Upgrade to koza 2.x and restore kgx RDF output

.copier-answers.yml

@@ -0,0 +1,11 @@
+_commit: adada77
+_src_path: gh:monarch-initiative/koza-ingest-template
+copyright_year: '2026'
+email: kevin@tislab.org
+full_name: Kevin Schaper
+github_handle: kevinschaper
+github_org: monarch-initiative
+license: BSD-3-Clause
+project_description: Ingest of genes from NCBI
+project_name: ncbi-gene
+project_slug: ncbi_gene

.github/workflows/release.yaml

@@ -0,0 +1,73 @@
+name: Release
+
+on:
+  schedule:
+    # Run monthly on the 3rd at midnight UTC
+    - cron: '0 0 3 * *'
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Release tag (leave empty for auto-generated date tag)'
+        required: false
+        type: string
+
+env:
+  NCBI_API_KEY: ${{ secrets.NCBI_API_KEY }}
+  NCBI_MAIL: ${{ secrets.NCBI_MAIL }}
+  TRANSFORMS: "transform"
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
+      - name: Set up Python
+        run: uv python install 3.11
+
+      - name: Install just
+        uses: extractions/setup-just@v2
+
+      - name: Run pipeline
+        run: just run
+
+      - name: Postprocess
+        run: just postprocess
+
+      - name: Generate release tag
+        id: tag
+        run: |
+          if [ -n "${{ inputs.tag }}" ]; then
+            echo "tag=${{ inputs.tag }}" >> $GITHUB_OUTPUT
+          else
+            echo "tag=v$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Create Release
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: ${{ steps.tag.outputs.tag }}
+          name: Release ${{ steps.tag.outputs.tag }}
+          body: |
+            Automated monthly release of NCBI Gene ingest data.
+
+            ## Transforms included
+            - transform (NCBI Gene)
+
+            ## Output
+            - Gene nodes with postprocessed files split by taxon
+          draft: false
+          prerelease: false
+          files: |
+            output/*_nodes.tsv
+            output/*_edges.tsv
+            output/*.nt.gz
+            output/by_taxon/*

.github/workflows/test.yaml

@@ -4,50 +4,32 @@ on:
   push:
     branches: [main]
   pull_request:
-  workflow_dispatch:
+    branches: [main]
 
 env:
   NCBI_API_KEY: ${{ secrets.NCBI_API_KEY }}
   NCBI_MAIL: ${{ secrets.NCBI_MAIL }}
 
 jobs:
-  test-backend:
-    runs-on: ${{ matrix.os }}
-
+  test:
+    runs-on: ubuntu-latest
     strategy:
       matrix:
         python-version: ["3.10", "3.11", "3.12"]
-        os: [ubuntu-latest]
-        #os: [ ubuntu-latest, windows-latest ]
 
     steps:
       - uses: actions/checkout@v4
 
-      - name: Debug Secrets
-        run: |
-            if [ -z "$NCBI_API_KEY" ]; then echo "NCBI_API_KEY is NOT set"; else echo "NCBI_API_KEY is SET"; fi
-            if [ -z "$NCBI_MAIL" ]; then echo "NCBI_MAIL is NOT set"; else echo "NCBI_MAIL is SET"; fi
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      #----------------------------------------------
-      #          install & configure poetry
-      #----------------------------------------------
-      - name: Install Poetry
-        uses: snok/install-poetry@v1
-
-      #----------------------------------------------
-      #    install your root project, if required
-      #----------------------------------------------
-      - name: Install library
-        run: poetry install --no-interaction
-
-      #----------------------------------------------
-      #              run pytest
-      #----------------------------------------------
-      - name: Run tests
-        run: poetry run pytest tests
+        run: uv python install ${{ matrix.python-version }}
+
+      - name: Install just
+        uses: extractions/setup-just@v2
 
+      - name: Run tests
+        run: just test

CLAUDE.md

@@ -0,0 +1,36 @@
+# ncbi-gene
+
+This is a Koza ingest repository for transforming NCBI Gene data into Biolink model format.
+
+## Project Structure
+
+- `download.yaml` - Configuration for downloading NCBI gene_info data
+- `src/` - Transform code and configuration
+  - `transform.py` / `transform.yaml` - Main transform for NCBI genes
+  - `taxon_lookup.py` - Helper module for fetching taxon names via NCBI E-utilities
+- `tests/` - Unit tests for transforms
+- `output/` - Generated nodes and edges (gitignored)
+- `data/` - Downloaded source data (gitignored)
+
+## Key Commands
+
+- `just run` - Full pipeline (download -> transform -> postprocess)
+- `just download` - Download NCBI gene_info data
+- `just transform-all` - Run all transforms
+- `just postprocess` - Split output by taxon
+- `just test` - Run tests
+
+## Postprocessing
+
+This ingest includes a postprocessing step to split the output nodes file by taxon:
+```bash
+uv run koza split output/ncbi_gene_nodes.tsv in_taxon --remove-prefixes --output-dir output/by_taxon
+```
+
+This creates separate files per species in `output/by_taxon/`.
+
+## Environment Variables
+
+The taxon lookup module uses NCBI E-utilities and can be configured with:
+- `NCBI_API_KEY` - NCBI API key for higher rate limits
+- `NCBI_MAIL` - Email for NCBI E-utilities identification