ProtRL: Open-Source Framework Fine-Tunes Protein Language Models with RL from a CSV

ferruz_noelia · x · 2026-09-01

AI4PD Lab released ProtRL, an open-source framework for fine-tuning autoregressive protein language models (pLMs) with reinforcement learning, accompanying the preprint Guiding Generative Protein Language Models with Reinforcement Learning.

• Supports GRPO, Weighted DPO (with optional IRPO regularisation), and REINFORCE (with optional entropy bonus)
• Users upload a CSV of their experimental data to fine-tune, apply RL, and generate new protein sequences; interactive notebooks and a local tiny-model demo are included
• 115 stars on GitHub, with benchmarking, examples, and training/generation scripts

Original post →

More from Research

• SafeAtlas-VL: Graded Multimodal Safety Dataset and Guard Models Hit SOTA — SJTU · 2026-09-01
• Evaluating the Hidden Costs of Personalization in LLMs via PRISK — illinois · 2026-09-01
• Chat-Edit-3D++: LLM-Driven Conversational Editing of 3D and 4D Scenes — stepfun-ai · 2026-09-01
• "The Elegance of XORshift Generators" Ranks 4th in SoME5 — AlanZucconi · 2026-09-01
• Negative Reinforcement vs. Punishment: Scott Alexander on AI Alignment and Sentience — davidmanheim · 2026-09-01
• New Book 'Elements of fMRI' Released with 42 Interactive Tutorials — bttyeo · 2026-09-01

Research channel →