refactor sanitize_ligand

utils/sanitize-ligand-plugin/.bumpversion.cfg → utils/docking/diffdock/sanitize-ligand-tool/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.1.1-dev1
+current_version = 0.1.0
 commit = False
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<dev>\d+))?

utils/docking/diffdock/sanitize-ligand-tool/.gitattributes

@@ -0,0 +1 @@
+*.sdf filter=lfs diff=lfs merge=lfs -text

utils/docking/diffdock/sanitize-ligand-tool/Dockerfile

@@ -0,0 +1,25 @@
+# docker build -f Dockerfile -t polusai/sanitize-ligand-tool .
+FROM condaforge/mambaforge
+
+ENV EXEC_DIR="/opt/executables"
+ENV POLUS_LOG="INFO"
+RUN mkdir -p ${EXEC_DIR}
+
+
+# Work directory defined in the base container
+# WORKDIR ${EXEC_DIR}
+
+COPY pyproject.toml ${EXEC_DIR}
+COPY VERSION ${EXEC_DIR}
+COPY README.md ${EXEC_DIR}
+COPY CHANGELOG.md ${EXEC_DIR}
+
+# Install needed packages here
+
+COPY src ${EXEC_DIR}/src
+
+ADD Dockerfile .
+
+RUN pip3 install ${EXEC_DIR} --no-cache-dir
+
+CMD ["--help"]

utils/sanitize-ligand-plugin/README.md → utils/docking/diffdock/sanitize-ligand-tool/README.md

@@ -1,4 +1,4 @@
-# Sanitize Ligand (0.1.1-dev1)
+# Sanitize Ligand (0.1.0)
 
 Handle molecules with rdkit errors gracefully.
 

utils/docking/diffdock/sanitize-ligand-tool/VERSION

@@ -0,0 +1 @@
+0.1.0

utils/docking/diffdock/sanitize-ligand-tool/build-docker.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+
+version=$(<VERSION)
+docker build . -t polusai/sanitize-ligand-tool:${version}

utils/docking/diffdock/sanitize-ligand-tool/environment.yml

@@ -0,0 +1,9 @@
+name: project_env
+channels:
+  - conda-forge
+dependencies:
+  - python==3.10
+  - rdkit==2024.03.1
+  - pytest==8.1.1
+  - cwltool==3.1.20240404144621
+  - cwl-utils==0.33

utils/docking/diffdock/sanitize-ligand-tool/ict.yml

@@ -0,0 +1,36 @@
+specVersion: "0.1.0"
+name: sanitize_ligand
+version: 0.1.0
+container: sanitize-ligand-tool
+entrypoint:
+title: sanitize_ligand
+description: Sanitize input ligand
+author: Brandon Walker, Nazanin Donyapour
+contact: [email protected], [email protected]
+repository:
+documentation:
+citation:
+
+inputs:
+  - name: input_small_mol_ligand
+    required: true
+    description:
+    type: File
+    format:
+      uri: edam:format_3814
+outputs:
+  - name: output_ligand
+    required: true
+    description:
+    type: File
+    format:
+      uri: edam:format_3814
+  - name: valid_ligand
+    required: true
+    description:
+    type: boolean
+ui:
+  - key: inputs.input_small_mol_ligand
+    title: "input_small_mol_ligand: "
+    description: ""
+    type: File

utils/sanitize-ligand-plugin/pyproject.toml → utils/docking/diffdock/sanitize-ligand-tool/pyproject.toml

@@ -1,15 +1,16 @@
 [tool.poetry]
 name = "mm-polus-sanitize-ligand"
-version = "0.1.1-dev1"
+version = "0.1.0"
 description = "Handle molecules with rdkit errors gracefully."
 authors = ["Brandon Walker <[email protected]>"]
 readme = "README.md"
 packages = [{include = "polus", from = "src"}]
 
 [tool.poetry.dependencies]
-python = ">=3.8"
+python = ">=3.9,<3.12"
 typer = "^0.7.0"
-rdkit = "*"
+sophios = "0.1.1"
+rdkit = "2024.3.3"
 
 [tool.poetry.group.dev.dependencies]
 bump2version = "^1.0.1"

utils/docking/diffdock/sanitize-ligand-tool/sanitize_ligand_0@1@0.cwl

@@ -0,0 +1,73 @@
+#!/usr/bin/env cwl-runner
+cwlVersion: v1.0
+
+class: CommandLineTool
+
+label: Sanitize input ligand
+
+doc: |-
+  Sanitize input ligand
+
+baseCommand: ["python", "-m", "polus.mm.utils.sanitize_ligand"]
+
+hints:
+  DockerRequirement:
+    dockerPull:  polusai/sanitize-ligand-tool@sha256:926e501300fa5b940c250347cf346cdcacf21944469ed82c3788a58e0957c18d
+
+requirements:
+  InlineJavascriptRequirement: {}
+  InitialWorkDirRequirement: # conditionally overwrite the input ligand, otherwise cwltool will symlink to the original
+    listing:
+      - $(inputs.input_small_mol_ligand)
+
+inputs:
+
+  input_small_mol_ligand:
+    type: File
+    format:
+      - edam:format_3814
+    inputBinding:
+      prefix: --input_small_mol_ligand
+
+outputs:
+
+  output_ligand:
+    type: File
+    format: edam:format_3814
+    outputBinding:
+      glob: "*.sdf"
+
+  valid_ligand:
+    type: boolean
+    outputBinding:
+      glob: valid.txt
+      loadContents: true
+      outputEval: |
+        ${
+          // Read the contents of the file
+          const lines = self[0].contents.split("\n");
+          // Read boolean value from the first line
+          const valid = lines[0].trim() === "True";
+          return valid;
+
+        }
+
+  stderr:
+    type: File
+    outputBinding:
+      glob: stderr
+
+  stdout:
+    type: File
+    outputBinding:
+      glob: stdout
+
+stderr: stderr
+
+stdout: stdout
+
+$namespaces:
+  edam: https://edamontology.org/
+
+$schemas:
+- https://raw.githubusercontent.com/edamontology/edamontology/master/EDAM_dev.owl

utils/sanitize-ligand-plugin/src/polus/mm/utils/__init__.py → utils/docking/diffdock/sanitize-ligand-tool/src/polus/mm/utils/__init__.py

@@ -1,6 +1,6 @@
 """sanitize_ligand."""
 
-__version__ = "0.1.1-dev1"
+__version__ = "0.1.0"
 
 from polus.mm.utils.sanitize_ligand import (  # pylint: disable=unused-import
     sanitize_ligand,

utils/docking/diffdock/sanitize-ligand-tool/src/polus/mm/utils/__main__.py

@@ -0,0 +1,35 @@
+"""Package entrypoint for the sanitize_ligand package."""
+
+# Base packages
+import logging
+from os import environ
+
+import typer
+from polus.mm.utils.sanitize_ligand import sanitize_ligand
+
+logging.basicConfig(
+    format="%(asctime)s - %(name)-8s - %(levelname)-8s - %(message)s",
+    datefmt="%d-%b-%y %H:%M:%S",
+)
+POLUS_LOG = getattr(logging, environ.get("POLUS_LOG", "INFO"))
+logger = logging.getLogger("polus.mm.utils.sanitize_ligand")
+logger.setLevel(POLUS_LOG)
+
+app = typer.Typer(help="Sanitize Ligand.")
+
+
+@app.command()
+def main(
+    input_small_mol_ligand: str = typer.Option(
+        ...,
+        "--input_small_mol_ligand",
+        help="Input input_small_mol_ligand to be processed.",
+    ),
+) -> None:
+    """Sanitize Ligand."""
+    logger.info(f"input_small_mol_ligand: {input_small_mol_ligand}")
+    sanitize_ligand(input_small_mol_ligand)
+
+
+if __name__ == "__main__":
+    app()

utils/sanitize-ligand-plugin/src/polus/mm/utils/sanitize_ligand.py → utils/docking/diffdock/sanitize-ligand-tool/src/polus/mm/utils/sanitize_ligand.py

@@ -163,35 +163,31 @@ def attempt_fix_ligand(
 
 
 def sanitize_ligand(
-    ligand_files: list[Path],
+    input_small_mol_ligand: Path,
     outdir: Path,
 ) -> None:
     """Sanitize ligand file.
 
     Args:
-        ligand_files: Ligand file pattern
+        input_small_mol_ligand: Ligand file
         outdir: Output directory
     """
-    for input_small_mol_ligand in ligand_files:
-        output_small_mol_ligand = outdir / Path(input_small_mol_ligand.name)
-        mol: Chem.SDMolSupplier = Chem.SDMolSupplier(
-            input_small_mol_ligand.resolve(),
-            sanitize=False,
-            removeHs=False,
-        )[0]
-
-        valid_ligand = is_valid_ligand(mol)
-        if not valid_ligand:
-            valid_ligand, rdkit_mol = attempt_fix_ligand(mol)
-        else:
-            rdkit_mol = mol
-
-        if valid_ligand:
-            with Chem.SDWriter(output_small_mol_ligand) as w:
-                w.write(rdkit_mol)
-
-    if len(ligand_files) == 1:
-        # if scattering with many files
-        # let the presence of the file indicate validity
-        with outdir.joinpath("valid.txt").open("w", encoding="utf-8") as f:
-            f.write(str(valid_ligand))
+    output_small_mol_ligand = outdir / Path(input_small_mol_ligand.name)
+    mol: Chem.SDMolSupplier = Chem.SDMolSupplier(
+        input_small_mol_ligand.resolve(),
+        sanitize=False,
+        removeHs=False,
+    )[0]
+
+    valid_ligand = is_valid_ligand(mol)
+    if not valid_ligand:
+        valid_ligand, rdkit_mol = attempt_fix_ligand(mol)
+    else:
+        rdkit_mol = mol
+
+    if valid_ligand:
+        with Chem.SDWriter(output_small_mol_ligand) as w:
+            w.write(rdkit_mol)
+
+    with outdir.joinpath("valid.txt").open("w", encoding="utf-8") as f:
+        f.write(str(valid_ligand))

utils/docking/diffdock/sanitize-ligand-tool/tests/test_sanitize.py

@@ -0,0 +1,59 @@
+"""Test the sanitize_ligand plugin."""
+from pathlib import Path
+
+import pytest
+from polus.mm.utils.sanitize_ligand import attempt_fix_ligand
+from rdkit import Chem
+from sophios.api.pythonapi import Step
+from sophios.api.pythonapi import Workflow
+
+
+@pytest.mark.catch_error()
+def test_kekulization_error_catch() -> None:
+    """Test catching Kekulization error.
+
+    Can't kekulize mol.  Unkekulized atoms: 6 7 8 9 10.
+    """
+    mol = Chem.MolFromSmiles("c1ccc(cc1)-c1nnc(n1)-c1ccccc1")
+    valid_ligand, rdkit_mol = attempt_fix_ligand(mol)
+    assert not valid_ligand
+
+
+@pytest.mark.fix_ligand()
+def test_fix_explicit_valence_error() -> None:
+    """Test fixing explicit valence error.
+
+    Explicit valence for atom # 1 C, 5, is greater than permitted
+    """
+    mol = Chem.MolFromSmiles("c1c(ccc2NC(CN=c(c21)(C)C)=O)O", sanitize=False)
+    valid_ligand, rdkit_mol = attempt_fix_ligand(mol)
+    assert valid_ligand
+
+
+def test_sanitize_ligand_cwl() -> None:
+    """Test the sanitize_ligand CWL."""
+    cwl_file_str = "sanitize_ligand_0@[email protected]"
+    cwl_file = Path(__file__).resolve().parent.parent / Path(cwl_file_str)
+
+    input_ligand_path = Path(__file__).resolve().parent / Path("4xk9_ligand.sdf")
+
+    sanitize_ligand = Step(clt_path=cwl_file)
+    sanitize_ligand.input_small_mol_ligand = input_ligand_path
+
+    steps = [sanitize_ligand]
+    filename = "sanitize_ligand"
+    viz = Workflow(steps, filename)
+
+    viz.run()
+
+    outdir = Path("outdir")
+    output_files = list(outdir.rglob("*.sdf"))
+
+    assert output_files, "No output SDF files were generated."
+
+    # Check if the input SDF filename is part of the output
+    input_filename = input_ligand_path.name
+    output_filenames = [f.name for f in output_files]
+    assert any(
+        input_filename in of for of in output_filenames
+    ), f"The input SDF file '{input_filename}' was not found in the output."