generate-conformers

utils/pre-process/data-download/pdbbind-generate-conformers-tool/.bumpversion.cfg

@@ -0,0 +1,29 @@
+[bumpversion]
+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+))?
+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/pdbbind_generate_conformers/__init__.py]

utils/pre-process/data-download/pdbbind-generate-conformers-tool/.gitattributes

@@ -0,0 +1,5 @@
+*.pdb filter=lfs diff=lfs merge=lfs -text
+*.pdbqt filter=lfs diff=lfs merge=lfs -text
+*.mol2 filter=lfs diff=lfs merge=lfs -text
+*.xlsx filter=lfs diff=lfs merge=lfs -text
+*.sdf filter=lfs diff=lfs merge=lfs -text

utils/pre-process/data-download/pdbbind-generate-conformers-tool/CHANGELOG.md

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

utils/pre-process/data-download/pdbbind-generate-conformers-tool/Dockerfile

@@ -0,0 +1,23 @@
+# docker build -f Dockerfile -t polusai/pdbbind-generate-conformers-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/pre-process/data-download/pdbbind-generate-conformers-tool/README.md

@@ -0,0 +1,22 @@
+# pdbbind_generate_conformers (0.1.0)
+
+Download the PDBbind refined database and generate conformers from SMILES
+
+## Options
+
+This plugin takes 9 input arguments and 3 output argument:
+
+| Name          | Description             | I/O    | Type   | Default |
+|---------------|-------------------------|--------|--------|---------|
+| input_excel_path |  | Input | File | File |
+| query | query str to search the dataset, Type: string, File type: input, Accepted formats: txt | Input | string | string |
+| output_txt_path | Path to the text dataset file, Type: string, File type: output, Accepted formats: txt | Input | string | string |
+| output_sdf_path | Path to the input file, Type: string, File type: input, Accepted formats: sdf | Input | string | string |
+| min_row | The row min inex, Type: int | Input | int | int |
+| max_row | The row max inex, Type: int | Input | int | int |
+| smiles_column | The name of the smiles column, Type: string, File type: output, Accepted formats: txt | Input | string | string |
+| binding_data_column | The name of the binding data column, Type: string, File type: output, Accepted formats: txt | Input | string | string |
+| convert_Kd_dG | If this is set to true, dG will be calculated | Input | boolean | boolean |
+| output_txt_path | Path to the txt file | Output | File | File |
+| output_sdf_path | Path to the input file, Type: string, File type: input, Accepted formats: sdf | Output | File[] | File[] |
+| experimental_dGs | Experimental Free Energies of Binding | Output | float[] | float[] |

utils/pre-process/data-download/pdbbind-generate-conformers-tool/VERSION

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

utils/pre-process/data-download/pdbbind-generate-conformers-tool/build-docker.sh

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

utils/pre-process/data-download/pdbbind-generate-conformers-tool/environment.yml

@@ -0,0 +1,10 @@
+name: project_env
+channels:
+  - conda-forge
+dependencies:
+  - python==<3.12,>=3.9
+  - pandas==2.2.2
+  - rdkit==2024.03.2
+  - openpyxl==3.1.2
+  - xorg-libxrender==0.9.11
+  - pytest==8.2.0

utils/pre-process/data-download/pdbbind-generate-conformers-tool/ict.yml

@@ -0,0 +1,123 @@
+specVersion: "0.1.0"
+name: pdbbind_generate_conformers
+version: 0.1.0
+container: generate-conformers-tool
+entrypoint:
+title: pdbbind_generate_conformers
+description: Download the PDBbind refined database and generate conformers from SMILES
+author: Brandon Walker, Nazanin Donyapour
+contact: [email protected], [email protected]
+repository:
+documentation:
+citation:
+
+inputs:
+  - name: input_excel_path
+    required: true
+    description:
+    type: File
+    format:
+      uri: edam:format_3620
+  - name: query
+    required: true
+    description: query str to search the dataset, Type string, File type input, Accepted formats txt
+    type: string
+    format:
+      uri: edam:format_2330
+  - name: output_txt_path
+    required: true
+    description: Path to the text dataset file, Type string, File type output, Accepted formats txt
+    type: string
+    defaultValue: system.log
+    format:
+      uri: edam:format_2330
+  - name: output_sdf_path
+    required: true
+    description: Path to the input file, Type string, File type input, Accepted formats sdf
+    type: string
+    format:
+      uri: edam:format_3814
+  - name: min_row
+    required: true
+    description: The row min inex, Type int
+    type: int
+    format:
+      uri: edam:format_2330
+  - name: max_row
+    required: true
+    description: The row max inex, Type int
+    type: int
+    format:
+      uri: edam:format_2330
+  - name: smiles_column
+    required: true
+    description: The name of the smiles column, Type string, File type output, Accepted formats txt
+    type: string
+    format:
+      uri: edam:format_2330
+  - name: binding_data_column
+    required: true
+    description: The name of the binding data column, Type string, File type output, Accepted formats txt
+    type: string
+    format:
+      uri: edam:format_2330
+  - name: convert_Kd_dG
+    required: true
+    description: If this is set to true, dG will be calculated
+    type: boolean
+    format:
+      uri: edam:format_2330
+outputs:
+  - name: output_txt_path
+    required: true
+    description: Path to the txt file
+    type: File
+    format:
+      uri: edam:format_2330
+  - name: output_sdf_path
+    required: true
+    description: Path to the input file, Type string, File type input, Accepted formats sdf
+    type: File[]
+    format:
+      uri: edam:format_3814
+  - name: experimental_dGs
+    required: true
+    description: Experimental Free Energies of Binding
+    type: float[]
+ui:
+  - key: inputs.input_excel_path
+    title: "input_excel_path: "
+    description: ""
+    type: File
+  - key: inputs.query
+    title: "query: "
+    description: "query str to search the dataset, Type string, File type input, Accepted formats txt"
+    type: string
+  - key: inputs.output_txt_path
+    title: "output_txt_path: "
+    description: "Path to the text dataset file, Type string, File type output, Accepted formats txt"
+    type: string
+  - key: inputs.output_sdf_path
+    title: "output_sdf_path: "
+    description: "Path to the input file, Type string, File type input, Accepted formats sdf"
+    type: string
+  - key: inputs.min_row
+    title: "min_row: "
+    description: "The row min inex, Type int"
+    type: int
+  - key: inputs.max_row
+    title: "max_row: "
+    description: "The row max inex, Type int"
+    type: int
+  - key: inputs.smiles_column
+    title: "smiles_column: "
+    description: "The name of the smiles column, Type string, File type output, Accepted formats txt"
+    type: string
+  - key: inputs.binding_data_column
+    title: "binding_data_column: "
+    description: "The name of the binding data column, Type string, File type output, Accepted formats txt"
+    type: string
+  - key: inputs.convert_Kd_dG
+    title: "convert_Kd_dG: "
+    description: "If this is set to true, dG will be calculated"
+    type: checkbox