Generative modeling of intrinsically disordered protein regions by reinforcing sparse autoencoder features

Jason X. Liu, Sebastian Ibarraran, Frank Hu, Soojung Yang, Xinyu A. Feng et al.|October 1, 2026arXiv

Key Takeaway

Sparse autoencoder features combined with reinforcement learning enable interpretable, composable control over protein sequence generation—activating 3.75x more targeted features than previous steering approaches and improving predicted biological function.

Summary

IDiom is a specialized protein language model trained on 54 million intrinsically disordered protein regions (IDRs) that can generate functional sequences with precise control over biological features.

training applications reasoning

Key Terms

sparse-autoencoder reinforcement-learning language-model protein-language-model activation-steering