Merge pull request #559 from monarch-initiative/update-prefixes

Rename GOA to GO

docs/Sources/goa.md → docs/Sources/go.md

@@ -1,4 +1,4 @@
-# Gene Ontology Annotation (GOA) Database
+# Gene Ontology (GO) Annotation Database
 
 The Gene Ontology Annotation Database compiles high-quality [Gene Ontology (GO)](http://www.geneontology.org/) annotations to proteins in the [UniProt Knowledgebase (UniProtKB)](https://www.uniprot.org/), RNA molecules from [RNACentral](http://rnacentral.org/) and protein complexes from the [Complex Portal](https://www.ebi.ac.uk/complexportal/home).
 
@@ -44,7 +44,7 @@ __**Associations**__
     * negated
     * has_evidence
     * aggregating_knowledge_source (["infores:monarchinitiative"])
-    * primary_knowledge_source (infores:goa)
+    * primary_knowledge_source
 
 OR
 
@@ -56,7 +56,7 @@ OR
     * negated
     * has_evidence
     * aggregating_knowledge_source (["infores:monarchinitiative"])
-    * primary_knowledge_source (infores:goa)
+    * primary_knowledge_source
 
 * **biolink:MacromolecularMachineToBiologicalProcessAssociation**:
     * id (random uuid)
@@ -66,7 +66,7 @@ OR
     * negated
     * has_evidence
     * aggregating_knowledge_source (["infores:monarchinitiative"])
-    * primary_knowledge_source (infores:goa)
+    * primary_knowledge_source
 
 * **biolink:MacromolecularMachineToCellularComponentAssociation**:
     * id (random uuid)
@@ -76,7 +76,7 @@ OR
     * negated
     * has_evidence
     * aggregating_knowledge_source (["infores:monarchinitiative"])
-    * primary_knowledge_source (infores:goa)
+    * primary_knowledge_source
 
 __**Possible Additional Gene to Gene Ontology Term Association?**__
 
@@ -88,7 +88,7 @@ __**Possible Additional Gene to Gene Ontology Term Association?**__
     * negated
     * has_evidence
     * aggregating_knowledge_source (["infores:monarchinitiative"])
-    * primary_knowledge_source (infores:goa)
+    * primary_knowledge_source
 
 ## Citation
 

mkdocs.yaml

@@ -23,7 +23,7 @@ nav:
     - CTD: 'Sources/ctd.md'
     # - Dictybase: 'Sources/dictybase.md'
     # - Flybase: 'Sources/flybase.md'
-    - GOA: 'Sources/goa.md'
+    - GO: 'Sources/go.md'
     - HGNC: 'Sources/hgnc.md'
     - HPOA: 'Sources/hpoa.md'
     # - MGI: 'Sources/mgi.md'

src/monarch_ingest/download.yaml

@@ -194,77 +194,77 @@
   local_name: data/flybase/entity_publication_fb.tsv.gz
   tag: flybase_publication_to_gene
 
-### GOA
+### GO
 
 # Homo sapiens (human)
 - url: http://current.geneontology.org/annotations/goa_human.gaf.gz
-  local_name: data/goa/9606.go_annotations.gaf.gz
-  tag: goa_go_annotation
+  local_name: data/go/9606.go_annotations.gaf.gz
+  tag: go_annotation
 
 # Mus musculus (house mouse)
 - url: http://current.geneontology.org/annotations/mgi.gaf.gz
-  local_name: data/goa/10090.go_annotations.gaf.gz
-  tag: goa_go_annotation
+  local_name: data/go/10090.go_annotations.gaf.gz
+  tag: go_annotation
 
 # Rattus norvegicus (Norway rat)
 - url: http://current.geneontology.org/annotations/rgd.gaf.gz
-  local_name: data/goa/10116.go_annotations.gaf.gz
-  tag: goa_go_annotation
+  local_name: data/go/10116.go_annotations.gaf.gz
+  tag: go_annotation
 
 # Canis lupus familiaris (dog)
 - url: http://current.geneontology.org/annotations/goa_dog.gaf.gz
-  local_name: data/goa/9615.go_annotations.gaf.gz
-  tag: goa_go_annotation
+  local_name: data/go/9615.go_annotations.gaf.gz
+  tag: go_annotation
 
 # Bos taurus (cow)
 - url: http://current.geneontology.org/annotations/goa_cow.gaf.gz
-  local_name: data/goa/9913.go_annotations.gaf.gz
-  tag: goa_go_annotation
+  local_name: data/go/9913.go_annotations.gaf.gz
+  tag: go_annotation
 
 # Sus scrofa (pig)
 - url: http://current.geneontology.org/annotations/goa_pig.gaf.gz
-  local_name: data/goa/9823.go_annotations.gaf.gz
-  tag: goa_go_annotation
+  local_name: data/go/9823.go_annotations.gaf.gz
+  tag: go_annotation
 
 # Gallus gallus (chicken)
 - url: http://current.geneontology.org/annotations/goa_chicken.gaf.gz
-  local_name: data/goa/9031.go_annotations.gaf.gz
-  tag: goa_go_annotation
+  local_name: data/go/9031.go_annotations.gaf.gz
+  tag: go_annotation
 
 # Danio rerio (Zebrafish)
 - url: http://current.geneontology.org/annotations/zfin.gaf.gz
-  local_name: data/goa/7955.go_annotations.gaf.gz
-  tag: goa_go_annotation
+  local_name: data/go/7955.go_annotations.gaf.gz
+  tag: go_annotation
 
 # Drosophila melanogaster (fruit fly)
 - url: http://current.geneontology.org/annotations/fb.gaf.gz
-  local_name: data/goa/7227.go_annotations.gaf.gz
-  tag: goa_go_annotation
+  local_name: data/go/7227.go_annotations.gaf.gz
+  tag: go_annotation
 
 # Caenorhabditis elegans (nematodes)
 - url: http://current.geneontology.org/annotations/wb.gaf.gz
-  local_name: data/goa/6239.go_annotations.gaf.gz
-  tag: goa_go_annotation
+  local_name: data/go/6239.go_annotations.gaf.gz
+  tag: go_annotation
 
 # Dictyostelium discoideum
 - url: http://current.geneontology.org/annotations/dictybase.gaf.gz
-  local_name: data/goa/44689.go_annotations.gaf.gz
-  tag: goa_go_annotation
+  local_name: data/go/44689.go_annotations.gaf.gz
+  tag: go_annotation
 
 # Various species in the Aspergillus genus
 - url: http://current.geneontology.org/annotations/aspgd.gaf.gz
-  local_name: data/goa/5052.go_annotations.gaf.gz
-  tag: goa_go_annotation
+  local_name: data/go/5052.go_annotations.gaf.gz
+  tag: go_annotation
 
 # Saccharomyces cerevisiae (baker's yeast)
 - url: http://current.geneontology.org/annotations/sgd.gaf.gz
-  local_name: data/goa/4932.go_annotations.gaf.gz
-  tag: goa_go_annotation
+  local_name: data/go/4932.go_annotations.gaf.gz
+  tag: go_annotation
 
 # Schizosaccharomyces pombe
 - url: http://current.geneontology.org/annotations/pombase.gaf.gz
-  local_name: data/goa/4896.go_annotations.gaf.gz
-  tag: goa_go_annotation
+  local_name: data/go/4896.go_annotations.gaf.gz
+  tag: go_annotation
 
 # HGNC
 -

src/monarch_ingest/ingests.yaml

@@ -18,8 +18,8 @@ dictybase_gene:
   config: 'ingests/dictybase/gene.yaml'
 dictybase_gene_to_phenotype:
   config: 'ingests/dictybase/gene_to_phenotype.yaml'
-goa_go_annotation:
-  config: 'ingests/goa/go_annotation.yaml'
+go_annotation:
+  config: 'ingests/go/annotation.yaml'
 hgnc_gene:
   config: 'ingests/hgnc/gene.yaml'
 hpoa_disease_to_phenotype:

src/monarch_ingest/ingests/goa/go_annotation.py → src/monarch_ingest/ingests/go/annotation.py

@@ -4,12 +4,11 @@
 Gene to GO term Associations
 (to MolecularActivity, BiologicalProcess and CellularComponent)
 """
-from typing import List
 import uuid
 
 from koza.cli_runner import get_koza_app
 
-from monarch_ingest.ingests.goa.goa_utils import (
+from monarch_ingest.ingests.go.annotation_utils import (
     parse_identifiers,
     get_biolink_classes,
     lookup_predicate,
@@ -18,7 +17,7 @@
 from loguru import logger
 
 
-koza_app = get_koza_app("goa_go_annotation")
+koza_app = get_koza_app("go_annotation")
 
 # for row in koza_app.source: # doesn't play nice with tests
 while (row := koza_app.get_row()) is not None:

src/monarch_ingest/ingests/goa/go_annotation.yaml → src/monarch_ingest/ingests/go/annotation.yaml

@@ -1,4 +1,4 @@
-name: 'goa_go_annotation'
+name: 'go_annotation'
 
 format: 'csv'  # is 'gaf' specifically recognized, or does it need to be specifically recognized?
 delimiter: '\t'
@@ -8,21 +8,21 @@ comment_char: '!'
 files:
   # Need to filter out 5052 - Contains data from multiple species of the
   # genus Aspergillus, taxon:5052, not just Aspergillus nidulans
-  - './data/goa/4932.go_annotations.gaf.gz'
-  - './data/goa/4896.go_annotations.gaf.gz'
-  - './data/goa/5052.go_annotations.gaf.gz'
-  - './data/goa/6239.go_annotations.gaf.gz'
-  - './data/goa/7227.go_annotations.gaf.gz'
-  - './data/goa/7955.go_annotations.gaf.gz'
-  - './data/goa/9031.go_annotations.gaf.gz'
-  - './data/goa/9606.go_annotations.gaf.gz'
-  - './data/goa/9615.go_annotations.gaf.gz'
-  - './data/goa/9823.go_annotations.gaf.gz'
-  - './data/goa/9913.go_annotations.gaf.gz'
-  - './data/goa/10090.go_annotations.gaf.gz'
-  - './data/goa/10116.go_annotations.gaf.gz'
-  - './data/goa/44689.go_annotations.gaf.gz'
-  # - './data/goa/162425.go_annotations.gaf.gz'
+  - './data/go/4932.go_annotations.gaf.gz'
+  - './data/go/4896.go_annotations.gaf.gz'
+  - './data/go/5052.go_annotations.gaf.gz'
+  - './data/go/6239.go_annotations.gaf.gz'
+  - './data/go/7227.go_annotations.gaf.gz'
+  - './data/go/7955.go_annotations.gaf.gz'
+  - './data/go/9031.go_annotations.gaf.gz'
+  - './data/go/9606.go_annotations.gaf.gz'
+  - './data/go/9615.go_annotations.gaf.gz'
+  - './data/go/9823.go_annotations.gaf.gz'
+  - './data/go/9913.go_annotations.gaf.gz'
+  - './data/go/10090.go_annotations.gaf.gz'
+  - './data/go/10116.go_annotations.gaf.gz'
+  - './data/go/44689.go_annotations.gaf.gz'
+  # - './data/go/162425.go_annotations.gaf.gz'
 
 filters:
   - inclusion: 'include'
@@ -48,16 +48,12 @@ filters:
       - 'taxon:227321'
       - 'taxon:559292'
 
-metadata:
-  ingest_title: 'GOA DB'
-  ingest_url: 'http://geneontology.org/'
-  description: 'Gene Ontology Annotations Database'
-  rights: 'http://geneontology.org/docs/go-citation-policy/'
+metadata: !include ./src/monarch_ingest/ingests/go/metadata.yaml
 
 global_table: './src/monarch_ingest/translation_table.yaml'
 
 # Evidence Code to ECO term mappings file
-local_table: './src/monarch_ingest/ingests/goa/gaf-eco-mapping.yaml'
+local_table: './src/monarch_ingest/ingests/go/gaf-eco-mapping.yaml'
 
 # http://geneontology.org/docs/go-annotation-file-gaf-format-2.2/
 columns:

src/monarch_ingest/ingests/goa/goa_utils.py → src/monarch_ingest/ingests/go/annotation_utils.py

@@ -2,7 +2,7 @@
 Some Gene Ontology Annotation ingest utility functions.
 """
 from re import sub, IGNORECASE, compile, Pattern
-from typing import Any, Optional, Tuple, List, Dict
+from typing import Optional, Tuple, List, Dict
 
 from loguru import logger
 

src/monarch_ingest/ingests/goa/metadata.yaml → src/monarch_ingest/ingests/go/metadata.yaml

@@ -1,7 +1,7 @@
-name: 'goa'
+name: 'GO'
 
 dataset_description:
-  ingest_title: 'GOA DB'
+  ingest_title: 'GO'
   ingest_url: 'http://geneontology.org/'
   description: 'Gene Ontology Annotations Database'
   rights: 'http://geneontology.org/docs/go-citation-policy/'

src/monarch_ingest/utils/ingest_utils.py

@@ -1,30 +1,29 @@
-import os, pkgutil
+import os
+import pkgutil
 from pathlib import Path
 import yaml
 
+from koza.io.yaml_loader import UniqueIncludeLoader
+
 
 def get_ingests():
-    return yaml.safe_load(pkgutil.get_data("monarch_ingest", 'ingests.yaml'))
+    return yaml.safe_load(pkgutil.get_data("monarch_ingest", "ingests.yaml"))
 
 
 def get_ingest(source: str):
     ingests = get_ingests
-    return yaml.load(
-        pkgutil.get_data("monarch_ingest", ingests[source]['config']), yaml.FullLoader
-    )
+    return yaml.load(pkgutil.get_data("monarch_ingest", ingests[source]["config"]), UniqueIncludeLoader)
 
 
 def file_exists(file):
-    return (Path(file).is_file() and os.stat(file).st_size > 1000)
+    return Path(file).is_file() and os.stat(file).st_size > 1000
 
 
 def ingest_output_exists(source, output_dir):
     ingests = get_ingests()
 
-    ingest_config = yaml.load(
-        pkgutil.get_data("monarch_ingest", ingests[source]['config']), yaml.FullLoader
-    )
-
+    ingest_config = yaml.load(pkgutil.get_data("monarch_ingest", ingests[source]["config"]), UniqueIncludeLoader)
+
     has_node_properties = "node_properties" in ingest_config
     has_edge_properties = "edge_properties" in ingest_config
 
@@ -37,4 +36,3 @@ def ingest_output_exists(source, output_dir):
         return False
 
     return True
-

tests/unit/goa/test_go_annotation.py → tests/unit/go/test_go_annotation.py

@@ -8,7 +8,7 @@
 from biolink.pydanticmodel_v2 import Association
 from loguru import logger
 
-from monarch_ingest.ingests.goa.goa_utils import parse_identifiers
+from monarch_ingest.ingests.go.annotation_utils import parse_identifiers
 
 
 @pytest.mark.parametrize(
@@ -50,23 +50,23 @@ def source_name():
     """
     :return: string source name of GO Annotations ingest
     """
-    return "goa_go_annotation"
+    return "go_annotation"
 
 
 @pytest.fixture
 def script():
     """
     :return: string path to GO Annotations ingest script
     """
-    return "./src/monarch_ingest/ingests/goa/go_annotation.py"
+    return "./src/monarch_ingest/ingests/go/annotation.py"
 
 
 @pytest.fixture(scope="package")
 def local_table():
     """
     :return: string path to Evidence Code to ECO term mappings file
     """
-    return "src/monarch_ingest/ingests/goa/gaf-eco-mapping.yaml"
+    return "src/monarch_ingest/ingests/go/gaf-eco-mapping.yaml"
 
 
 @pytest.fixture
@@ -301,7 +301,7 @@ def test_rows():
 
 
 @pytest.fixture
-def basic_goa(mock_koza, source_name, test_rows, script, global_table, local_table):
+def basic_go(mock_koza, source_name, test_rows, script, global_table, local_table):
     """
     Mock Koza run for GO annotation ingest.
 
@@ -449,12 +449,12 @@ def basic_goa(mock_koza, source_name, test_rows, script, global_table, local_tab
 }
 
 
-def test_association(basic_goa):
-    if not len(basic_goa):
+def test_association(basic_go):
+    if not len(basic_go):
         logger.warning("test_association() null test?")
         return
 
-    association = basic_goa[2]
+    association = basic_go[2]
     assert association
     assert association.subject in result_expected.keys()