)
@@ -62,7 +62,10 @@ result = extract.hpo("patient has developmental delay but no hypotonia")
 print(result.hpids)
 
 ["HP:0001263"]
-
+
+print(result.negated_hpids)
+
+["HP:0001252"]
 
 ```
 

tests/test_extract.py

@@ -424,3 +424,33 @@ def test_handling_term_hyphenation(self):
             # replace hyphens with space
             hpids = extract.hpo(test[0].replace('-', ' ')).hpids
             self.assertEqual(hpids, [test[1]])
+
+    def test_negated_hpo_retention(self):
+        extract = Extractor(correct_spelling=False,
+                            remove_overlapping=True,
+                            resolve_conflicts=True,
+                            max_neighbors=2,
+                            phenotypes_only=False,
+                            remove_negated=True)
+
+        resp = extract.hpo("Patient has developmental delay but no hypotonia")
+        self.assertEqual(["HP:0001252"], resp.negated_hpids)
+
+        resp = extract.hpo("developmental delay and a wide mouth")
+        self.assertEqual([], resp.negated_hpids)
+
+        resp = extract.hpo("developmental delay with no wide mouth")
+        self.assertEqual(['HP:0000154'], resp.negated_hpids)
+
+        resp = extract.hpo("developmental delay without a wide mouth")
+        self.assertEqual(['HP:0000154'], resp.negated_hpids)
+
+        resp = extract.hpo("no developmental delay, but has a wide mouth")
+        self.assertEqual(['HP:0001263'], resp.negated_hpids)
+
+        resp = extract.hpo("the patient has a wide mouth but no developmental delay.")
+        self.assertEqual(['HP:0001263'], resp.negated_hpids)
+
+        resp = extract.hpo("the patient does not have either a wide mouth or developmental delay.")
+        self.assertEqual(set(['HP:0000154', 'HP:0001263']), set(resp.negated_hpids))
+

txt2hpo/__init__.py

@@ -1,2 +1,2 @@
 __project__ = 'txt2hpo'
-__version__ = '0.2.3'
+__version__ = '2021.0'

txt2hpo/extract.py

@@ -22,6 +22,7 @@ def __init__(self, entries=None, model=None, negation_model=None):
             self.entries = entries
         self.model = model
         self.negation_model = negation_model
+        self.negated_entries = []
 
     def add(self,entry):
         self.entries += entry
@@ -36,6 +37,7 @@ def remove_tagged(self, tag, state=True, status=True):
             to_remove = [entry for entry in self.entries if entry[tag] != state]
         for element in to_remove:
             self.remove(element)
+            self.negated_entries.append(element)
 
     def detect_negation(self):
         for entry in self.entries:
@@ -124,6 +126,10 @@ def resolve_conflicts(self):
     def hpids(self):
         return list(set(np.array([x['hpid'] for x in self.entries]).flatten()))
 
+    @property
+    def negated_hpids(self):
+        return list(set(np.array([x['hpid'] for x in self.negated_entries]).flatten()))
+
     @property
     def json(self):
         result = self.entries_sans_context.copy()