Initial scaffolding and example

.github/workflows/modal.yml

@@ -0,0 +1,33 @@
+name: Modal Deploy
+
+on:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+jobs:
+  modal_deply:
+    name: Deploy
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.12
+          cache: pip
+
+      - name: Install Modal
+        run: pip install -r dev-requirements.txt -r modal/requirements.txt
+
+      - name: Deploy job (wildcard for all files)
+        run: |
+          for file in $(find tools -type f -name 'modal.py'); do
+            modal deploy $file
+          done
+        env: # SEE: https://modal.com/docs/guide/environment_variables#runtime-environment-variables
+          MODAL_DEPLOY_TOKEN: ${{ secrets.MODAL_DEPLOY_TOKEN }}
+          MODAL_TOKEN_ID: ${{ secrets.MODAL_TOKEN_ID }}
+          MODAL_TOKEN_SECRET: ${{ secrets.MODAL_TOKEN_SECRET }}
+          MODAL_ENVIRONMENT: chemistry

.pre-commit-config.yaml

@@ -0,0 +1,91 @@
+default_language_version:
+  python: python3
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: check-added-large-files
+      - id: check-byte-order-marker
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-shebang-scripts-are-executable
+      - id: check-symlinks
+      - id: check-toml
+      - id: check-yaml
+        exclude: "kubernetes.yaml$" # This line excludes kubernetes.yaml from being checked as it is WIP
+      - id: debug-statements
+      - id: detect-private-key
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+        exclude: .gitignore
+      - id: trailing-whitespace
+        exclude: .gitignore
+  - repo: https://github.com/psf/black-pre-commit-mirror
+    rev: 24.4.2
+    hooks:
+      - id: black-jupyter
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.5.1
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+  - repo: https://github.com/rbubley/mirrors-prettier
+    rev: v3.3.2
+    hooks:
+      - id: prettier
+  - repo: https://github.com/google/yamlfmt
+    rev: v0.13.0
+    hooks:
+      - id: yamlfmt
+  - repo: https://github.com/Yelp/detect-secrets
+    rev: v1.5.0
+    hooks:
+      - id: detect-secrets
+  - repo: https://github.com/pappasam/toml-sort
+    rev: v0.23.1
+    hooks:
+      - id: toml-sort-fix
+        exclude: poetry.lock
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.3.0
+    hooks:
+      - id: codespell
+        additional_dependencies: [".[toml]"]
+  - repo: https://github.com/sqlfluff/sqlfluff
+    rev: 3.1.0
+    hooks:
+      - id: sqlfluff-fix
+  - repo: https://github.com/hadolint/hadolint
+    rev: v2.13.0-beta
+    hooks:
+      - id: hadolint-docker
+  - repo: https://github.com/jsh9/markdown-toc-creator
+    rev: 0.0.6
+    hooks:
+      - id: markdown-toc-creator
+  - repo: https://github.com/jumanjihouse/pre-commit-hooks
+    rev: 3.0.0
+    hooks:
+      - id: check-mailmap
+  - repo: https://github.com/python-poetry/poetry
+    rev: 1.8.0
+    hooks:
+      - id: poetry-check
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.10.1
+    hooks:
+      - id: mypy
+        additional_dependencies:
+          - types-requests
+          - types-fastapi
+  - repo: https://github.com/srstevenson/nb-clean
+    rev: 3.3.0
+    hooks:
+      - id: nb-clean
+        args: [--preserve-cell-outputs, --remove-empty-cells]
+  - repo: https://github.com/abravalheri/validate-pyproject
+    rev: v0.18
+    hooks:
+      - id: validate-pyproject
+        additional_dependencies:
+          - "validate-pyproject-schema-store[all]>=2024.06.24" # Pin for Ruff's FURB154

tools/cheminformatics/modal.py

@@ -0,0 +1,26 @@
+from modal import App, web_endpoint
+from modal import Image
+
+rdkit_image = (
+    Image.debian_slim(python_version="3.12")
+    .pip_install("rdkit")
+)
+with rdkit_image.imports():
+    from rdkit import Chem, DataStructs
+    from rdkit.Chem import AllChem
+
+
+app = App()
+
+@app.function(image=rdkit_image)
+@web_endpoint()
+def tanimoto(s1: str, s2: str) -> float:
+    """Calculate the Tanimoto similarity of two SMILES strings."""
+    try:
+        mol1 = Chem.MolFromSmiles(s1)
+        mol2 = Chem.MolFromSmiles(s2)
+        fp1 = AllChem.GetMorganFingerprintAsBitVect(mol1, 2, nBits=2048)
+        fp2 = AllChem.GetMorganFingerprintAsBitVect(mol2, 2, nBits=2048)
+        return DataStructs.TanimotoSimilarity(fp1, fp2)
+    except (TypeError, ValueError, AttributeError):
+        return "Error: Not a valid SMILES string"