Merge pull request #3 from misterbrandonwalker/sanitize_ligand

sanitize_ligand

utils/sanitize-ligand-plugin/.bumpversion.cfg

@@ -0,0 +1,29 @@
+[bumpversion]
+current_version = 0.1.1-dev1
+commit = False
+tag = False
+parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<dev>\d+))?
+serialize = 
+	{major}.{minor}.{patch}-{release}{dev}
+	{major}.{minor}.{patch}
+
+[bumpversion:part:release]
+optional_value = _
+first_value = dev
+values = 
+	dev
+	_
+
+[bumpversion:part:dev]
+
+[bumpversion:file:pyproject.toml]
+search = version = "{current_version}"
+replace = version = "{new_version}"
+
+[bumpversion:file:VERSION]
+
+[bumpversion:file:README.md]
+
+[bumpversion:file:plugin.json]
+
+[bumpversion:file:src/polus/mm/utils/__init__.py]

utils/sanitize-ligand-plugin/.dockerignore

@@ -0,0 +1,4 @@
+.venv
+out
+tests
+__pycache__

utils/sanitize-ligand-plugin/CHANGELOG.md

@@ -0,0 +1,5 @@
+# CHANGELOG
+
+## 0.1.0
+
+Initial release.

utils/sanitize-ligand-plugin/Dockerfile

@@ -0,0 +1,27 @@
+FROM condaforge/mambaforge
+
+# environment variables defined
+ENV EXEC_DIR="/opt/executables"
+
+RUN mkdir -p ${EXEC_DIR}
+COPY pyproject.toml ${EXEC_DIR}
+COPY VERSION ${EXEC_DIR}
+COPY README.md ${EXEC_DIR}
+COPY CHANGELOG.md ${EXEC_DIR}
+
+RUN conda install -c conda-forge rdkit --yes
+
+RUN pip install filepattern
+
+RUN conda init bash
+
+RUN mamba clean --all --yes
+
+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

@@ -0,0 +1,18 @@
+# Sanitize Ligand (0.1.1-dev1)
+
+Handle molecules with rdkit errors gracefully.
+
+## Building
+
+To build the Docker image for the conversion plugin, run `./build-docker.sh`.
+ of `plugin.json` into the pop-up window and submit.
+
+## Options
+
+This plugin takes 2 input arguments and 1 output argument:
+
+| Name                   | Description                      | I/O    | Type   |
+|------------------------|----------------------------------|--------|--------|
+| pattern                | Filepattern to parse files       | Input  | string
+| indir                  | Input collection                 | Input  | collection
+| outdir                 | Output collection                | Output | collection

utils/sanitize-ligand-plugin/VERSION

@@ -0,0 +1 @@
+0.1.1-dev1

utils/sanitize-ligand-plugin/build-docker.sh

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

utils/sanitize-ligand-plugin/plugin.json

@@ -0,0 +1,36 @@
+{
+  "name": "Sanitize Ligand",
+  "version": "0.1.1-dev1",
+  "title": "Sanitize Ligand",
+  "description": "Handle molecules with rdkit errors gracefully.",
+  "author": "Brandon Walker ([email protected])",
+  "institution": "National Center for Advancing Translational Sciences, National Institutes of Health",
+  "repository": "https://github.com/labshare/polus-plugins",
+  "website": "https://ncats.nih.gov/preclinical/core/informatics",
+  "citation": "",
+  "containerId": "polusai/sanitize-ligand-plugin:0.1.1-dev1",
+  "baseCommand": [
+    "python3",
+    "-m",
+    "polus.plugins.sanitize_ligand"
+  ],
+  "inputs": {
+    "pattern": {
+      "type": "string",
+      "title": "Filepattern to parse files",
+      "description": "Filepattern to parse sdf files for sanitizing.",
+      "required": "True"
+    },
+    "indir": {
+      "type": "collection",
+      "description": "Input collection.",
+      "required": "True"
+    }
+  },
+  "outputs": {
+    "outdir": {
+      "type": "collection",
+      "description": "Output collection."
+    }
+  }
+}

utils/sanitize-ligand-plugin/pyproject.toml

@@ -0,0 +1,30 @@
+[tool.poetry]
+name = "mm-polus-sanitize-ligand"
+version = "0.1.1-dev1"
+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"
+typer = "^0.7.0"
+rdkit = "*"
+
+[tool.poetry.group.dev.dependencies]
+bump2version = "^1.0.1"
+pytest = "^7.4"
+pytest-sugar = "^0.9.6"
+pre-commit = "^3.2.1"
+black = "^23.3.0"
+mypy = "^1.1.1"
+ruff = "^0.0.270"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.pytest.ini_options]
+pythonpath = [
+  "."
+]

utils/sanitize-ligand-plugin/run-plugin.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+
+version=$(<VERSION)
+
+container_input_dir="/inddir"
+container_output_dir="/outdir"
+
+docker run -v $tool_mount_path_input:${container_input_dir} \
+           -v $tool_mount_path_output:${container_output_dir} \
+            mm/sanitize-ligand-plugin:${version} \
+            --pattern ${pattern} \
+            --indir ${container_input_dir} \
+            --outdir ${container_output_dir}

utils/sanitize-ligand-plugin/src/polus/mm/utils/__init__.py

@@ -0,0 +1,7 @@
+"""sanitize_ligand."""
+
+__version__ = "0.1.1-dev1"
+
+from polus.mm.utils.sanitize_ligand import (  # pylint: disable=unused-import
+    sanitize_ligand,
+)

utils/sanitize-ligand-plugin/src/polus/mm/utils/__main__.py

@@ -0,0 +1,63 @@
+"""Package entrypoint for the sanitize_ligand package."""
+
+# Base packages
+import logging
+from os import environ
+from pathlib import Path
+
+import filepattern as fp
+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(
+    pattern: str = typer.Option(
+        ...,
+        "--pattern",
+        help="Input filepattern to be processed.",
+    ),
+    in_dir: Path = typer.Option(
+        ...,
+        "--indir",
+        help="Input directory.",
+        exists=True,
+        writable=True,
+        file_okay=False,
+        resolve_path=True,
+    ),
+    out_dir: Path = typer.Option(
+        ...,
+        "--outdir",
+        help="Output directory.",
+        exists=True,
+        writable=True,
+        file_okay=False,
+        resolve_path=True,
+    ),
+) -> None:
+    """Sanitize Ligand."""
+    logger.info(f"pattern: {pattern}")
+    logger.info(f"indir: {in_dir}")
+    logger.info(f"outdir: {out_dir}")
+    ligand_file_paths = []
+    ligand_files = fp.FilePattern(in_dir, pattern)
+    for input_small_mol_ligand in ligand_files():
+        ligand = input_small_mol_ligand[-1][0]
+        ligand_file_paths.append(ligand)
+
+    sanitize_ligand(ligand_file_paths, out_dir)
+
+
+if __name__ == "__main__":
+    app()