GitHub - OpenADMET/openadmet-models: Machine learning workflows for the OpenADMET project

Abstraction: Open-source ML framework for drug ADMET property prediction tasks

Key points:

• openadmet-models provides ML architectures and training routines for ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) prediction in drug discovery
• Includes traditional ML methods, deep learning models, and active learning workflows in a single flexible library
• Designed for rapid experimentation and prototyping; intentionally not exhaustive of every SOTA architecture
• Hosted by the Open Molecular Software Foundation (OMSF) under the MIT license
• Installable via mamba/conda with GPU-compatible environment option; tutorials available on Google Colab

Connections: Openadmet · Github · Machine Learning · Drug Discovery · Active Learning

Source: https://github.com/OpenADMET/openadmet-models