fixed merge conflict

.github/workflows/add_dunder_methods.yaml

@@ -0,0 +1,37 @@
+name: add dunder methods to genome_annotation model
+
+on:
+  push:
+    paths:
+      - 'bkbit/models/genome_annotation.py'
+
+permissions:
+  contents: write
+
+jobs:
+  run-script:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout this repository
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.9
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+
+      
+      - name: Run add_dunderMethods_genomeAnnotation
+        run: python bkbit/model_editors/add_dunderMethods_genomeAnnotation.py
+
+      - name: Commit changes
+        run: |
+          git config --global user.name 'github-actions'
+          git config --global user.email '[email protected]'
+          git add bkbit/models/genome_annotation.py
+          git commit -m 'Update genome_annotation.py with dunder methods'
+          git push

.github/workflows/generate_docs.yaml

@@ -0,0 +1,34 @@
+name: Publish bkbit Documentation
+
+on:
+  push:
+    branches:
+      - main
+      - create_docs_20241003
+
+jobs:
+  publish_bkbit_docs:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v3
+        with:
+          python-version: "3.10"
+      - name: Install dependencies
+        run: |
+          pip install -e .
+          pip install sphinx sphinx_rtd_theme
+          pip install m2r
+      - name: Sphinx build
+        run: |
+          sphinx-apidoc -o docs bkbit --separate
+          sphinx-build docs docs/_build/html
+      - name: Deploy
+        uses: peaceiris/actions-gh-pages@v3
+        with:
+          publish_branch: gh-pages
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: docs/_build/html
+          force_orphan: true

.gitignore

@@ -0,0 +1,2 @@
+__pycache__
+_build

bkbit/cli.py

@@ -4,6 +4,9 @@
 from bkbit.data_translators.library_generation_translator import specimen2jsonld
 from bkbit.data_translators.file_manifest_translator import filemanifest2jsonld
 from bkbit.data_translators.specimen_metadata_translator import list_library_aliquot
+from bkbit.data_translators.genome_annotation_translator import gff2jsonld
+from bkbit.utils.get_ncbi_taxonomy import download_ncbi_taxonomy
+from bkbit.model_editors.linkml_trimmer import linkml_trimmer
 
 @click.group()
 def cli():
@@ -16,6 +19,9 @@ def cli():
 cli.add_command(specimen2jsonld)
 cli.add_command(filemanifest2jsonld)
 cli.add_command(list_library_aliquot)
+cli.add_command(gff2jsonld)
+cli.add_command(download_ncbi_taxonomy)
+cli.add_command(linkml_trimmer)
 
 if __name__ == '__main__':
     cli()

bkbit/data_translators/README.md

@@ -95,4 +95,111 @@ ls .
 DO-XIQQ6047.jsonld
 DO-WFFF3774.jsonld
 DO-RMRL6873.jsonld
+# genome_annotation_translator.py
+
+## Overview
+genome_annotation_translator uses annotated genome data in GFF3 format to generate respective data objects representing genes, genome assemblies, and organisms. All data object are defined in the [Genome Annotation Schema](https://brain-bican.github.io/models/index_genome_annotation/).<br>
+Each jsonld file will contain:
+- GeneAnnotation objects
+- 1 GenomeAnnotation object
+- 1 GenomeAssembly object
+- 1 OrganismTaxon object
+- 1 Checksum object
+
+
+
+## Command Line
+### gen-geneannotation
+```python
+gen-geneannotation [OPTIONS] GFF3_URL 
+```
+
+#### Options
+<span style="color: red;">-a, --assembly_accession</span> <br> 
+&emsp;ID assigned to the genomic assembly used in the GFF3 file. <br>
+&emsp;<b>*Note*</b>: Must be provided when using ENSEMBL GFF3 files
+
+<span style="color: red;">-s, --assembly_strain</span> <br>
+&emsp;Specific strain of the organism associated with the GFF3 file.
+
+<span style="color: red;">-l, --log_level</span> <br>
+&emsp;Logging level. <br>
+&emsp;DEFAULT:<br>
+&emsp;&emsp;'WARNING'<br>
+&emsp;OPTIONS:<br>
+&emsp;&emsp;DEBUG | INFO | WARNING | ERROR | CRITICIAL 
+
+<span style="color: red;">-f, --log_to_file</span> <br>
+&emsp;Log to a file instead of the console. <br>
+&emsp;DEFAULT:<br>
+&emsp;&emsp;False <br>
+
+## Examples
+#### Example 1: NCBI GFF3 File 
+
+```python
+pip install bkbit
+
+gen-geneannotation 'https://ftp.ncbi.nlm.nih.gov/genomes/all/annotation_releases/9823/106/GCF_000003025.6_Sscrofa11.1/GCF_000003025.6_Sscrofa11.1_genomic.gff.gz' > output.jsonld
+```
+
+#### Example 2: ENSEMBL GFF3 File 
+
+```python
+pip install bkbit
+
+# genome_annotation_translator.py
+
+## Overview
+genome_annotation_translator uses annotated genome data in GFF3 format to generate respective data objects representing genes, genome assemblies, and organisms. All data object are defined in the [Genome Annotation Schema](https://brain-bican.github.io/models/index_genome_annotation/).<br>
+Each jsonld file will contain:
+- GeneAnnotation objects
+- 1 GenomeAnnotation object
+- 1 GenomeAssembly object
+- 1 OrganismTaxon object
+- 1 Checksum object
+
+
+
+## Command Line
+### gen-geneannotation
+```python
+gen-geneannotation [OPTIONS] GFF3_URL 
+```
+
+#### Options
+<span style="color: red;">-a, --assembly_accession</span> <br> 
+&emsp;ID assigned to the genomic assembly used in the GFF3 file. <br>
+&emsp;<b>*Note*</b>: Must be provided when using ENSEMBL GFF3 files
+
+<span style="color: red;">-s, --assembly_strain</span> <br>
+&emsp;Specific strain of the organism associated with the GFF3 file.
+
+<span style="color: red;">-l, --log_level</span> <br>
+&emsp;Logging level. <br>
+&emsp;DEFAULT:<br>
+&emsp;&emsp;'WARNING'<br>
+&emsp;OPTIONS:<br>
+&emsp;&emsp;DEBUG | INFO | WARNING | ERROR | CRITICIAL 
+
+<span style="color: red;">-f, --log_to_file</span> <br>
+&emsp;Log to a file instead of the console. <br>
+&emsp;DEFAULT:<br>
+&emsp;&emsp;False <br>
+
+## Examples
+#### Example 1: NCBI GFF3 File 
+
+```python
+pip install bkbit
+
+gen-geneannotation 'https://ftp.ncbi.nlm.nih.gov/genomes/all/annotation_releases/9823/106/GCF_000003025.6_Sscrofa11.1/GCF_000003025.6_Sscrofa11.1_genomic.gff.gz' > output.jsonld
+```
+
+#### Example 2: ENSEMBL GFF3 File 
+
+```python
+pip install bkbit
+
+gen-geneannotation -a 'GCF_003339765.1' 'https://ftp.ensembl.org/pub/release-104/gff3/macaca_mulatta/Macaca_mulatta.Mmul_10.104.gff3.gz' > output.jsonld
 ```