first commit

utils/mm-python-template/{{cookiecutter.container_name}}/src/{{cookiecutter.package_folders}}/{{cookiecutter.package_name}}.py

@@ -0,0 +1 @@
+"""{{ cookiecutter.plugin_name }}."""

utils/pre-process/data-download/torchdrug_download-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/torchdrug_download/__init__.py]

utils/pre-process/data-download/torchdrug_download-tool/.dockerignore

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

utils/pre-process/data-download/torchdrug_download-tool/.gitignore

@@ -0,0 +1 @@
+poetry.lock

utils/pre-process/data-download/torchdrug_download-tool/CHANGELOG.md

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

utils/pre-process/data-download/torchdrug_download-tool/Dockerfile

@@ -0,0 +1,49 @@
+# docker build -f Dockerfile -t polusai/torch-drug-tool .
+
+FROM condaforge/mambaforge
+
+ENV EXEC_DIR="/opt/executables"
+ENV POLUS_LOG="INFO"
+RUN mkdir -p ${EXEC_DIR}
+
+# Install g++ and other essential packages
+# needed to install torch
+RUN apt-get update && apt-get install -y \
+    g++ \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+# 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}
+# need this here because poetry install needs the src directory
+COPY src ${EXEC_DIR}/src
+
+# Install needed packages here
+RUN pip3 install --upgrade pip
+RUN pip3 install poetry
+RUN poetry install
+# need to install torch here otherwise get
+#0 2.132 Collecting torch-cluster==1.6.0 (from polus-mm-utils-torchdrug_download==0.1.0)
+#0 2.144   Downloading torch_cluster-1.6.0.tar.gz (43 kB)
+#0 2.150      ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 43.4/43.4 kB 9.0 MB/s eta 0:00:00
+#0 2.164   Preparing metadata (setup.py): started
+#0 2.329   Preparing metadata (setup.py): finished with status 'error'
+#0 2.333   error: subprocess-exited-with-error
+#0 2.333
+#0 2.333   × python setup.py egg_info did not run successfully.
+#0 2.333   │ exit code: 1
+#0 2.333   ╰─> [6 lines of output]
+#0 2.333       Traceback (most recent call last):
+#0 2.333         File "<string>", line 2, in <module>
+#0 2.333         File "<pip-setuptools-caller>", line 34, in <module>
+#0 2.333         File "/tmp/pip-install-fdght_zq/torch-cluster_10a1a1bbf63e4e1ca1e035b9639f5253/setup.py", line 8, in <module>
+#0 2.333           import torch
+#0 2.333       ModuleNotFoundError: No module named 'torch'
+RUN pip3 install torch
+
+RUN pip3 install ${EXEC_DIR} --no-cache-dir

utils/pre-process/data-download/torchdrug_download-tool/README.md

@@ -0,0 +1,28 @@
+# torchdrug (0.1.0)
+
+Access datasets and models from TorchDrug
+
+## Reading inputs/outputs from .cwl files
+This adds inputs/outputs from .cwl files into cookiecutter.json
+`python read_cwl_inputs_outputs.py path_to_cwl_file.cwl`
+
+## Modifying template files
+To dynamically add inputs/outputs from cookiecutter.json to README.MD, __main__.py and plugin_package function
+`python modify_base_template.py`
+
+## Building
+
+To build the Docker image for the conversion plugin, run `./build-docker.sh`.
+
+## Install WIPP Plugin
+
+If WIPP is running, navigate to the plugins page and add a new plugin. Paste the
+contents of `plugin.json` into the pop-up window and submit.
+## Options
+
+This plugin takes 1 input arguments    and 1 output argument:
+
+| Name          | Description             | I/O    | Type   | Default |
+|---------------|-------------------------|--------|--------|---------|
+| dataset | Input dataset to extract | Input | string | string |
+| outdir | Output collection. | Output | collection | collection |

utils/pre-process/data-download/torchdrug_download-tool/VERSION

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

utils/pre-process/data-download/torchdrug_download-tool/ict.yml

@@ -0,0 +1,21 @@
+specVersion: 0.1.0
+name: labshare/torchdrug-download
+version: 0.1.0
+container: polusai/torchdrug-tool:0.1.0
+entrypoint: ""
+title: torchdrug_download
+description: Access datasets and models from TorchDrug
+author: Brandon Walker ([email protected])
+repository: https://github.com/labshare/mmtools
+documentation: https://ncats.nih.gov/preclinical/core/informatics
+citation: ""
+inputs:
+- name: dataset
+  required: true
+  description: Input dataset to extract
+  type: string
+outputs:
+- name: outdir
+  required: false
+  description: Output collection.
+  type: collection

utils/pre-process/data-download/torchdrug_download-tool/pyproject.toml

@@ -0,0 +1,46 @@
+[tool.poetry]
+name = "polus-mm-utils-torchdrug_download"
+version = "0.1.0"
+description = "Access datasets and models from TorchDrug"
+authors = ["Data Scientist <[email protected]>"]
+readme = "README.md"
+packages = [{include = "polus", from = "src"}]
+
+[tool.poetry.dependencies]
+python = ">=3.8,<3.11"
+torch = { version = "1.12.1", source="torch"}
+torchaudio = { version = "0.12.1", source="torch"}
+torchvision = { version = "0.13.1", source="torch"}
+torch-cluster = { version = "1.6.0", source="pyg"}
+torch-scatter = { version = "2.0.9", source="pyg"}
+torchdrug = "0.2.1"
+rdkit = "2023.9.5"
+typer = "^0.7.0"
+
+[[tool.poetry.source]]
+name = "torch"
+url = "https://download.pytorch.org/whl/cu116"
+secondary = true
+
+[[tool.poetry.source]]
+name = "pyg"
+url = "https://data.pyg.org/whl/torch-1.12.1+cu116.html"
+secondary = true
+
+[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/pre-process/data-download/torchdrug_download-tool/src/polus/mm/utils/torchdrug_download/__init__.py

@@ -0,0 +1,7 @@
+"""torchdrug."""
+
+__version__ = "0.1.0"
+
+from polus.mm.utils.torchdrug_download.torchdrug_download import (  # noqa # pylint: disable=unused-import
+    torchdrug_download,
+)

utils/pre-process/data-download/torchdrug_download-tool/src/polus/mm/utils/torchdrug_download/__main__.py

@@ -0,0 +1,152 @@
+"""Package entrypoint for the torchdrug package."""
+
+# Base packages
+import logging
+from enum import Enum
+from os import environ
+from pathlib import Path
+
+import typer
+from polus.mm.utils.torchdrug_download.torchdrug_download import torchdrug_download
+from torchdrug import datasets
+
+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.torchdrug_download.")
+logger.setLevel(POLUS_LOG)
+
+app = typer.Typer(help="torchdrug_download.")
+
+
+class DatabaseEnum(str, Enum):
+    """class DatabaseEnum for the input database to be processed."""
+
+    ClinTox = "ClinTox"
+    PDBBind = "PDBBind"
+    FB15k = "FB15k"
+    FB15k237 = "FB15k237"
+    WN18 = "WN18"
+    WN18RR = "WN18RR"
+    Hetionet = "Hetionet"
+    BACE = "BACE"
+    BBBP = "BBBP"
+    CEP = "CEP"
+    ChEMBLFiltered = "ChEMBLFiltered"
+    Delaney = "Delaney"
+    FreeSolv = "FreeSolv"
+    HIV = "HIV"
+    Lipophilicity = "Lipophilicity"
+    MUV = "MUV"
+    Malaria = "Malaria"
+    OPV = "OPV"
+    QM8 = "QM8"
+    QM9 = "QM9"
+    SIDER = "SIDER"
+    Tox21 = "Tox21"
+    ToxCast = "ToxCast"
+    ZINC250k = "ZINC250k"
+    ZINC2m = "ZINC2m"
+    MOSES = "MOSES"
+    PCQM4M = "PCQM4M"
+    BetaLactamase = "BetaLactamase"
+    Fluorescence = "Fluorescence"
+    Stability = "Stability"
+    Solubility = "Solubility"
+    BinaryLocalization = "BinaryLocalization"
+    SubcellularLocalization = "SubcellularLocalization"
+    EnzymeCommission = "EnzymeCommission"
+    GeneOntology = "GeneOntology"
+    AlphaFoldDB = "AlphaFoldDB"
+    Fold = "Fold"
+    SecondaryStructure = "SecondaryStructure"
+    ProteinNet = "ProteinNet"
+    HumanPPI = "HumanPPI"
+    YeastPPI = "YeastPPI"
+    PPIAffinity = "PPIAffinity"
+    BindingDB = "BindingDB"
+    USPTO50k = "USPTO50k"
+    Cora = "Cora"
+    PubMed = "PubMed"
+
+
+@app.command()
+def main(
+    dataset: DatabaseEnum = typer.Option(
+        ...,
+        "--dataset",
+        help="Input database to be processed.",
+    ),
+    out_dir: Path = typer.Option(
+        ...,
+        "--outdir",
+        help="Output directory.",
+        exists=True,
+        writable=True,
+        file_okay=False,
+        resolve_path=True,
+    ),
+) -> None:
+    """torchdrug_download."""
+    dataset_mapping = {
+        "PDBBind": datasets.PDBBind,
+        "ClinTox": datasets.ClinTox,
+        "FB15k": datasets.FB15k,
+        "FB15k237": datasets.FB15k237,
+        "WN18": datasets.WN18,
+        "WN18RR": datasets.WN18RR,
+        "Hetionet": datasets.Hetionet,
+        "BACE": datasets.BACE,
+        "BBBP": datasets.BBBP,
+        "CEP": datasets.CEP,
+        "ChEMBLFiltered": datasets.ChEMBLFiltered,
+        "Delaney": datasets.Delaney,
+        "FreeSolv": datasets.FreeSolv,
+        "HIV": datasets.HIV,
+        "Lipophilicity": datasets.Lipophilicity,
+        "MUV": datasets.MUV,
+        "Malaria": datasets.Malaria,
+        "OPV": datasets.OPV,
+        "QM8": datasets.QM8,
+        "QM9": datasets.QM9,
+        "SIDER": datasets.SIDER,
+        "Tox21": datasets.Tox21,
+        "ToxCast": datasets.ToxCast,
+        "ZINC250k": datasets.ZINC250k,
+        "ZINC2m": datasets.ZINC2m,
+        "MOSES": datasets.MOSES,
+        "PCQM4M": datasets.PCQM4M,
+        "BetaLactamase": datasets.BetaLactamase,
+        "Fluorescence": datasets.Fluorescence,
+        "Stability": datasets.Stability,
+        "Solubility": datasets.Solubility,
+        "BinaryLocalization": datasets.BinaryLocalization,
+        "SubcellularLocalization": datasets.SubcellularLocalization,
+        "EnzymeCommission": datasets.EnzymeCommission,
+        "GeneOntology": datasets.GeneOntology,
+        "AlphaFoldDB": datasets.AlphaFoldDB,
+        "Fold": datasets.Fold,
+        "SecondaryStructure": datasets.SecondaryStructure,
+        "ProteinNet": datasets.ProteinNet,
+        "HumanPPI": datasets.HumanPPI,
+        "YeastPPI": datasets.YeastPPI,
+        "PPIAffinity": datasets.PPIAffinity,
+        "BindingDB": datasets.BindingDB,
+        "USPTO50k": datasets.USPTO50k,
+        "Cora": datasets.Cora,
+        "PubMed": datasets.PubMed,
+    }
+
+    if dataset not in dataset_mapping:
+        msg = f"Unsupported dataset: {dataset}"
+        raise ValueError(msg)
+
+    logger.info(f"database: {dataset}")
+    logger.info(f"outdir: {out_dir}")
+    torchdrug_download(dataset, out_dir, dataset_mapping)
+
+
+if __name__ == "__main__":
+    app()

utils/pre-process/data-download/torchdrug_download-tool/src/polus/mm/utils/torchdrug_download/torchdrug_download.py

@@ -0,0 +1,19 @@
+"""torchdrug_download."""
+from pathlib import Path
+
+
+def torchdrug_download(dataset: str, outdir: Path, dataset_mapping: dict) -> None:
+    """torchdrug.
+
+    Args:
+        dataset: Input dataset to extract
+        outdir: Output collection.
+        dataset_mapping: Mapping of dataset to class.
+
+    Returns:
+        None
+    """
+    # Create an instance of the selected dataset class
+    selected_dataset_class = dataset_mapping[dataset]
+    # lazy = False causes issues with PDBBind dataset such as invalid sequence
+    dataset = selected_dataset_class(outdir, lazy=True)

utils/pre-process/data-download/torchdrug_download-tool/tests/__init__.py

@@ -0,0 +1 @@
+"""Tests for torchdrug_download."""

utils/pre-process/data-download/torchdrug_download-tool/tests/test_torchdrug.py

@@ -0,0 +1,14 @@
+"""Tests for torchdrug_download."""
+from pathlib import Path
+
+from polus.mm.utils.torchdrug_download.torchdrug_download import torchdrug_download
+from torchdrug import datasets
+
+
+def test_torchdrug_download_check() -> None:
+    """Test torchdrug_download."""
+    dataset = "Tox21"
+    outdir = Path.cwd()
+    dataset_mapping = {"Tox21": datasets.Tox21}
+    torchdrug_download(dataset, outdir, dataset_mapping)
+    assert Path("tox21.csv").exists()