wormbase is now integrated into AllianceGenome

biothings · Jul 24, 2024 · 53b752b · 53b752b
1 parent dd05f39
commit 53b752b
Show file tree

Hide file tree

Showing 5 changed files with 101 additions and 90 deletions.
diff --git a/src/config_web.py b/src/config_web.py
@@ -80,7 +80,7 @@
     "ratmap:": r"RATMAP:",
     "rgd:": r"RGD:",
     "flybase:": r"FLYBASE:",
-    "wormbase:": r"WormBase:",
+    # "wormbase:": r"WormBase:", # deprecated for alliancegenome
     "tair:": r"TAIR:",
     "zfin:": r"ZFIN:",
     "sgd:": r"SGD:",

diff --git a/src/hub/dataload/sources/entrez/gene_upload.py b/src/hub/dataload/sources/entrez/gene_upload.py
@@ -1,8 +1,8 @@
-from .parser import GeneInfoParser
-from .parser import get_geneid_d
 import biothings.hub.dataload.uploader as uploader
 from biothings.utils.common import dump2gridfs
 
+from .parser import GeneInfoParser, get_geneid_d
+
 
 class EntrezGeneUploader(uploader.MergerSourceUploader):
 
@@ -22,8 +22,16 @@ def get_geneid_d(self, *args, **kwargs):
     def post_update_data(self, *args, **kwargs):
         self.logger.info('Uploading "geneid_d" to GridFS...')
         geneid_d = self.get_geneid_d(load_cache=False, save_cache=False)
-        dump2gridfs(geneid_d, self.name + '__geneid_d.pyobj', self.db)
-        for field in ["MGI", "HGNC", "RGD", "TAIR", "WormBase", "ZFIN", "SGD", "FLYBASE"]:
+        dump2gridfs(geneid_d, self.name + "__geneid_d.pyobj", self.db)
+        for field in [
+            "MGI",
+            "HGNC",
+            "RGD",
+            "TAIR",
+            "ZFIN",
+            "SGD",
+            "FLYBASE",
+        ]:
             self.logger.info("Indexing '%s'" % field)
             self.collection.create_index(field, background=True)
 
@@ -33,105 +41,87 @@ def get_mapping(klass):
             "entrezgene": {
                 "type": "keyword",
                 "normalizer": "keyword_lowercase_normalizer",
-                "copy_to": "all"
-            },
-            "taxid": {
-                "type": "integer"
+                "copy_to": "all",
             },
+            "taxid": {"type": "integer"},
             "alias": {
                 "type": "keyword",
                 "normalizer": "keyword_lowercase_normalizer",
-                "copy_to": "all"
-            },
-            "name": {
-                "type": "text",
-                "copy_to": "all"
-            },
-            "other_names": {
-                "type": "text",
-                "copy_to": "all"
+                "copy_to": "all",
             },
+            "name": {"type": "text", "copy_to": "all"},
+            "other_names": {"type": "text", "copy_to": "all"},
             "symbol": {
                 "type": "keyword",
                 "normalizer": "keyword_lowercase_normalizer",
-                "copy_to": "all"
+                "copy_to": "all",
             },
             "locus_tag": {
                 "type": "keyword",
                 "normalizer": "keyword_lowercase_normalizer",
-                "copy_to": "all"
+                "copy_to": "all",
             },
-
             # do not index map_location and type_of_gene
-            "map_location": {
-                "index": False,
-                "type": "text"
-            },
+            "map_location": {"index": False, "type": "text"},
             "type_of_gene": {
                 "normalizer": "keyword_lowercase_normalizer",
-                "type": "keyword"
-            },
-            "AnimalQTLdb": {
-                "index": False,
-                "type": "text"
-            },
-            "Vega": {
-                "index": False,
-                "type": "text"
+                "type": "keyword",
             },
-
+            "AnimalQTLdb": {"index": False, "type": "text"},
+            "Vega": {"index": False, "type": "text"},
             # convert index_name to lower-case, and excluded from "_all"
             "HGNC": {
-                "type": "keyword",              # 1771
-                "normalizer": "keyword_lowercase_normalizer"
+                "type": "keyword",  # 1771
+                "normalizer": "keyword_lowercase_normalizer",
             },
             "HPRD": {
-                "type": "keyword",              # 00310
-                "normalizer": "keyword_lowercase_normalizer"
+                "type": "keyword",  # 00310
+                "normalizer": "keyword_lowercase_normalizer",
             },
             "MIM": {
-                "type": "keyword",              # 116953
-                "normalizer": "keyword_lowercase_normalizer"
+                "type": "keyword",  # 116953
+                "normalizer": "keyword_lowercase_normalizer",
             },
             "MGI": {
-                "type": "keyword",              # MGI:104772
-                "normalizer": "keyword_lowercase_normalizer"
-            },
-            "RATMAP": {
-                "type": "keyword",
-                "normalizer": "keyword_lowercase_normalizer"
+                "type": "keyword",  # MGI:104772
+                "normalizer": "keyword_lowercase_normalizer",
             },
+            "RATMAP": {"type": "keyword", "normalizer": "keyword_lowercase_normalizer"},
             "RGD": {
-                "type": "keyword",             # 70486
-                "normalizer": "keyword_lowercase_normalizer"
+                "type": "keyword",  # 70486
+                "normalizer": "keyword_lowercase_normalizer",
             },
             "FLYBASE": {
-                "type": "keyword",            # FBgn0004107
-                "normalizer": "keyword_lowercase_normalizer"
+                "type": "keyword",  # FBgn0004107
+                "normalizer": "keyword_lowercase_normalizer",
             },
-            "WormBase": {
-                "type": "keyword",         # WBGene00000871
-                "normalizer": "keyword_lowercase_normalizer"
+            # "WormBase": {
+            #     "type": "keyword",         # WBGene00000871
+            #     "normalizer": "keyword_lowercase_normalizer"
+            # },
+            "AllianceGenome": {
+                "type": "keyword",  # WBGene00019362
+                "normalizer": "keyword_lowercase_normalizer",
             },
             "TAIR": {
-                "type": "keyword",             # AT3G48750
-                "normalizer": "keyword_lowercase_normalizer"
+                "type": "keyword",  # AT3G48750
+                "normalizer": "keyword_lowercase_normalizer",
             },
             "ZFIN": {
-                "type": "keyword",             # ZDB-GENE-040426-2741
-                "normalizer": "keyword_lowercase_normalizer"
+                "type": "keyword",  # ZDB-GENE-040426-2741
+                "normalizer": "keyword_lowercase_normalizer",
             },
             "SGD": {
-                "type": "keyword",             # S000003566
-                "normalizer": "keyword_lowercase_normalizer"
+                "type": "keyword",  # S000003566
+                "normalizer": "keyword_lowercase_normalizer",
             },
             "Xenbase": {
                 "type": "keyword",
-                "normalizer": "keyword_lowercase_normalizer"
+                "normalizer": "keyword_lowercase_normalizer",
             },
             "miRBase": {
                 "type": "keyword",
-                "normalizer": "keyword_lowercase_normalizer"
+                "normalizer": "keyword_lowercase_normalizer",
             },
         }
         return mapping
diff --git a/src/hub/datatransform/keylookup.py b/src/hub/datatransform/keylookup.py
@@ -3,51 +3,70 @@
 
 graph_mygene = nx.DiGraph()
 
-for field in ["entrez","ensembl","uniprot","mgi","hgnc","rgd","tair","wormbase","zfin","sgd","flybase"]:
+for field in [
+    "entrez",
+    "ensembl",
+    "uniprot",
+    "mgi",
+    "hgnc",
+    "rgd",
+    "tair",
+    "zfin",
+    "sgd",
+    "flybase",
+]:
     graph_mygene.add_node(field)
 
 
-graph_mygene.add_edge('swissprot', 'entrez',
-        object=MongoDBEdge('uniprot',
-                           lookup='uniprot.Swiss-Prot',
-                           field='_id'))
+graph_mygene.add_edge(
+    "swissprot",
+    "entrez",
+    object=MongoDBEdge("uniprot", lookup="uniprot.Swiss-Prot", field="_id"),
+)
 
-graph_mygene.add_edge('swissprot', 'swissprot',
-        object=MongoDBEdge('uniprot',
-                           lookup='uniprot.Swiss-Prot',
-                           field='uniprot.Swiss-Prot'))
+graph_mygene.add_edge(
+    "swissprot",
+    "swissprot",
+    object=MongoDBEdge(
+        "uniprot", lookup="uniprot.Swiss-Prot", field="uniprot.Swiss-Prot"
+    ),
+)
 
-graph_mygene.add_edge('trembl', 'entrez',
-        object=MongoDBEdge('uniprot',
-                           lookup='uniprot.TrEMBL',
-                           field='_id'))
+graph_mygene.add_edge(
+    "trembl",
+    "entrez",
+    object=MongoDBEdge("uniprot", lookup="uniprot.TrEMBL", field="_id"),
+)
 
 # TODO: GeneID already contains entrez _id but we need to keep
 # the interface until keylookup is able to take from values
 # from docs
-graph_mygene.add_edge('entrez', 'entrez',
-        object=MongoDBEdge('entrez_gene',
-                           lookup='_id',
-                           field='_id'))
+graph_mygene.add_edge(
+    "entrez", "entrez", object=MongoDBEdge("entrez_gene", lookup="_id", field="_id")
+)
 
-for field in ["MGI","HGNC","RGD","TAIR","WormBase","ZFIN","SGD","FLYBASE"]:
-    graph_mygene.add_edge(field.lower(), 'entrez',
-            object=MongoDBEdge('entrez_gene',
-                               lookup=field,
-                               field='_id'))
+for field in ["MGI", "HGNC", "RGD", "TAIR", "ZFIN", "SGD", "FLYBASE"]:
+    graph_mygene.add_edge(
+        field.lower(),
+        "entrez",
+        object=MongoDBEdge("entrez_gene", lookup=field, field="_id"),
+    )
 
 
 # TODO: conversions from ensembl to entrez should be added but mappings are currently
 # computed and stored in mongo as files, not collections, so they can't be queried
 
 import pprint
+
 pprint.pprint(graph_mygene)
 
+
 class MyGeneKeyLookup(DataTransformMDB):
 
     def __init__(self, input_types, skip_on_failure=False):
-        super(MyGeneKeyLookup, self).__init__(graph_mygene,
-                input_types,
-                output_types=["entrez","ensembl"],
-                skip_on_failure=skip_on_failure)
-
+        super(MyGeneKeyLookup, self).__init__(
+            graph_mygene,
+            input_types,
+            output_types=["entrez", "ensembl"],
+            skip_on_failure=skip_on_failure,
+        )
diff --git a/src/tests/data_tests/test_1_annotation.py b/src/tests/data_tests/test_1_annotation.py
@@ -136,7 +136,7 @@ def test_104(self):
     def test_105(self):
         # this is not nematode, "taxid": 31234
         res = self.request("gene/171911").json()
-        assert "WormBase" in res
+        assert "AllianceGenome" in res
 
     def test_106(self):
         # fission yeast

diff --git a/src/tests/data_tests/test_4_input.py b/src/tests/data_tests/test_4_input.py
@@ -1,3 +1,4 @@
+import pytest
 from biothings.tests.web import BiothingsDataTest
 
 
@@ -44,6 +45,7 @@ def test_411_case_sensitivity(self):
         # case-insensitive sources
         self.query(q="mirbase:MI0017267")
 
+    @pytest.mark.skip("Deprecated now integrated into AllianceGenome")
     def test_412_case_sensitivity(self):
         self.query(q="wormbase:WBGene00019362", species=6239)