Refactor: single package, typed r_brics, more lint rules

.github/workflows/quality.yml

@@ -10,10 +10,10 @@ jobs:
     - name: Checkout
       uses: actions/checkout@v4
 
-    - name: Set up Python 3.11
+    - name: Set up Python 3.12
       uses: actions/setup-python@v4
       with:
-        python-version: '3.11'
+        python-version: '3.12'
 
     - name: Install uv
       run: |
@@ -45,11 +45,5 @@ jobs:
     - name: Run ruff (formatter)
       run: ruff format --check
 
-    - name: Run isort
-      run: isort --check --profile black .
-
     - name: Run mypy
       run: mypy .
-
-    - name: Run tests
-      run: pytest -v

.github/workflows/tests.yml

@@ -0,0 +1,43 @@
+name: Tests
+
+on: [push, pull_request]
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+
+    - name: Set up Python 3.12
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.12'
+
+    - name: Install uv
+      run: |
+        curl -LsSf https://astral.sh/uv/install.sh | sh
+        echo "$HOME/.cargo/bin" >> $GITHUB_PATH
+
+    - name: Cache dependencies
+      uses: actions/cache@v4
+      with:
+        path: |
+          ~/.cache/uv
+          ~/.uv
+          .venv
+        key: ${{ runner.os }}-uv-${{ hashFiles('pyproject.toml') }}
+        restore-keys: |
+          ${{ runner.os }}-uv-
+
+    - name: Create and activate virtual environment
+      run: |
+        uv venv
+        echo "$PWD/.venv/bin" >> $GITHUB_PATH
+
+    - name: Install dependencies
+      run: uv pip install -e ".[dev]"
+
+    - name: Run tests with coverage
+      run: |
+        pytest -v --cov=fragmentretro --cov-report=xml --cov-report=term

.gitignore

@@ -19,6 +19,8 @@ wheels/
 *.egg-info/
 .installed.cfg
 *.egg
+.mypy_cache/
+.ruff_cache/
 
 # Virtual Environment
 .venv/

.pre-commit-config.yaml

@@ -6,23 +6,16 @@ repos:
     hooks:
       - id: ruff
         name: ruff (linter)
-        entry: ruff check
-        language: system
+        entry: ruff check --fix
+        language: python
         types: [python]
 
       - id: ruff-format
         name: ruff (formatter)
         entry: ruff format
-        language: system
+        language: python
         types: [python]
 
-      - id: isort
-        name: isort
-        entry: isort
-        language: system
-        types: [python]
-        args: [--profile=black]
-
       # - id: mypy
       #   name: mypy
       #   entry: mypy

.python-version

@@ -0,0 +1 @@
+3.12.10

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2025 Batista Lab (Yale University)
+Copyright (c) 2025 Yu Shee
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

data/process_buyables.py

@@ -5,21 +5,23 @@
 
 from tqdm import tqdm
 
-from FragmentRetro.utils.filter_compound import precompute_properties
-from FragmentRetro.utils.helpers import canonicalize_smiles
-from FragmentRetro.utils.logging_config import logger
+from fragmentretro.utils.filter_compound import precompute_properties
+from fragmentretro.utils.helpers import canonicalize_smiles
+from fragmentretro.utils.logging_config import logger
 
 DATA_PATH = Path(__file__).parent
 BUYABLES_PATH = DATA_PATH / "buyables"
 PRECOMPUTE_PATH = DATA_PATH / "precompute"
 
 if __name__ == "__main__":
     logger.info("Decompressing buyables data...")
-    with gzip.open(BUYABLES_PATH / "buyables_all.json.gz", "rb") as f_in:
-        with open(BUYABLES_PATH / "buyables_all.json", "wb") as f_out:
-            shutil.copyfileobj(f_in, f_out)
+    with (
+        gzip.open(BUYABLES_PATH / "buyables_all.json.gz", "rb") as f_in,
+        open(BUYABLES_PATH / "buyables_all.json", "wb") as f_out,
+    ):
+        shutil.copyfileobj(f_in, f_out)
     logger.info("Loading buyables data...")
-    with open(BUYABLES_PATH / "buyables_all.json", "r") as f:
+    with open(BUYABLES_PATH / "buyables_all.json") as f:
         buyables = json.load(f)
     buyables_smiles = [buyable["smiles"] for buyable in buyables]
 

data/process_stock.py

@@ -1,20 +1,20 @@
 from pathlib import Path
 
-from FragmentRetro.utils.filter_compound import precompute_properties
+from fragmentretro.utils.filter_compound import precompute_properties
 
 DATA_PATH = Path(__file__).parent
 PAROUTES_PATH = DATA_PATH / "paroutes"
 PRECOMPUTE_PATH = DATA_PATH / "precompute"
 
 
 if __name__ == "__main__":
-    with open(PAROUTES_PATH / "n1-stock.txt", "r") as f:
+    with open(PAROUTES_PATH / "n1-stock.txt") as f:
         n1_stock = [line.strip() for line in f.readlines()]
     PRECOMPUTE_PATH.mkdir(parents=True, exist_ok=True)
     precompute_properties(n1_stock, PRECOMPUTE_PATH / "n1_stock_properties.json")
     # precompute_properties(n1_stock, PRECOMPUTE_PATH / "n1_stock_properties_fp1024.json", fpSize=1024)
 
-    with open(PAROUTES_PATH / "n5-stock.txt", "r") as f:
+    with open(PAROUTES_PATH / "n5-stock.txt") as f:
         n5_stock = [line.strip() for line in f.readlines()]
     PRECOMPUTE_PATH.mkdir(parents=True, exist_ok=True)
     precompute_properties(n5_stock, PRECOMPUTE_PATH / "n5_stock_properties.json")

docs/CNAME

@@ -0,0 +1 @@
+fragment.batistalab.com

docs/FragmentRetro/fragmenter-base.md

@@ -5,7 +5,7 @@
 You will only have to define the abstract methods to find fragmentation bonds and to break these bonds. Other methods like building fragment graph (`networkx` graph), visualization, and how to get SMILES string given a combination of fragments are provided in this base class.
 
 ```python
-from FragmentRetro.fragmenter_base import Fragmenter
+from fragmentretro.fragmenter_base import Fragmenter
 
 # suppose you have a new way to find and break bonds: `FindTestBonds` and `BreakTestBonds`
 
@@ -28,7 +28,7 @@ class TestFragmenter(Fragmenter):
 
 ## Source Code
 
-::: FragmentRetro.fragmenter_base
+::: fragmentretro.fragmenter_base
     handler: python
     options:
       show_root_heading: true

docs/FragmentRetro/fragmenter.md

@@ -5,7 +5,7 @@ Once you have the fragmentation algorithms such as BRICS, you can get derived cl
 ## Example Use
 
 ```python
-from FragmentRetro.fragmenter import BRICSFragmenter
+from fragmentretro.fragmenter import BRICSFragmenter
 
 smiles = "COc1ccc(-n2nccn2)c(C(=O)N2CCC[C@@]2(C)c2nc3c(C)c(Cl)ccc3[nH]2)c1"
 fragmenter = BRICSFragmenter(smiles)
@@ -16,7 +16,7 @@ fragmenter.visualize(figsize=(20, 10), verbose=False, with_indices=True)
 
 ## Source Code
 
-::: FragmentRetro.fragmenter
+::: fragmentretro.fragmenter
     handler: python
     options:
       show_root_heading: true

docs/FragmentRetro/retrosynthesis.md

@@ -5,9 +5,9 @@ The `Retrosynthesis` class identifies all possible retrosynthesis solutions for
 ## Example Use
 
 ```python
-from FragmentRetro.fragmenter import BRICSFragmenter
-from FragmentRetro.retrosynthesis import Retrosynthesis
-from FragmentRetro.solutions import RetrosynthesisSolution
+from fragmentretro.fragmenter import BRICSFragmenter
+from fragmentretro.retrosynthesis import Retrosynthesis
+from fragmentretro.solutions import RetrosynthesisSolution
 
 # Define your building block set (SMILES strings)
 original_BBs = set(['Brc1cc(OC)ccc1-n1nccn1',
@@ -44,7 +44,7 @@ retro_solution.visualize_solutions(retro_solution.solutions, molsPerRow=4)[-1]
 
 ## Source Code
 
-::: FragmentRetro.retrosynthesis
+::: fragmentretro.retrosynthesis
     handler: python
     options:
       show_root_heading: true

docs/FragmentRetro/solutions.md

@@ -5,9 +5,9 @@ The `RetrosynthesisSolution` class is designed to find and visualize all possibl
 ## Example Use
 
 ```python
-from FragmentRetro.retrosynthesis import Retrosynthesis
-from FragmentRetro.fragmenter import BRICSFragmenter
-from FragmentRetro.solutions import RetrosynthesisSolution
+from fragmentretro.retrosynthesis import Retrosynthesis
+from fragmentretro.fragmenter import BRICSFragmenter
+from fragmentretro.solutions import RetrosynthesisSolution
 
 # Example SMILES
 smiles = "COc1ccc(-n2nccn2)c(C(=O)N2CCC[C@@]2(C)c2nc3c(C)c(Cl)ccc3[nH]2)c1"
@@ -32,7 +32,7 @@ for i, img in enumerate(images):
 
 ## Source Code
 
-::: FragmentRetro.solutions
+::: fragmentretro.solutions
     handler: python
     options:
       show_root_heading: true

docs/FragmentRetro/substructure-matcher.md

@@ -5,7 +5,7 @@ Check if a fragment (which can contain dummy or any atoms represented by "*") is
 ## Example Use
 
 ```python
-from FragmentRetro.substructure_matcher import SubstructureMatcher
+from fragmentretro.substructure_matcher import SubstructureMatcher
 
 fragment_smiles = "[4*]CCN[5*]",
 molecule_smiles = "CCCNC"
@@ -16,7 +16,7 @@ print(SubstructureMatcher.is_strict_substructure(fragment_smiles, molecule_smile
 
 ## Source Code
 
-::: FragmentRetro.substructure_matcher
+::: fragmentretro.substructure_matcher
     handler: python
     options:
       show_root_heading: true

docs/FragmentRetro/utils/type-definition.md → docs/FragmentRetro/typing.md

@@ -1,23 +1,25 @@
 # Type Definitions
 
-[type_definitions.py](/src/FragmentRetro/type_definitions.py) is a good place to store your type definitions to make code clean and pass mypy tests.
+`fragmentretro.typing` is a good place to store your type definitions to make code clean and pass mypy tests.
 
 ## Example Usage
 
 ```python
+from fragmentretro.typing import BondType
+
 def _find_fragmentation_bonds(mol: Mol) -> list[BondType]:
     return list(FindBRICSBonds(mol))
 ```
 
-where `BondType` is defined in [type_definitions.py](/src/FragmentRetro/utils/type_definitions.py) as:
+where `BondType` is defined in `fragmentretro.typing` as:
 
 ```python
-BondType: TypeAlias = tuple[tuple[int, int], tuple[str, str]]
+type BondType = tuple[tuple[int, int], tuple[str, str]]
 ```
 
 ## Source Code
 
-::: FragmentRetro.utils.type_definitions
+::: fragmentretro.typing
     handler: python
     options:
       show_root_heading: true

docs/FragmentRetro/utils/filter-compound.md

@@ -8,7 +8,7 @@ The `precompute_properties` function computes properties for a large set of comp
 
 ```python
 from pathlib import Path
-from FragmentRetro.utils.filter_compound import precompute_properties
+from fragmentretro.utils.filter_compound import precompute_properties
 
 DATA_PATH = Path(__file__).parent.parent / "data"
 PAROUTES_PATH = DATA_PATH / "paroutes"
@@ -27,8 +27,8 @@ precompute_properties(n1_stock_subset, MOL_PROPERTIES_PATH, fpSize=2048)
 The `CompoundFilter` class is used to initialize a filter, and the `get_filtered_BBs` method retrieves the screened building blocks. The following example demonstrates filtering using a specific fragment SMILES string.
 
 ```python
-from FragmentRetro.utils.filter_compound import CompoundFilter
-from FragmentRetro.utils.helpers import replace_dummy_atoms_regex
+from fragmentretro.utils.filter_compound import CompoundFilter
+from fragmentretro.utils.helpers import replace_dummy_atoms_regex
 
 fragment_smiles_list = ["[5*]N1CCC[C@@]1([13*])C", "[4*]CCN[5*]", "[4*]C[8*]", "[*]C[*]", "[3*]O[3*]"]
 fragment_smiles = fragment_smiles_list[1]
@@ -39,7 +39,7 @@ filtered_indices, filtered_BBs = compound_filter.get_filtered_BBs(fragment_smile
 
 ## Source Code
 
-::: FragmentRetro.utils.filter_compound
+::: fragmentretro.utils.filter_compound
     handler: python
     options:
       show_root_heading: true

docs/FragmentRetro/utils/helper.md

@@ -7,7 +7,7 @@ This module provides helper functions for working with SMILES strings.
 `canonicalize_smiles` is for canonicalizing SMILES strings.
 
 ```python
-from FragmentRetro.utils.helpers import canonicalize_smiles
+from fragmentretro.utils.helpers import canonicalize_smiles
 
 smiles = 'C[C@@H](O)C(=O)O'
 canonical_smiles = canonicalize_smiles(smiles)
@@ -19,7 +19,7 @@ print(f"Canonical SMILES: {canonical_smiles}")
 `replace_dummy_atoms_regex` is for replacing dummy atoms with hydrogen atoms for pattern fingerprint screening. See how it's used in the `filter_compounds` function in the `CompoundFilter` class.
 
 ```python
-from FragmentRetro.utils.helpers import replace_dummy_atoms_regex
+from fragmentretro.utils.helpers import replace_dummy_atoms_regex
 
 smiles_with_dummy = '[5*]N1CCC[C@@]1([13*])C'
 smiles_without_dummy = replace_dummy_atoms_regex(smiles_with_dummy)
@@ -30,7 +30,7 @@ print(f"SMILES without dummy atoms: {smiles_without_dummy}")
 `remove_indices_before_dummy` is for removing indices before dummy atoms. This is to record processed fragment SMILES strings in the most general format. See how it's used in the `Retrosythesis` class as well.
 
 ```python
-from FragmentRetro.utils.helpers import remove_indices_before_dummy
+from fragmentretro.utils.helpers import remove_indices_before_dummy
 
 smiles_with_indices = '[5*]N1CCC[C@@]1([13*])C'
 smiles_without_indices = remove_indices_before_dummy(smiles_with_indices)
@@ -40,7 +40,7 @@ print(f"SMILES without indices: {smiles_without_indices}")
 
 ## Source Code
 
-::: FragmentRetro.utils.helpers
+::: fragmentretro.utils.helpers
     handler: python
     options:
       show_root_heading: true