feat: initial training implementation (#1)

.gitattributes

@@ -0,0 +1 @@
+tests/data/train_smoke/* filter=lfs diff=lfs merge=lfs -text

.github/workflows/docker-build.yml

@@ -25,9 +25,9 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
-          fetch-depth: "0"
+          lfs: 'true'
 
       - name: Log in to the Container registry
         uses: docker/login-action@v2

.github/workflows/main.yml

@@ -21,7 +21,9 @@ jobs:
   linting:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v1
+      - uses: actions/checkout@v4
+        with:
+          lfs: 'true'
 
       - name: Install Python
         uses: actions/setup-python@v2
@@ -47,7 +49,9 @@ jobs:
   sphinx-docs:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v1
+      - uses: actions/checkout@v4
+        with:
+          lfs: 'true'
 
       - name: Install Python
         uses: actions/setup-python@v2
@@ -76,9 +80,9 @@ jobs:
           - '3.11'
     needs: linting
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with:
-          fetch-depth: 0 # we need tags for versioneer to work
+          lfs: 'true'
 
       - name: Install Python
         uses: actions/setup-python@v2

.github/workflows/release-please.yml

@@ -17,10 +17,10 @@ jobs:
           package-name: cada-prio
           token: ${{ secrets.BOT_TOKEN }}
 
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         if: ${{ steps.release.outputs.release_created }}
         with:
-          fetch-depth: 0
+          lfs: 'true'
 
       - name: Set up Python
         if: ${{ steps.release.outputs.release_created }}

.gitignore

@@ -1,3 +1,5 @@
+/model-out
+
 *~
 .*.sw?
 

CONTRIBUTING.rst

@@ -16,7 +16,7 @@ Types of Contributions
 Report Bugs
 ===========
 
-Report bugs at https://github.com/bihealth/cada-ng/issues.
+Report bugs at https://github.com/bihealth/cada-prio/issues.
 
 If you are reporting a bug, please include:
 
@@ -39,12 +39,12 @@ Anything tagged with "enhancement" and "help wanted" is open to whoever wants to
 Write Documentation
 ===================
 
-cada-ng could always use more documentation, whether as part of the official cada-ng docs, in docstrings, or even on the web in blog posts, articles, and such.
+cada-prio could always use more documentation, whether as part of the official cada-prio docs, in docstrings, or even on the web in blog posts, articles, and such.
 
 Submit Feedback
 ===============
 
-The best way to send feedback is to file an issue at https://github.com/bihealth/cada-ng/issues.
+The best way to send feedback is to file an issue at https://github.com/bihealth/cada-prio/issues.
 
 If you are proposing a feature:
 
@@ -56,18 +56,18 @@ If you are proposing a feature:
 Get Started!
 ------------
 
-Ready to contribute? Here's how to set up `cada-ng` for local development.
+Ready to contribute? Here's how to set up `cada-prio` for local development.
 
-1. Fork the `cada-ng` repo on GitHub.
+1. Fork the `cada-prio` repo on GitHub.
 2. Clone your fork locally::
 
-    $ git clone git@github.com:bihealth/cada-ng.git
+    $ git clone git@github.com:bihealth/cada-prio.git
 
 3. Install your local copy into a virtualenv.
    Assuming you have virtualenvwrapper installed, this is how you set up your fork for local development::
 
-    $ mkvirtualenv cada-ng
-    $ cd cada-ng/
+    $ mkvirtualenv cada-prio
+    $ cd cada-prio/
     $ python setup.py develop
 
 4. Create a branch for local development::
@@ -79,7 +79,7 @@ Ready to contribute? Here's how to set up `cada-ng` for local development.
 5. When you're done making changes, check that your changes pass flake8 and the
    tests, including testing other Python versions with tox::
 
-    $ flake8 cada-ng tests
+    $ flake8 cada-prio tests
     $ python setup.py test or pytest
     $ tox
 

README.md

@@ -1,16 +1,16 @@
-[![CI](https://github.com/bihealth/cada-ng/actions/workflows/main.yml/badge.svg?branch=main)](https://github.com/bihealth/cada-ng/actions/workflows/main.yml)
-[![codecov](https://codecov.io/gh/bihealth/cada-ng/graph/badge.svg?token=HIBwaG4eYM)](https://codecov.io/gh/bihealth/cada-ng)
-[![Documentation Status](https://readthedocs.org/projects/cada-ng/badge/?version=latest)](https://cada-ng.readthedocs.io/en/latest/?badge=latest)
-[![Pypi](https://img.shields.io/pypi/pyversions/cada-ng.svg)](https://pypi.org/project/cada-ng)
+[![CI](https://github.com/bihealth/cada-prio/actions/workflows/main.yml/badge.svg?branch=main)](https://github.com/bihealth/cada-prio/actions/workflows/main.yml)
+[![codecov](https://codecov.io/gh/bihealth/cada-prio/graph/badge.svg?token=HIBwaG4eYM)](https://codecov.io/gh/bihealth/cada-prio)
+[![Documentation Status](https://readthedocs.org/projects/cada-prio/badge/?version=latest)](https://cada-prio.readthedocs.io/en/latest/?badge=latest)
+[![Pypi](https://img.shields.io/pypi/pyversions/cada-prio.svg)](https://pypi.org/project/cada-prio)
 
 # CADA: The Next Generation
 
 This is a re-implementation of the [CADA](https://github.com/Chengyao-Peng/CADA) method for phenotype-similarity prioritization.
 
 - Free software: MIT license
-- Documentation: https://cada-ng.readthedocs.io/en/latest/
-- Discussion Forum: https://github.com/bihealth/cada-ng/discussions
-- Bug Reports: https://github.com/bihealth/cada-ng/issues
+- Documentation: https://cada-prio.readthedocs.io/en/latest/
+- Discussion Forum: https://github.com/bihealth/cada-prio/discussions
+- Bug Reports: https://github.com/bihealth/cada-prio/issues
 
 
 ## Managing GitHub Project with Terraform
@@ -22,7 +22,7 @@ This is a re-implementation of the [CADA](https://github.com/Chengyao-Peng/CADA)
 # cd utils/terraform
 
 # terraform init
-# terraform import github_repository.cada-ng cada-ng
+# terraform import github_repository.cada-prio cada-prio
 # terraform validate
 # terraform fmt
 # terraform plan

cada_prio/cli.py

@@ -2,7 +2,7 @@
 
 import click
 
-from cada_prio import _version
+from cada_prio import _version, train_model
 
 
 @click.group()
@@ -13,3 +13,31 @@ def cli(ctx: click.Context, verbose: bool):
     """Main entry point for CLI via click."""
     ctx.ensure_object(dict)
     ctx.obj["verbose"] = verbose
+
+
+@cli.command("train-model")
+@click.argument("path_out", type=str)
+@click.option("--path-hgnc-json", type=str, help="path to HGNC JSON", required=True)
+@click.option(
+    "--path-gene-hpo-links", type=str, help="path to gene-HPO term links JSONL", required=True
+)
+@click.option(
+    "--path-hpo-genes-to-phenotype",
+    type=str,
+    help="path to genes_to_phenotype.txt file",
+    required=True,
+)
+@click.option("--path-hpo-obo", type=str, help="path HPO OBO file", required=True)
+@click.pass_context
+def cli_train_model(
+    ctx: click.Context,
+    path_out: str,
+    path_hgnc_json: str,
+    path_gene_hpo_links: str,
+    path_hpo_genes_to_phenotype: str,
+    path_hpo_obo: str,
+):
+    ctx.ensure_object(dict)
+    train_model.run(
+        path_out, path_hgnc_json, path_gene_hpo_links, path_hpo_genes_to_phenotype, path_hpo_obo
+    )