InterPLM (Nature Methods 2025)
github.com/elanapearl/interplmDiscovering interpretable features in protein language models via sparse autoencoders, enabling mechanistic understanding of PLM representations for protein engineering and design (288+ stars, MIT License)
Sourced from
- Awesome AI for Science — github.com/elanapearl/interplm
- GitHub — github.com/elanapearl/interplm
Related resources
Protein structure prediction
AlphaFold 3 inference pipeline for unified biomolecular structure prediction of proteins, nucleic acids, small molecules, ions, and post-translational modifications (Google DeepMind, Nature 2024)
Deep learning library for Chemistry based on Tensorflow
Protein structure prediction from ESM models
First fully open-source model achieving AlphaFold3-level accuracy with 1000x faster binding affinity prediction (MIT)