Hugging Face's logo

Spaces:
bcadkins01
/
beta_lactam_demo
Sleeping

App Files Community
beta_lactam_demo / README.md
bcadkins01's picture
bcadkins01
Update README.md
13cc203 verified
preview code
|
raw
history blame
3.85 kB
metadata
title: Beta Lactam Demo
emoji: 📚
colorFrom: gray
colorTo: red
sdk: streamlit
sdk_version: 1.39.0
app_file: app.py
pinned: false
license: mit
short_description: app to generate and view beta-lactam molecules

Beta-Lactam Molecule Generator and Viewer

Overview

This application demonstrates a drug discovery pipeline that allows users to:

  • Generate novel beta-lactam molecules using a generative AI model.
  • View the generated molecules with options to display and copy SMILES or SAFE strings.
  • Predict ADMET properties for the generated molecules using ADMET-AI.

Features

  • Molecule Generation:
    • Generates up to 5 beta-lactam molecules at a time.
    • Users can adjust the creativity (temperature) of the generation process.
    • Generated molecules are named 'Mol01' to 'Mol05'.
  • Molecule Viewing:
    • Displays molecule structures using Streamlit.
    • Option to view molecules as SMILES or SAFE strings.
    • Provides copy-to-clipboard functionality for molecule strings.
  • ADMET Property Prediction:
    • Integrates ADMET-AI to predict properties such as absorption, distribution, metabolism, excretion, and toxicity.
    • Displays predicted properties alongside each molecule.

How to Use the App

  1. Set Generation Parameters:
  • Use the sidebar to adjust the creativity (temperature) slider.
  • Select the number of molecules to generate (maximum of 5).
  1. Choose String Format:
  • Select whether to display molecule strings as SMILES or SAFE.
  1. Generate Molecules:
  • Click the 'Generate Molecules' button.
  • Generated molecules will appear with their structures, strings, and predicted ADMET properties.
  1. Copy Molecule Strings:
  • Use the 'Copy' button under each molecule to copy the SMILES or SAFE string to your clipboard.

Technical Details

  • Generative Model: Uses the model: 'seyonec/PubChem10M_SMILES_BPE_450k' fine-tuned on beta-lactam structures.
  • ADMET Predictions: Uses the ADMET-AI library to predict molecular properties.
  • Visualization: Employs RDKit and SAFE encoding for molecule rendering.
  • Frameworks and Libraries:
    • Streamlit for the web interface.
    • Transformers library for model loading and generation.
    • RDKit for cheminformatics.

The application is intended for demonstration purposes and may require adjustments for production use.

License

This project is licensed under the terms of the MIT license.

Attributions and Acknowledgments

ChEMBL Database:

This project utilizes data from the ChEMBL Database, licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).

Please cite: Zdrazil B, Felix E, Hunter F, et al. The ChEMBL Database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods. Nucleic Acids Research. 2024;52(D1) . doi:10.1093/nar/gkad1004

SAFE Encoding

This project uses the SAFE Encoding framework, licensed under the Apache License 2.0.

Please cite: Noutahi E, Gabellini C, Craig M, Lim JS, Tossou P. Gotta be SAFE: A New Framework for Molecular Design. arXiv preprint arXiv:2310.10773, 2023. ADMET-AI

This project utilizes the ADMET-AI platform for predicting ADMET properties. ADMET-AI is licensed under the MIT License.

Please cite: Swanson K, Walther P, Leitz J, et al. ADMET-AI: A machine learning ADMET platform for evaluation of large-scale chemical libraries. bioRxiv. 2023. doi:10.1101/2023.12.28.573531 RDKit

This project uses RDKit: Open-source cheminformatics software.

Please cite: RDKit: Open-source cheminformatics. https://www.rdkit.org DOI for the version used: [Insert the specific DOI corresponding to your RDKit version from Zenodo] Original Model This project fine-tunes an original model using data from the ChEMBL Database.

[Include any necessary details about the original model, its source, and licensing information.]