moses

Deep learning library for Chemistry based on Tensorflow

Directed message passing neural networks for property prediction of molecules and reactions with uncertainty and interpretation.

Provides functionality for producing geometric representations of protein and RNA structures, and biological interaction networks.

A Deep Learning Library for Compound and Protein Modeling DTI, Drug Property, PPI, DDI, Protein Function Prediction.

E(3)-equivariant neural network interatomic potentials achieving DFT accuracy with up to 1000× less training data than invariant models, foundational architecture behind MACE and Allegro (Harvard, MIT, Nature Communications 2022)

TransformerEngine-accelerated checkpoints and training recipes for scaling biological foundation models (ESM-2, AMPLIFY, Geneformer, CodonFM) from single-GPU prototyping to multi-node FSDP training with FP8/MXFP8/NVFP4 precision, compatible with PyTorch, HF Accelerate, and PyTorch Lightning, plus sparse-autoencoder interpretability tools for biological foundation models (851+ stars, 2026)