Merge pull request #360 from apriltuesday/february-fixes

deduplicate clinical significances

eva_cttv_pipeline/clinvar_xml_io/clinvar_xml_io/clinvar_xml_io.py

@@ -176,11 +176,11 @@ def clinical_significance_raw(self):
 
     @property
     def clinical_significance_list(self):
-        """The normalised list of all clinical significance values. The original value is (1) split into multiple values
-        by 3 delimiters: ('/', ', ', '; '), (2) converted into lowercase and (3) sorted lexicographically. Example:
-        'Benign/Likely benign, risk_factor' → ['benign', 'likely benign', 'risk factor']. See /data-exploration/
-        clinvar-variant-types/README.md for further explanation."""
-        return sorted(re.split('/|, |; ', self.clinical_significance_raw.lower().replace('_', ' ')))
+        """The normalised deduplicated list of all clinical significance values. The original value is (1) split into
+        multiple values by 3 delimiters: ('/', ', ', '; '), (2) converted into lowercase and (3) sorted
+        lexicographically. Example: 'Benign/Likely benign, risk_factor' → ['benign', 'likely benign', 'risk factor'].
+        See /data-exploration/clinvar-variant-types/README.md for further explanation."""
+        return sorted(list(set(re.split('/|, |; ', self.clinical_significance_raw.lower().replace('_', ' ')))))
 
     @property
     def allele_origins(self):

setup.py

@@ -10,7 +10,7 @@ def get_requires():
 
 
 setup(name='eva_cttv_pipeline',
-      version='2.7.2',
+      version='2.7.3',
       packages=find_packages(),
       install_requires=get_requires(),
       #! TBD: list as a dependency subpackage 'clinvar_xml_utils.clinvar_xml_utils.clinvar_xml_utils'