Merge pull request #44 from biolink/add_resources_to_automation

fix gen-python, remove inlining, and add test for schema validation

.github/workflows/pr-verify-pull-request.yaml

@@ -39,6 +39,12 @@ jobs:
         run: |
           make test_pr
 
+      - name: Validate YAML file
+        run: yamllint -c .yamllint-config src/information_resource_registry/schema/information_resource_registry.yaml
 
-
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v1
+        with:
+          ignore_words_list: amination,ehr,mor,nin,brite,mirgate,BRITE
+          skip: SEMMEDDB*,semmed*,.idea,.venv,.git,*.pdf,*.svg,context.*
 

.github/workflows/push-main-regenerate-artifacts.yaml

@@ -7,7 +7,7 @@ on:
     branches:
       - main
   schedule:
-    - cron: '0 5 * * 1'  # at 05:00 UTC every Monday
+    - cron: '0 7 * * 1'  # at 07:00 UTC every Monday
   workflow_dispatch:
     types: trigger-build-artifacts
 
@@ -40,8 +40,8 @@ jobs:
         run: |
           poetry install
           make gen-project
-          make sankey
           make test_pr
+          make sankey
           make gendoc
           if [ $? -eq 0 ]; then
             git config --local user.email "[email protected]"

.github/workflows/weekly-url-check.yaml

@@ -26,19 +26,8 @@ jobs:
           pip install poetry
           poetry install 
 
-      - name: Run URL validation and regenerate sankey diagram
+      - name: Run URL validation
         run: |
-          make sankey
-          make test
-          if [ $? -eq 0 ]; then
-            git config --local user.email "[email protected]"
-            git config --local user.name "GitHub Action"
-            git add project/*
-            git add src/*
-            git add infores_catalog.yaml
-            git commit -m "Regenerate data_flow diagram and validate URLs in infores_catalog.yaml"
-            git push
-          else
-            echo "'make' validation and sankey generation failed to finish successfully"
-          fi
+          make check_urls
+      
 

Makefile

@@ -43,13 +43,13 @@ test_pr:
 	$(RUN) yamllint -c .yamllint-config src/information_resource_registry/schema/*.yaml
 	$(RUN) yamllint -c .yamllint-config infores_catalog.yaml
 
-test:
+test: check_urls
 	$(RUN) linkml-validate infores_catalog.yaml -s src/information_resource_registry/schema/information_resource_registry.yaml
 	$(RUN) pytest
 	$(RUN) codespell
 	$(RUN) yamllint -c .yamllint-config src/information_resource_registry/schema/*.yaml
 	$(RUN) yamllint -c .yamllint-config infores_catalog.yaml
-	$(RUN) python src/information_resource_registry/validation/verify_infores.py
+
 
 clean:
 	rm -rf $(DEST)

infores_catalog.yaml

@@ -206,6 +206,8 @@ information_resources:
       are ignored.
     knowledge_level: knowledge_assertion
     agent_type: not_provided
+    xref:
+      - https://github.com/NCATSTranslator/Translator-All/wiki/Automat
   - id: infores:automat-chembio
     status: deprecated
     name: Automat Chembio
@@ -1678,7 +1680,7 @@ information_resources:
     status: released
     name: Drugs to target pAthways by the Tissue Expression
     xref:
-      - https://www.tatonettilab.org/date/
+      - https://tatonettilab-resources.s3.amazonaws.com/syspharm/DATE.zip
     synonym:
       - DATE
     knowledge_level: knowledge_assertion
@@ -2258,7 +2260,7 @@ information_resources:
     status: deprecated
     name: GOTE (Gpcrs to dOwnstream cellular pathways byTissue Expression)
     xref:
-      - http://tatonettilab.org/resources/GOTE/source_code/
+      - https://tatonettilab-resources.s3.amazonaws.com/syspharm/GOTE.zip
     synonym:
       - GOTE
     knowledge_level: knowledge_assertion
@@ -3754,7 +3756,7 @@ information_resources:
     status: released
     name: SABIO-RK Biochemical Reaction Kinetics Database
     xref:
-      - http://sabiork.h-its.org/
+      - https://www.h-its.org/projects/sabio-rk-biochemical-reaction-kinetics-database/
     knowledge_level: knowledge_assertion
     agent_type: not_provided
   - id: infores:scibite
@@ -4325,7 +4327,7 @@ information_resources:
     status: released
     name: Community Structure-Activity Resource
     xref:
-      - http://www.csardock.org/
+      - https://github.com/NCATSTranslator/Translator-All/wiki/Community-Structure-Activity-Resource
     synonym:
       - CSAR
     knowledge_level: knowledge_assertion
@@ -4729,20 +4731,26 @@ information_resources:
       - infores:aragorn
       - infores:arax
       - infores:molepro
+    xref:
+      - https://github.com/broadinstitute/GeLiNEA
   - id: infores:automat-binding-db
     knowledge_level: not_provided
     agent_type: not_provided
     status: released
     consumed_by:
       - infores:aragorn
       - infores:arax
+    xref:
+      - https://github.com/NCATSTranslator/Translator-All/wiki/Automat
   - id: infores:automat-reactome
     knowledge_level: not_provided
     agent_type: not_provided
     status: released
     consumed_by:
       - infores:aragorn
       - infores:arax
+    xref:
+      - https://github.com/NCATSTranslator/Translator-All/wiki/Automat
   - id: infores:automat-robokop
     knowledge_level: not_provided
     agent_type: not_provided
@@ -4751,7 +4759,11 @@ information_resources:
       - infores:aragorn
       - infores:arax
       - infores:service-provider-trapi
+    xref:
+      - https://github.com/NCATSTranslator/Translator-All/wiki/Automat
   - id: infores:ars
+    xref:
+      - https://github.com/NCATSTranslator/Translator-All/wiki/Autonomous-Relay-System-(ARS)
     knowledge_level: not_provided
     agent_type: not_provided
     status: released
@@ -4767,6 +4779,8 @@ information_resources:
     status: released
     consumed_by:
       - infores:rtx-kg2
+    xref:
+      - https://github.com/NCATSTranslator/Translator-All/wiki/Automat
   - id: infores:annotator
     status: released
     name: Annotator Service
@@ -4781,9 +4795,13 @@ information_resources:
     knowledge_level: not_provided
     agent_type: not_provided
     status: released
+    xref:
+      - https://github.com/NCATSTranslator/Translator-All/wiki/Automat
   - id: infores:omop-ohdsi
     consumed_by:
       - infores:cohd
     knowledge_level: not_provided
     agent_type: not_provided
     status: released
+    xref:
+      - https://github.com/NCATSTranslator/Translator-All/wiki/Automat

pyproject.toml

@@ -24,6 +24,7 @@ generate_sankey = "information_resource_registry.translator_dataflow.generate_sa
 molepro_consume = "information_resource_registry.translator_dataflow.molepro_consume:main"
 rtx_kg2 = "information_resource_registry.translator_dataflow.rtx_kg2:main"
 unsecret = "information_resource_registry.translator_dataflow.unsecret:main"
+check_urls = "information_resource_registry.validation.check_urls:main"
 
 [tool.poetry-dynamic-versioning]
 enable = true
@@ -42,6 +43,8 @@ kaleido = "0.2.1"
 pandas = "^2.2.3"
 plotly = "^5.24.1"
 yamllint = "^1.35.1"
+linkml = "^1.8.5"
+tqdm = "^4.66.6"
 
 [tool.poetry.dev-dependencies]
 linkml = ">=1.6.3"