feat(*): updated WB pipeline and added option to load IBA from gaf files

alliance-genome · Mar 26, 2021 · caaeb1a · caaeb1a
1 parent 7db8e06
commit caaeb1a
Show file tree

Hide file tree

Showing 6 changed files with 35 additions and 15 deletions.
diff --git a/genedescriptions/api_manager.py b/genedescriptions/api_manager.py
@@ -12,7 +12,7 @@ def __init__(self, textpresso_api_token):
         self.textpresso_api_token = textpresso_api_token
         self.tpc_cache = {}
         self.class_cache = {}
-        self.tpc_api_endpoint = "https://textpressocentral.org:18080/v1/textpresso/api/get_documents_count"
+        self.tpc_api_endpoint = "http://textpressocentral.org:9001/v1/textpresso/api/get_documents_count"
         if not os.environ.get('PYTHONHTTPSVERIFY', '') and getattr(ssl, '_create_unverified_context', None):
             ssl._create_default_https_context = ssl._create_unverified_context
 
@@ -29,7 +29,7 @@ def get_textpresso_popularity(self, keyword: str):
             return self.tpc_cache[keyword]
         else:
             data = json.dumps({"token": self.textpresso_api_token, "query": {
-                "keywords": keyword, "type": "document", "corpora": ["C. elegans"]}})
+                "keywords": keyword, "type": "document", "corpora": ["C. elegans and Suppl"]}})
             data = data.encode('utf-8')
             req = urllib.request.Request(self.tpc_api_endpoint, data, headers={'Content-type': 'application/json',
                                                                                'Accept': 'application/json'})

diff --git a/genedescriptions/config_parser.py b/genedescriptions/config_parser.py
@@ -32,10 +32,10 @@ class GenedescConfigParser(object):
     def __init__(self, file_path):
         with open(file_path) as conf_file:
             self.config = yaml.safe_load(conf_file)
-            # self.add_go_do_not_annotate_to_blacklist(
-            #     'http://current.geneontology.org/ontology/subsets/gocheck_do_not_annotate.json')
-            # self.add_go_do_not_annotate_to_blacklist(
-            #     'http://current.geneontology.org/ontology/subsets/gocheck_do_not_manually_annotate.json')
+            self.add_go_do_not_annotate_to_blacklist(
+                'http://current.geneontology.org/ontology/subsets/gocheck_do_not_annotate.json')
+            self.add_go_do_not_annotate_to_blacklist(
+                'http://current.geneontology.org/ontology/subsets/gocheck_do_not_manually_annotate.json')
 
     def add_go_do_not_annotate_to_blacklist(self, slim_url):
         response = urllib.request.urlopen(slim_url)

diff --git a/genedescriptions/data_manager.py b/genedescriptions/data_manager.py
@@ -10,6 +10,8 @@
 from collections import defaultdict
 from typing import List, Iterable, Dict
 from ontobio import AssociationSetFactory
+from ontobio.io.assocparser import AssocParserConfig
+from ontobio.io.gafparser import GafParser
 from ontobio.ontol_factory import OntologyFactory
 from ontobio.ontol import Ontology
 from ontobio.assocmodel import AssociationSet
@@ -312,9 +314,10 @@ def load_associations_from_file(self, associations_type: DataType, associations_
             associations_cache_path (str): path to cache file for the associations
             config (GenedescConfigParser): configuration object where to read properties
         """
-        assocs = AssociationSetFactory().create_from_file(file=self._get_cached_file(
-            cache_path=associations_cache_path, file_source_url=associations_url),
-            ontology=self.get_ontology(associations_type), skim=False)
+        assoc_config = AssocParserConfig(remove_double_prefixes=True, paint=True)
+        assocs = AssociationSetFactory().create_from_assocs(assocs=GafParser(config=assoc_config).parse(
+            file=self._get_cached_file(cache_path=associations_cache_path, file_source_url=associations_url),
+            skipheader=True), ontology=self.get_ontology(associations_type))
         self.set_associations(associations_type=associations_type, associations=assocs, config=config)
 
     def get_annotations_for_gene(self, gene_id: str, annot_type: DataType = DataType.GO,

diff --git a/wormbase/config_wb.yml b/wormbase/config_wb.yml
@@ -7,7 +7,7 @@ generic:
 
 # options for WormBase gene description generation - used when data_fetcher is set to 'wb_data_fetcher'
 wb_options:
-  release: "WS279"
+  release: "WS280"
   raw_files_source: "ftp://ftp.ebi.ac.uk/pub/databases/wormbase/releases"
   agr_human_go_associations: "http://download.alliancegenome.org/3.2.0/GAF/HUMAN/GAF_HUMAN_1.gaf"
   agr_go_ontology: "http://download.alliancegenome.org/3.2.0/ONTOLOGY/GO/ONTOLOGY_GO_2.obo"
@@ -114,6 +114,23 @@ go_sentences_options:
     - "GO:0040014"
     - "GO:0040015"
     - "GO:0040018"
+    - "GO:0048522"
+    - "GO:0048523"
+    - "GO:0050794"
+    - "GO:0050789"
+    - "GO:0048519"
+    - "GO:0048518"
+    - "GO:0044057"
+    - "GO:0042221"
+    - "GO:0050795"
+    - "GO:0048856"
+    - "GO:0044237"
+    - "GO:0031323"
+    - "GO:0065009"
+    - "GO:0044092"
+    - "GO:0044093"
+    - "GO:0065008"
+
   remap_terms:
     "GO:0018996": "GO:0042303"
     "GO:0007591": "GO:0042303"
@@ -511,9 +528,9 @@ go_sentences_options:
   trimming_algorithm: ic
   max_num_terms: 3
   trim_min_distance_from_root:
-    F: 3
-    P: 5
-    C: 5
+    F: 2
+    P: 2
+    C: 2
   add_multiple_if_covers_more_children: false
   remove_overlapped_terms: true
   slim_url: http://current.geneontology.org/ontology/subsets/goslim_generic.obo

diff --git a/wormbase/wb_data_manager.py b/wormbase/wb_data_manager.py
@@ -69,7 +69,7 @@ def __init__(self, config: GenedescConfigParser, species: str, go_relations: Lis
                                                        "disease_associations.by_orthology." + release_version +
                                                        ".tsv.txt")
         self.do_associations_url = raw_files_source + '/' + release_version + \
-                                   '/ONTOLOGY/disease_associations.by_orthology.' + release_version + '.tsv.txt'
+                                   '/ONTOLOGY/disease_association.by_orthology.' + release_version + '.tsv.txt'
         self.do_associations_new_cache_path = os.path.join(cache_location, "wormbase", release_version, 'ONTOLOGY',
                                                            'disease_association.' + release_version + '.daf.txt')
         self.do_associations_new_url = raw_files_source + '/' + release_version + '/ONTOLOGY/disease_association.' + \

diff --git a/wormbase/wormbase_pipeline.py b/wormbase/wormbase_pipeline.py
@@ -285,7 +285,7 @@ def main():
         if "json" in args.output_formats:
             logger.info("Writing descriptions to json")
             desc_writer.write_json(os.path.join(conf_parser.get_out_dir(), date_prefix + "_" + organism + ".json"),
-                                   pretty=True, include_single_gene_stats=True, data_manager=dm)
+                                   include_single_gene_stats=True, data_manager=dm)
         if "txt" in args.output_formats:
             logger.info("Writing descriptions to txt")
             desc_writer.write_plain_text(os.path.join(conf_parser.get_out_dir(), date_prefix + "_" + organism + ".txt"))