Add Interface for OptiSim Algorithm

.github/workflows/interface_auto.yml

@@ -0,0 +1,77 @@
+name: Deployment on DockerHub and Hugging Face
+
+# Trigger the workflow on push and pull request events to the 'main' or 'master' branch
+on:
+  push:
+    branches:
+      - "master"
+      - "main"
+      - "optisim-interface"
+  pull_request:
+    branches:
+      - "master"
+      - "main"
+
+jobs:
+  build-and-deploy:
+    # Run the job on the latest Ubuntu runner
+    runs-on: ubuntu-latest
+
+    steps:
+    # Step 1: Check out the latest code from the repository
+    - name: Checkout code
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        lfs: true
+
+    # Step 2: Set up Git LFS
+    - name: Set up Git LFS
+      run: |
+        git lfs install
+        git lfs pull
+
+    # Step 3: Remove binary files from git history
+    - name: Remove binary files from git history
+      run: |
+        git filter-branch --force --index-filter \
+          "git rm --cached --ignore-unmatch DiverseSelector/test/test2/BBB_SECFP6_1024.xlsx DiverseSelector/test/test2/BBB_SECFP6_2048.xlsx" \
+          --prune-empty --tag-name-filter cat -- --all
+
+    # Step 4: Set up Python environment with version 3.11
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: 3.11
+
+    # Step 5: Install the required dependencies
+    - name: Install dependencies
+      run: |
+        pip install -r requirements.txt
+
+    # Step 6: Build the Docker image to Docker Hub
+    - name: Build Docker image
+      run: |
+        docker build . -t jackyzzz076/selector-deployment:latest
+
+    # Step 7: Push the Docker image to Docker Hub
+    - name: Push Docker image
+      run: |
+        docker login -u jackyzzz076 -p ${{ secrets.DOCKERHUB_TOKEN }}
+        docker push jackyzzz076/selector-deployment:latest
+
+    # Step 8: Replace the README.md file for Hugging Face
+    - name: Replace README for Hugging Face
+      run: |
+        mv README_hf.md README.md
+        git config --global user.name "github-actions[bot]"
+        git config --global user.email "[email protected]"
+        git add README.md
+        git commit -m "Replace README.md with README_hf.md for Hugging Face"
+
+    # Step 9: Push the app to Hugging Face
+    - name: Push to Hugging Face
+      env:
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+      run: |
+        git push https://JackyZzZzZ:[email protected]/spaces/JackyZzZzZ/selector optisim-interface:main --force

Dockerfile

@@ -0,0 +1,34 @@
+# Use the official image as a parent image
+FROM python:3.11-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Install system dependencies required for building packages
+RUN apt-get update && \
+    apt-get install -y build-essential && \
+    apt-get clean
+
+# Copy the requirements file into the container
+COPY requirements.txt requirements.txt
+COPY requirements_dev.txt requirements_dev.txt
+
+# Upgrade pip, setuptools, and wheel
+RUN pip install --upgrade pip setuptools wheel
+
+# Install the dependencies using --use-pep517
+RUN pip install --use-pep517 --no-cache-dir -r requirements.txt
+RUN pip install --use-pep517 --no-cache-dir -r requirements_dev.txt
+RUN pip install --use-pep517 --no-cache-dir streamlit
+
+# Copy the rest of the application code
+COPY . .
+
+# Install the Selector package using PEP 517 standards-based tools
+RUN pip install --use-pep517 .
+
+# Expose the port the app runs on
+EXPOSE 8501
+
+# Command to run the app
+CMD ["streamlit", "run", "streamlit_app/app.py", "--server.enableXsrfProtection=false"]

README_hf.md

@@ -0,0 +1,8 @@
+---
+title: QC-Selector
+emoji: 🐳
+colorFrom: purple
+colorTo: gray
+sdk: docker
+app_port: 8501
+---

streamlit_app/app.py

@@ -0,0 +1,99 @@
+# The Selector library provides a set of tools for selecting a
+# subset of the dataset and computing diversity.
+#
+# Copyright (C) 2023 The QC-Devs Community
+#
+# This file is part of Selector.
+#
+# Selector is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version 3
+# of the License, or (at your option) any later version.
+#
+# Selector is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, see <http://www.gnu.org/licenses/>
+#
+# --
+
+import streamlit as st
+import os
+
+
+# Get the current directory path
+current_dir = os.path.dirname(os.path.abspath(__file__))
+
+# Construct the path to the assets directory
+assets_dir = os.path.join(current_dir, "assets")
+
+# Set page configuration
+st.set_page_config(
+    page_title = "Selector",
+    page_icon = os.path.join(assets_dir, "QC-Devs.png"),
+)
+
+st.image(os.path.join(assets_dir, "selector_logo.png"))
+
+st.write("# Welcome to Selector! 👋")
+
+st.sidebar.success("Select an algorithm to get started.")
+
+st.info("👈 Select an algorithm from the sidebar to see some examples of what Selector can do!")
+
+st.markdown(
+    """
+    [selector](https://github.com/theochem/Selector) is a free, open-source, and cross-platform
+    Python library designed to help you effortlessly identify the most diverse subset of molecules
+    from your dataset. 
+    Please use the following citation in any publication using selector library:
+
+    **“Selector: A Generic Python Package for Subset Selection”**, Fanwang Meng, Alireza Tehrani, 
+    Valerii Chuiko, Abigail Broscius, Abdul, Hassan, Maximilian van Zyl, Marco Martínez González, 
+    Yang, Ramón Alain Miranda-Quintana, Paul W. Ayers, and Farnaz Heidar-Zadeh”
+
+    The selector source code is hosted on [GitHub](https://github.com/theochem/Selector) 
+    and is released under the [GNU General Public License v3.0](https://github.com/theochem/Selector/blob/main/LICENSE). 
+    We welcome any contributions to the selector library in accordance with our Code of Conduct; 
+    please see our [Contributing Guidelines](https://qcdevs.org/guidelines/qcdevs_code_of_conduct/).
+    Please report any issues you encounter while using 
+    selector library on [GitHub Issues](https://github.com/theochem/Selector/issues). 
+    For further information and inquiries please contact us at [email protected].
+
+    ### Why QC-Selector?
+    In the world of chemistry, selecting the right subset of molecules is critical for a wide
+    range of applications, including drug discovery, materials science, and molecular optimization. 
+    QC-Selector offers a cutting-edge solution to streamline this process, empowering researchers, 
+    scientists, and developers to make smarter decisions faster.
+
+    ### Key Features
+    1. Import Your Dataset: Simply import your molecule dataset in various file formats, including SDF, SMILES, and InChi, to get started.
+
+    2. Define Selection Criteria: Specify the desired level of diversity and other relevant parameters to tailor the subset selection to your unique requirements.
+
+    3. Run the Analysis: Let QC-Selector’s powerful algorithms process your dataset and efficiently select the most diverse molecules.
+
+    4. Export: Explore the diverse subset and export the results for further analysis and integration into your projects.
+"""
+)
+
+st.sidebar.title("About QC-Devs")
+
+st.sidebar.info("QC-Devs develops various free, open-source, and cross-platform libraries for scientific computing, especially theoretical and computational chemistry. Our goal is to make programming accessible to chemists and promote precepts of sustainable software development. For further information and inquiries please contact us at [email protected].")
+
+# Add icons to the sidebar
+st.sidebar.markdown(
+    """
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/4.7.0/css/font-awesome.min.css">
+    <div style="text-align: center;">
+        <a href="https://qcdevs.org/" target="_blank"><i class="fa fa-home" style="font-size:24px"></i> WEBSITE</a><br>
+        <a href="mailto:[email protected]"><i class="fa fa-envelope" style="font-size:24px"></i> EMAIL</a><br>
+        <a href="https://github.com/theochem" target="_blank"><i class="fa fa-github" style="font-size:24px"></i> GITHUB</a><br>
+        © 2024 QC-Devs. All rights reserved.
+    </div>
+    """,
+    unsafe_allow_html=True
+)

streamlit_app/pages/page_DISE.py

@@ -0,0 +1,112 @@
+# The Selector library provides a set of tools for selecting a
+# subset of the dataset and computing diversity.
+#
+# Copyright (C) 2023 The QC-Devs Community
+#
+# This file is part of Selector.
+#
+# Selector is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version 3
+# of the License, or (at your option) any later version.
+#
+# Selector is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, see <http://www.gnu.org/licenses/>
+#
+# --
+
+import streamlit as st
+import sys
+import os
+
+from selector.methods.distance import DISE
+
+# Add the streamlit_app directory to the Python path
+current_dir = os.path.dirname(os.path.abspath(__file__))
+parent_dir = os.path.join(current_dir, "..")
+sys.path.append(parent_dir)
+
+from utils import *
+
+# Set page configuration
+st.set_page_config(
+    page_title = "DISE",
+    page_icon = os.path.join(parent_dir, "assets" , "QC-Devs.png"),
+)
+
+st.title("Directed Sphere Exclusion (DISE)")
+
+
+description = """
+    In a nutshell, this algorithm iteratively excludes any sample within a given radius from
+    any already selected sample. The radius of the exclusion sphere is an adjustable parameter.
+    Compared to Sphere Exclusion algorithm, the Directed Sphere Exclusion algorithm achieves a
+    more evenly distributed subset selection by abandoning the random selection approach and
+    instead imposing a directed selection.
+
+    Reference sample is chosen based on the `ref_index`, which is excluded from the selected
+    subset. All samples are sorted (ascending order) based on their Minkowski p-norm distance
+    from the reference sample. Looping through sorted samples, the sample is selected if it is
+    not already excluded. If selected, all its neighboring samples within a sphere of radius r
+    (i.e., exclusion sphere) are excluded from being selected. When the selected number of points
+    is greater than specified subset `size`, the selection process terminates. The `r0` is used
+    as the initial radius of exclusion sphere, however, it is optimized to select the desired
+    number of samples.
+    """
+
+references = "Gobbi, A., and Lee, M.-L. (2002). DISE: directed sphere exclusion."\
+             "Journal of Chemical Information and Computer Sciences,"\
+             "43(1), 317–323. https://doi.org/10.1021/ci025554v"
+
+display_sidebar_info("Directed Sphere Exclusion (DISE)", description, references)
+
+# File uploader for feature matrix or distance matrix (required)
+matrix_file = st.file_uploader("Upload a feature matrix or distance matrix (required)",
+                               type=["csv", "xlsx", "npz", "npy"], key="matrix_file", on_change=clear_results)
+
+# Clear selected indices if a new matrix file is uploaded
+if matrix_file is None:
+    clear_results()
+# Load data from matrix file
+else:
+    matrix = load_matrix(matrix_file)
+    num_points = st.number_input("Number of points to select", min_value = 1, step = 1,
+                                 key = "num_points", on_change=clear_results)
+    label_file = st.file_uploader("Upload a cluster label list (optional)", type = ["csv", "xlsx"],
+                                  key = "label_file", on_change=clear_results)
+    labels = load_labels(label_file) if label_file else None
+
+    # Parameters for Directed Sphere Exclusion
+    st.info("The parameters below are optional. If not specified, default values will be used.")
+
+    r0 = st.number_input("Initial guess for radius of exclusion sphere (r0)", value=None, step=0.1,
+                         on_change=clear_results)
+    ref_index = st.number_input("Reference index (ref_index)", value=0, step=1, on_change=clear_results)
+    tol = st.number_input("Percentage tolerance of sample size error (tol)", value=0.05, step=0.05,
+                          on_change=clear_results)
+    n_iter = st.number_input("Number of iterations for optimizing the radius of exclusion sphere (n_iter)",
+                             value=10, step=10, on_change=clear_results)
+    p = st.number_input("Minkowski p-norm distance (p)", value=2.0, step=1.0, on_change=clear_results)
+    eps = st.number_input("Approximate nearest neighbor search parameter (eps)", value=0.0, step=0.1,
+                          on_change=clear_results)
+
+    if st.button("Run DISE Algorithm"):
+        selector = DISE(r0=r0, ref_index=ref_index, tol=tol, n_iter=n_iter, p=p, eps=eps)
+        selected_ids = run_algorithm(selector, matrix, num_points, labels)
+        st.session_state['selector'] = selector
+        st.session_state['selected_ids'] = selected_ids
+
+# Check if the selected indices are stored in the session state
+if 'selected_ids' in st.session_state and matrix_file is not None:
+    selected_ids = st.session_state['selected_ids']
+    st.write("Selected indices:", selected_ids)
+
+    if 'selector' in st.session_state:
+        st.write("Radius of the exclusion sphere:", st.session_state['selector'].r)
+
+    export_results(selected_ids)