initial commit

.gitignore

@@ -0,0 +1,211 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# History files
+.Rhistory
+.Rapp.history
+
+# Session Data files
+.RData
+.RDataTmp
+
+# User-specific files
+.Ruserdata
+
+# Example code in package build process
+*-Ex.R
+
+# Output files from R CMD build
+/*.tar.gz
+
+# Output files from R CMD check
+/*.Rcheck/
+
+# RStudio files
+.Rproj.user/
+
+# produced vignettes
+vignettes/*.html
+vignettes/*.pdf
+
+# OAuth2 token, see https://github.com/hadley/httr/releases/tag/v0.3
+.httr-oauth
+
+# knitr and R markdown default cache directories
+*_cache/
+/cache/
+
+# Temporary files created by R markdown
+*.utf8.md
+*.knit.md
+
+# R Environment Variables
+.Renviron
+
+# pkgdown site
+docs/
+
+# translation temp files
+po/*~
+
+# RStudio Connect folder
+rsconnect/
+

Dockerfile

@@ -0,0 +1,61 @@
+FROM ubuntu:18.04
+
+ARG UNAME=dream
+ARG UID=1000
+ARG GID=1000
+ENV CONDA_DIR=/opt/mambaforge
+ENV LANG=C.UTF-8 LC_ALL=C.UTF-8
+ENV PATH=${CONDA_DIR}/bin:${PATH}
+
+RUN rm -rf /tmp/*
+RUN apt-get clean && apt-get update && \ 
+    apt-get install --no-install-recommends --yes \
+    gosu wget bzip2 ca-certificates \
+    git libcairo2 \
+    libxtst6 libxt6 \
+    fonts-texgyre \
+    gsfonts \
+    libblas-dev \
+    libbz2-* \
+    libcurl4 \
+    liblapack-dev \
+    libpcre2* \
+    libjpeg-turbo* \
+    libpangocairo-* \
+    libpng16* \
+    libtiff* \
+    liblzma* \
+    unzip \
+    zip \
+    zlib1g \
+    && apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+RUN wget --no-hsts --quiet https://github.com/conda-forge/miniforge/releases/latest/download/Mambaforge-Linux-x86_64.sh -O /tmp/mambaforge.sh && \
+    /bin/bash /tmp/mambaforge.sh -b -p ${CONDA_DIR} && \
+    rm /tmp/mambaforge.sh && \
+    conda clean --tarballs --index-cache --packages --yes && \
+    find ${CONDA_DIR} -follow -type f -name '*.a' -delete && \
+    find ${CONDA_DIR} -follow -type f -name '*.pyc' -delete && \
+    conda clean --force-pkgs-dirs --all --yes  && \
+    echo ". ${CONDA_DIR}/etc/profile.d/conda.sh && conda activate base" >> /etc/skel/.bashrc && \
+    echo ". ${CONDA_DIR}/etc/profile.d/conda.sh && conda activate base" >> ~/.bashrc
+
+COPY environment.yml /tmp/environment.yml
+COPY Python_package/dist/dream-0.1.dev0-py3-none-any.whl /tmp/dream-0.1.dev0-py3-none-any.whl
+COPY R_package/DREAM_0.1.0.tar.gz /tmp/DREAM_0.1.0.tar.gz
+
+SHELL ["/bin/bash", "--login", "-c"]
+RUN mamba env update -n base -f /tmp/environment.yml
+RUN mamba run -n base R -e "install.packages('TopKLists', dependencies=FALSE, repos='http://cran.us.r-project.org')"
+RUN mamba run -n base R -e "devtools::install_github('filosi/nettools', dependencies=FALSE, upgrade_dependencies=FALSE)"
+RUN mamba run -n base R -e "install.packages('IRkernel', dependencies=FALSE, repos='http://cran.us.r-project.org'); IRkernel::installspec(user=FALSE)"
+RUN mamba run -n base pip install /tmp/dream-0.1.dev0-py3-none-any.whl
+RUN mamba run -n base R CMD INSTALL /tmp/DREAM_0.1.0.tar.gz
+
+# make sure entrypoint.sh has +x flag
+COPY entrypoint.sh /entrypoint.sh
+RUN mkdir -p /workspace && chmod -R 777 /workspace
+WORKDIR /workspace
+ENTRYPOINT [ "/entrypoint.sh" ]
+CMD [ "mamba", "run", "--no-capture-output", "-n", "base", "jupyter", "lab", "--ip='*'", "--NotebookApp.token=''", "--NotebookApp.password=''"]

Python_package/dream/api.py

@@ -0,0 +1,109 @@
+import io
+import json
+import pandas as pd
+import numpy as np
+from flask import Flask, jsonify, request
+from dream.chemicals import pairwise_fingerprint_similarity
+from dream.chemicals import pairwise_mcs_similarity
+
+
+from dream.genetic_algorithm import genetic_algorithm
+
+app = Flask(__name__)
+
+@app.route("/chemicals_distance", methods=["GET", "POST"])
+def chemicals_distance():
+    parameters = request.args.to_dict(flat=True)
+    method = parameters.pop("method", "fingerprint")
+    data = request.get_json()
+    smiles_dict = data["smiles"]
+    rev_smiles_dict = {v:k for k,v in smiles_dict.items()}
+    smiles = pd.Series(smiles_dict)
+
+    try:
+        if method == "mcs":
+            only_heavy_atoms = (parameters.pop("only_heavy_atoms", "TRUE") == "TRUE")
+            similarities = pairwise_mcs_similarity(
+                smiles, only_heavy_atoms=only_heavy_atoms
+            )
+        elif method == "fingerprint":
+            radius = int(parameters.pop("radius", 4))
+            n_bits = int(parameters.pop("n_bits", 2048))
+            similarities = pairwise_fingerprint_similarity(
+                smiles, radius=radius, n_bits=n_bits
+            )
+        else:
+            # http 400 error code: bad request: https://http.cat/400
+            return jsonify({"error": "Unrecognized method: " + method}), 400
+    except Exception as err:
+        return jsonify({"error": str(err)}), 400
+    # negative log transformation converts the similarity to a distance
+    distances = [(rev_smiles_dict[mol1], rev_smiles_dict[mol2], -np.log(max(1e-5, sim))) for (mol1, mol2, sim) in similarities]
+    return jsonify({"distances": distances})
+
+@app.route("/genetic_algorithm", methods=["GET", "POST"])
+def genetic_algorithm_api():
+    parameters = request.args.to_dict(flat=True)
+
+    population_size = int(parameters.pop("population_size", 100))
+    n_offsprings = int(parameters.pop("n_offsprings", 20))
+    attribute_init_prob = float(parameters.pop("attribute_init_prob", 0.3))
+    attribute_mutation_prob = float(parameters.pop("attribute_mutation_prob", 0.1))
+    crossover_prob = float(parameters.pop("crossover_prob", 0.7))
+    mutation_prob = float(parameters.pop("mutation_prob", 0.3))
+    n_generations = int(parameters.pop("n_generations", 2500))
+
+    data = request.get_json()
+    smiles_distances = data.pop("smiles_distances", None)
+    moa_distances = data.pop("moa_distances", None)
+    graph_distances = data.pop("graph_distances", None)
+    ppi_network = data.pop("ppi_network", None)
+    graph_rank = data.pop("graph_rank", None)
+    drug_targets = data.pop("drug_targets", None)
+
+    try:
+        check_not_none(
+            smiles_distances=smiles_distances,
+            moa_distances=moa_distances,
+            graph_distances=graph_distances,
+            ppi_network=ppi_network,
+            graph_rank=graph_rank,
+            drug_targets=drug_targets
+        )
+    except ValueError as e:
+        return jsonify(
+            {"error": "{} is missing or not well formatted".format(str(e))}
+        )
+
+    drug_names, population, logbook, hall_of_fame = genetic_algorithm(
+        smiles_distances=smiles_distances,
+        moa_distances=moa_distances,
+        graph_distances=graph_distances,
+        ppi_network=ppi_network,
+        graph_rank=graph_rank,
+        drug_targets=drug_targets,
+        population_size=population_size,
+        n_offsprings=n_offsprings,
+        attribute_init_prob=attribute_init_prob,
+        attribute_mutation_prob=attribute_mutation_prob,
+        crossover_prob=crossover_prob,
+        mutation_prob=mutation_prob,
+        n_generations=n_generations,
+        verbose=False,
+    )
+
+    return jsonify({
+        "drug_names": drug_names,
+        "population": population,
+        "logbook": logbook,
+        "hall_of_fame":hall_of_fame,
+    })
+
+def check_not_none(**kwargs):
+    for (k, v) in kwargs.items():
+        if v is None:
+            raise ValueError(k)
+
+if __name__ == '__main__':
+    app.debug = True
+    app.run()