refactor pdbfixer

utils/pre-process/structure-change/pdbfixer-tool/Dockerfile

@@ -0,0 +1,31 @@
+# docker build -f Dockerfile -t polusai/pdbfixer-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
+# errors installing pdbfixer from poetry so using conda
+COPY environment.yml ${EXEC_DIR}
+RUN mamba env create -f ${EXEC_DIR}/environment.yml
+RUN echo "source activate project_env" > ~/.bashrc
+ENV PATH /opt/conda/envs/env/bin:$PATH
+
+COPY src ${EXEC_DIR}/src
+
+ADD Dockerfile .
+
+RUN conda run -n project_env pip install ${EXEC_DIR} --no-cache-dir
+
+CMD ["--help"]

utils/pdbfixer-plugin/README.md → utils/pre-process/structure-change/pdbfixer-tool/README.md

@@ -12,7 +12,7 @@ This plugin takes 9 input arguments and 1 output argument:
 | input_helper_pdb_path | Template input PDB path | Input | File | File |
 | pdbid | PDB id from RCSB? | Input | string | string |
 | url | URL to retrieve PDB from | Input | string | string |
-| output_pdb_path |  | Input | string | string |
+| output_pdb_path | Output protein file path name | Input | string | string |
 | add_atoms | What missing atoms to add, all, heavy or none | Input | string | string |
 | add_residues | If set to True, adds missing residue | Input | boolean | boolean |
 | replace_nonstandard | Replace nonstandard residues with standard equivalents | Input | boolean | boolean |

utils/pdbfixer-plugin/environment.yml → utils/pre-process/structure-change/pdbfixer-tool/environment.yml

@@ -7,5 +7,6 @@ dependencies:
   - pdbfixer==1.9
   - ruamel.yaml==0.17.21
   - pytest==8.1.1
-  - cwltool==3.1.20240404144621
-  - cwl-utils==0.33
+  - pip
+  - pip:
+    - sophios==0.1.1

utils/pdbfixer-plugin/ict.yml → utils/pre-process/structure-change/pdbfixer-tool/ict.yml

@@ -1,11 +1,12 @@
 specVersion: 0.1.0
 name: labshare/pdbfixer
 version: 0.1.0
-container: polusai/pdbfixer-plugin:0.1.0
+container: polusai/pdbfixer-tool:0.1.0
 entrypoint: ""
 title: pdbfixer
 description: Fix pdbfiles.
-author: Data Scientist ([email protected])
+author: Brandon Walker, Nazanin Donyapour
+contact: [email protected], [email protected]
 repository: https://github.com/labshare/mmtools
 documentation: https://ncats.nih.gov/preclinical/core/informatics
 citation:

utils/pdbfixer-plugin/pdb_fixer.cwl → utils/pre-process/structure-change/pdbfixer-tool/pdb_fixer_0@1@0.cwl

@@ -12,7 +12,7 @@ baseCommand: ["python", "-m", "polus.mm.utils.pdbfixer"]
 
 hints:
   DockerRequirement:
-    dockerPull: mrbrandonwalker/pdbfixer
+    dockerPull: polusai/pdbfixer-tool@sha256:8c4c7756a3981799da1b7699a471be59684890c365fa4e30c62c96d256eb089f
 
 inputs:
   input_pdb_path:

utils/pre-process/structure-change/pdbfixer-tool/tests/test_pdbfixer.py

@@ -0,0 +1,64 @@
+"""Tests for pdbfixer."""
+from pathlib import Path
+
+from polus.mm.utils.pdbfixer.pdbfixer import runpdbfixer
+from sophios.api.pythonapi import Step
+from sophios.api.pythonapi import Workflow
+
+
+def test_pdbfixer() -> None:
+    """Test pdbfixer."""
+    add_atoms = "all"
+    add_residues = True
+    pdbid = ""
+    url = ""
+    replace_nonstandard = True
+    keep_heterogens = "all"
+    input_pdb_path = "1msn_protein.pdb"
+    input_helper_pdb_path = "1msn_protein.pdb"
+    input_pdb_path = str(Path(__file__).resolve().parent / Path(input_pdb_path))
+    input_helper_pdb_path = str(
+        Path(__file__).resolve().parent / Path(input_helper_pdb_path),
+    )
+    output_pdb_path = "test.pdb"
+    output_pdb_path = str(Path(__file__).resolve().parent / Path(output_pdb_path))
+
+    runpdbfixer(
+        input_pdb_path,
+        input_helper_pdb_path,
+        output_pdb_path,
+        add_atoms,
+        add_residues,
+        pdbid,
+        url,
+        replace_nonstandard,
+        keep_heterogens,
+    )
+
+    assert Path(output_pdb_path).exists()
+
+
+def test_cwl_pdb_fixer() -> None:
+    """Test the pdbfixer function in cwltool."""
+    cwl_file_str = "pdb_fixer_0@[email protected]"
+    cwl_file = Path(__file__).resolve().parent / Path(cwl_file_str)
+    # Create a Step instance for pdb_fixer
+    pdb_fixer = Step(clt_path=cwl_file)
+
+    # Set input properties
+    pdb_fixer.input_pdb_path = str(Path(__file__).resolve().parent / "1msn_protein.pdb")
+    pdb_fixer.input_helper_pdb_path = str(
+        Path(__file__).resolve().parent / "1msn_protein.pdb",
+    )
+    pdb_fixer.output_pdb_path = "output.pdb"
+
+    # Define the workflow
+    steps = [pdb_fixer]
+    filename = "pdb_fixer"
+    workflow = Workflow(steps, filename)
+
+    # Run the workflow
+    workflow.run()
+
+    # Check if the output file exists
+    assert Path("output.pdb").exists(), "The file 'output.pdb' does not exist."