add ict 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 = 0.1.1-dev2
 commit = False
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<dev>\d+))?
@@ -24,6 +24,6 @@ replace = version = "{new_version}"
 
 [bumpversion:file:README.md]
 
-[bumpversion:file:plugin.json]
+[bumpversion:file:ict.yml]
 
 [bumpversion:file:src/polus/mm/utils/__init__.py]

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

@@ -1,4 +1,6 @@
-FROM condaforge/mambaforge
+# docker build -f Dockerfile -t mrbrandonwalker/sanitize_ligand_tool .
+
+FROM python:3.11-buster
 
 # environment variables defined
 ENV EXEC_DIR="/opt/executables"
@@ -8,20 +10,11 @@ COPY pyproject.toml ${EXEC_DIR}
 COPY VERSION ${EXEC_DIR}
 COPY README.md ${EXEC_DIR}
 COPY CHANGELOG.md ${EXEC_DIR}
+# need copy src here because pyproject.toml has a reference to the src directory
+COPY src ${EXEC_DIR}/src
 
-RUN conda install -c conda-forge rdkit --yes
-
-RUN pip install filepattern
-
-RUN conda init bash
-
-RUN mamba clean --all --yes
+WORKDIR ${EXEC_DIR}
 
 ADD Dockerfile ${EXEC_DIR}
 
-COPY src ${EXEC_DIR}/src
-
 RUN pip3 install ${EXEC_DIR} --no-cache-dir
-# Default command. Additional arguments are provided through the command line
-ENTRYPOINT ["python3", "-m", "polus.mm.utils"]
-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 (0.1.1-dev2)
 
 Handle molecules with rdkit errors gracefully.
 

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

@@ -0,0 +1 @@
+0.1.1-dev2

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

@@ -0,0 +1,25 @@
+specVersion: 0.1.0
+name: labshare/sanitize-ligand
+version: 0.1.1-dev2
+container: polusai/sanitize-ligand-tool:0.1.1-dev2
+entrypoint: ""
+title: Sanitize Ligand
+description: Handle molecules with rdkit errors gracefully.
+author: Brandon Walker ([email protected])
+repository: https://github.com/labshare/polus-plugins
+documentation: https://ncats.nih.gov/preclinical/core/informatics
+citation: ""
+inputs:
+- name: pattern
+  required: true
+  description: Filepattern to parse files
+  type: string
+- name: indir
+  required: true
+  description: Input collection.
+  type: collection
+outputs:
+- name: outdir
+  required: false
+  description: Output collection.
+  type: collection

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 = "0.1.1-dev2"
 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 = "*"
+rdkit = "2024.3.3"
+sophios = "0.1.1"
 
 [tool.poetry.group.dev.dependencies]
 bump2version = "^1.0.1"

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

@@ -0,0 +1,65 @@
+#!/usr/bin/env cwl-runner
+cwlVersion: v1.0
+
+class: CommandLineTool
+
+label: Sanitize input ligand
+
+doc: |-
+  Sanitize input ligand
+
+baseCommand: ["python", "-m", "polus.mm.utils"]
+
+hints:
+  DockerRequirement:
+    dockerPull:  mrbrandonwalker/sanitize_ligand_tool@sha256:6c272a427377e05ed2a83da5cdb3c00678b74b05c248f56c78d2349201f34d2f
+
+requirements:
+  InlineJavascriptRequirement: {}
+  InitialWorkDirRequirement: # conditionally overwrite the input ligand, otherwise cwltool will symlink to the original
+    listing:
+        - entry: $(inputs.input_small_mol_ligand)
+          writable: true
+
+inputs:
+
+  input_small_mol_ligand:
+    type: File
+    format: edam:format_3814
+    inputBinding:
+      prefix: --input_small_mol_ligand
+
+  output_ligand:
+    type: string?
+
+  valid_ligand:
+    type: string?
+
+outputs:
+
+  output_ligand:
+    type: File
+    format: edam:format_3814
+    outputBinding:
+      glob: "*.sdf"
+
+  valid_ligand:
+    type: boolean
+    outputBinding:
+      glob: valid.txt
+      loadContents: true
+      outputEval: |
+        ${
+          // Read the contents of the file
+          const lines = self[0].contents.split("\n");
+          // Read boolean value from the first line
+          const valid = lines[0].trim() === "True";
+          return valid;
+
+        }
+
+$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__ = "0.1.1-dev2"
 
 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 +1,36 @@
+"""Package entrypoint for the sanitize_ligand package."""
+
+# Base packages
+import logging
+from os import environ
+from pathlib import Path
+
+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: Path = 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

@@ -162,36 +162,28 @@ def attempt_fix_ligand(
     return valid_lig, molecule
 
 
-def sanitize_ligand(
-    ligand_files: list[Path],
-    outdir: Path,
-) -> None:
+def sanitize_ligand(input_small_mol_ligand: Path) -> None:
     """Sanitize ligand file.
 
     Args:
-        ligand_files: Ligand file pattern
-        outdir: Output directory
+        input_small_mol_ligand: Ligand file
     """
-    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 = 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 Path("valid.txt").open("w", encoding="utf-8") as f:
+        f.write(str(valid_ligand))