Merge branch 'mmaiers-nmdp-littlep'

Author: pbashyal-nmdp

pyard/data_repository.py

@@ -20,6 +20,7 @@
 #    > http://www.fsf.org/licensing/licenses/lgpl.html
 #    > http://www.opensource.org/licenses/lgpl-license.php
 #
+from collections import namedtuple
 import functools
 import sqlite3
 
@@ -37,6 +38,9 @@
 # List of expression characters
 expression_chars = ['N', 'Q', 'L', 'S']
 
+ars_mapping_tables = ['dup_g', 'dup_lg', 'dup_lgx', 'g_group', 'lg_group', 'lgx_group']
+ARSMapping = namedtuple("ARSMapping", ars_mapping_tables)
+
 
 def get_n_field_allele(allele: str, n: int) -> str:
     """
@@ -64,12 +68,15 @@ def get_2field_allele(a: str) -> str:
 
 
 def generate_ars_mapping(db_connection: sqlite3.Connection, imgt_version):
-    if db.tables_exists(db_connection, ['dup_g', 'g_group', 'lg_group', 'lgx_group']):
+    if db.tables_exists(db_connection, ars_mapping_tables):
         dup_g = db.load_dict(db_connection, table_name='dup_g', columns=('allele', 'g_group'))
+        dup_lg = db.load_dict(db_connection, table_name='dup_lg', columns=('allele', 'lg_group'))
+        dup_lgx = db.load_dict(db_connection, table_name='dup_lgx', columns=('allele', 'lgx_group'))
         g_group = db.load_dict(db_connection, table_name='g_group', columns=('allele', 'g'))
         lg_group = db.load_dict(db_connection, table_name='lg_group', columns=('allele', 'lg'))
         lgx_group = db.load_dict(db_connection, table_name='lgx_group', columns=('allele', 'lgx'))
-        return dup_g, g_group, lg_group, lgx_group
+        return ARSMapping(dup_g=dup_g, dup_lg=dup_lg, dup_lgx=dup_lgx,
+                          g_group=g_group, lg_group=lg_group, lgx_group=lgx_group)
 
     ars_url = f'{IMGT_HLA_URL}{imgt_version}/wmda/hla_nom_g.txt'
     df = pd.read_csv(ars_url, skiprows=6, names=["Locus", "A", "G"], sep=";").dropna()
@@ -81,17 +88,38 @@ 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]))
 
+    # multiple Gs
     mg = df.drop_duplicates(['2d', 'G'])['2d'].value_counts()
     multiple_g_list = mg[mg > 1].reset_index()['index'].to_list()
 
+    # Keep only the alleles that have more than 1 mapping
     dup_g = df[df['2d'].isin(multiple_g_list)][['G', '2d']] \
         .drop_duplicates() \
         .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]))
+    # multiple lg
+    mlg = df.drop_duplicates(['2d', 'lg'])['2d'].value_counts()
+    multiple_lg_list = mlg[mlg > 1].reset_index()['index'].to_list()
+
+    # Keep only the alleles that have more than 1 mapping
+    dup_lg = df[df['2d'].isin(multiple_lg_list)][['lg', '2d']] \
+        .drop_duplicates() \
+        .groupby('2d', as_index=True).agg("/".join) \
+        .to_dict()['lg']
+
+    # multiple lgx
+    mlgx = df.drop_duplicates(['2d', 'lgx'])['2d'].value_counts()
+    multiple_lgx_list = mlgx[mlgx > 1].reset_index()['index'].to_list()
+
+    # Keep only the alleles that have more than 1 mapping
+    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 +144,14 @@ 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 ARSMapping(dup_g=dup_g, dup_lg=dup_lg, dup_lgx=dup_lgx,
+                      g_group=g_group, lg_group=lg_group, lgx_group=lgx_group)
 
 
 def generate_alleles_and_xx_codes(db_connection: sqlite3.Connection, imgt_version):
@@ -331,7 +362,8 @@ def generate_serology_mapping(db_connection: sqlite3.Connection, imgt_version):
 
         # re-sort allele lists into smartsort order
         for sero in sero_mapping.keys():
-           sero_mapping[sero] =  '/'.join(sorted(sero_mapping[sero].split('/'), key=functools.cmp_to_key(smart_sort_comparator)))
+            sero_mapping[sero] = '/'.join(
+                sorted(sero_mapping[sero].split('/'), key=functools.cmp_to_key(smart_sort_comparator)))
 
         # Save the serology mapping to db
         db.save_dict(db_connection, table_name='serology_mapping',

pyard/pyard.py

@@ -26,7 +26,8 @@
 from typing import Iterable
 
 from . import db
-from .data_repository import generate_ars_mapping, generate_mac_codes, generate_alleles_and_xx_codes, \
+from .data_repository import generate_ars_mapping, \
+    generate_mac_codes, generate_alleles_and_xx_codes, \
     generate_serology_mapping, generate_v2_to_v3_mapping
 from .db import is_valid_mac_code, mac_code_to_alleles, v2_to_v3_allele
 from .smart_sort import smart_sort_comparator
@@ -63,7 +64,7 @@ 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.ars_mappings = generate_ars_mapping(self.db_connection, imgt_version)
         # Load Serology mappings
         generate_serology_mapping(self.db_connection, imgt_version)
         # Load V2 to V3 mappings
@@ -111,21 +112,25 @@ def redux(self, allele: str, ars_type: str) -> str:
         if allele.endswith(('P', 'G')):
             allele = allele[:-1]
 
-        if ars_type == "G" and allele in self._G:
-            if allele in self.dup_g:
-                return self.dup_g[allele]
+        if ars_type == "G" and allele in self.ars_mappings.g_group:
+            if allele in self.ars_mappings.dup_g:
+                return self.ars_mappings.dup_g[allele]
             else:
-                return self._G[allele]
+                return self.ars_mappings.g_group[allele]
         elif ars_type == "lg":
-            if allele in self._lg:
-                return self._lg[allele]
+            if allele in self.ars_mappings.dup_lg:
+                return self.ars_mappings.dup_lg[allele]
+            elif allele in self.ars_mappings.lg_group:
+                return self.ars_mappings.lg_group[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:
-                return self._lgx[allele]
+            if allele in self.ars_mappings.dup_lgx:
+                return self.ars_mappings.dup_lgx[allele]
+            elif allele in self.ars_mappings.lgx_group:
+                return self.ars_mappings.lgx_group[allele]
             else:
                 # for 'lgx' when allele is not in G group,
                 # return allele with only first 2 field
@@ -296,7 +301,8 @@ def _get_alleles_from_serology(self, serology) -> Iterable[str]:
         else:
             return alleles
 
-    def _combine_with_colon(self, digits_field):
+    @staticmethod
+    def _combine_with_colon(digits_field):
         num_of_digits = len(digits_field)
         return ':'.join(digits_field[i:i + 2] for i in range(0, num_of_digits, 2))
 
@@ -424,11 +430,11 @@ def toG(self, allele: str) -> str:
         :return: ARS G reduced allele
         :rtype: str
         """
-        if allele in self._G:
-            if allele in self.dup_g:
-                return self.dup_g[allele]
+        if allele in self.ars_mappings.g_group:
+            if allele in self.ars_mappings.dup_g:
+                return self.ars_mappings.dup_g[allele]
             else:
-                return self._G[allele]
+                return self.ars_mappings.g_group[allele]
         else:
             return "X"
 

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   |