Merge branch 'littlep' of https://github.com/mmaiers-nmdp/py-ard into mmaiers-nmdp-littlep

Author: pbashyal-nmdp

pyard/data_repository.py

@@ -81,6 +81,8 @@ def generate_ars_mapping(db_connection: sqlite3.Connection, imgt_version):
 
     df['2d'] = df['A'].apply(get_2field_allele)
     df['3d'] = df['A'].apply(get_3field_allele)
+    df['lg'] = df['G'].apply(lambda a: ":".join(a.split(":")[0:2]) + "g")
+    df['lgx'] = df['G'].apply(lambda a: ":".join(a.split(":")[0:2]))
 
     mg = df.drop_duplicates(['2d', 'G'])['2d'].value_counts()
     multiple_g_list = mg[mg > 1].reset_index()['index'].to_list()
@@ -90,8 +92,23 @@ def generate_ars_mapping(db_connection: sqlite3.Connection, imgt_version):
         .groupby('2d', as_index=True).agg("/".join) \
         .to_dict()['G']
 
-    df['lg'] = df['G'].apply(lambda a: ":".join(a.split(":")[0:2]) + "g")
-    df['lgx'] = df['G'].apply(lambda a: ":".join(a.split(":")[0:2]))
+    mlg = df.drop_duplicates(['2d', 'lg'])['2d'].value_counts()
+    multiple_lg_list = mlg[mlg > 1].reset_index()['index'].to_list()
+
+    dup_lg = df[df['2d'].isin(multiple_lg_list)][['lg', '2d']] \
+        .drop_duplicates() \
+        .groupby('2d', as_index=True).agg("/".join) \
+        .to_dict()['lg']
+
+    mlgx = df.drop_duplicates(['2d', 'lgx'])['2d'].value_counts()
+    multiple_lgx_list = mlgx[mlgx > 1].reset_index()['index'].to_list()
+
+    dup_lgx = df[df['2d'].isin(multiple_lgx_list)][['lgx', '2d']] \
+        .drop_duplicates() \
+        .groupby('2d', as_index=True).agg("/".join) \
+        .to_dict()['lgx']
+
+
 
     # Creating dictionaries with mac_code->ARS group mapping
     df_g = pd.concat([
@@ -116,11 +133,13 @@ def generate_ars_mapping(db_connection: sqlite3.Connection, imgt_version):
     lgx_group = df_lgx.set_index('A')['lgx'].to_dict()
 
     db.save_dict(db_connection, table_name='dup_g', dictionary=dup_g, columns=('allele', 'g_group'))
+    db.save_dict(db_connection, table_name='dup_lg', dictionary=dup_lg, columns=('allele', 'lg_group'))
+    db.save_dict(db_connection, table_name='dup_lgx', dictionary=dup_lgx, columns=('allele', 'lgx_group'))
     db.save_dict(db_connection, table_name='g_group', dictionary=g_group, columns=('allele', 'g'))
     db.save_dict(db_connection, table_name='lg_group', dictionary=lg_group, columns=('allele', 'lg'))
     db.save_dict(db_connection, table_name='lgx_group', dictionary=lgx_group, columns=('allele', 'lgx'))
 
-    return dup_g, g_group, lg_group, lgx_group
+    return dup_g, dup_lg, dup_lgx, g_group, lg_group, lgx_group
 
 
 def generate_alleles_and_xx_codes(db_connection: sqlite3.Connection, imgt_version):

pyard/pyard.py

@@ -63,7 +63,7 @@ def __init__(self, imgt_version: str = 'Latest',
         # Load Alleles and XX Codes
         self.valid_alleles, self.xx_codes = generate_alleles_and_xx_codes(self.db_connection, imgt_version)
         # Load ARS mappings
-        self.dup_g, self._G, self._lg, self._lgx = generate_ars_mapping(self.db_connection, imgt_version)
+        self.dup_g, self.dup_lg, self.dup_lgx, self._G, self._lg, self._lgx = generate_ars_mapping(self.db_connection, imgt_version)
         # Load Serology mappings
         generate_serology_mapping(self.db_connection, imgt_version)
         # Load V2 to V3 mappings
@@ -117,14 +117,18 @@ def redux(self, allele: str, ars_type: str) -> str:
             else:
                 return self._G[allele]
         elif ars_type == "lg":
-            if allele in self._lg:
+            if allele in self.dup_lg:
+                return self.dup_lg[allele]
+            elif allele in self._lg:
                 return self._lg[allele]
             else:
                 # for 'lg' when allele is not in G group,
                 # return allele with only first 2 field
                 return ':'.join(allele.split(':')[0:2]) + 'g'
         elif ars_type == "lgx":
-            if allele in self._lgx:
+            if allele in self.dup_lgx:
+                return self.dup_lgx[allele]
+            elif allele in self._lgx:
                 return self._lgx[allele]
             else:
                 # for 'lgx' when allele is not in G group,

tests/environment.py

@@ -2,4 +2,4 @@
 
 
 def before_all(context):
-    context.ard = ARD('3290', data_dir='/tmp/py-ard')
+    context.ard = ARD('3440', data_dir='/tmp/py-ard')

tests/features/allele.feature

@@ -7,17 +7,19 @@ Feature: Alleles
     Then the reduced allele is found to be <Redux Allele>
 
     Examples:
-      | Allele         | Level | Redux Allele    |
-      | A*01:01:01     | G     | A*01:01:01G     |
-      | A*01:01:01     | lg    | A*01:01g        |
-      | A*01:01:01     | lgx   | A*01:01         |
+      | Allele         | Level | Redux Allele      |
+      | A*01:01:01     | G     | A*01:01:01G       |
+      | A*01:01:01     | lg    | A*01:01g          |
+      | A*01:01:01     | lgx   | A*01:01           |
 
-      | HLA-A*01:01:01 | G     | HLA-A*01:01:01G |
-      | HLA-A*01:01:01 | lg    | HLA-A*01:01g    |
-      | HLA-A*01:01:01 | lgx   | HLA-A*01:01     |
+      | HLA-A*01:01:01 | G     | HLA-A*01:01:01G   |
+      | HLA-A*01:01:01 | lg    | HLA-A*01:01g      |
+      | HLA-A*01:01:01 | lgx   | HLA-A*01:01       |
 
-      | DRB1*14:05:01  | lgx   | DRB1*14:05      |
-      | DRB1*14:05:01  | lg    | DRB1*14:05g     |
+      | DRB1*14:05:01  | lgx   | DRB1*14:05        |
+      | DRB1*14:05:01  | lg    | DRB1*14:05g       |
 
-      | DRB1*14:06:01  | lgx   | DRB1*14:06      |
-      | DRB1*14:06:01  | lg    | DRB1*14:06g     |
+      | DRB1*14:06:01  | lgx   | DRB1*14:06        |
+      | DRB1*14:06:01  | lg    | DRB1*14:06g       |
+      | C*02:02        | lg    | C*02:02g/C*02:10g |
+      | C*02:02        | lgx   | C*02:02/C*02:10   |