ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning

• URL: http://arxiv.org/abs/2506.07459v2
• Date: Tue, 10 Jun 2025 18:30:51 GMT
• Title: ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning
• Authors: Ziwen Wang, Jiajun Fan, Ruihan Guo, Thao Nguyen, Heng Ji, Ge Liu,
• Abstract summary: We present ProteinZero, a novel framework that enables computationally scalable, automated, and continuous self-improvement of the inverse folding model.<n>ProteinZero substantially outperforms existing methods across every key metric in protein design.<n> Notably, the entire RL run on CATH-4.3 can be done with a single 8 X GPU node in under 3 days, including reward.
• Score: 49.2607661375311
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Protein generative models have shown remarkable promise in protein design but still face limitations in success rate, due to the scarcity of high-quality protein datasets for supervised pretraining. We present ProteinZero, a novel framework that enables scalable, automated, and continuous self-improvement of the inverse folding model through online reinforcement learning. To achieve computationally tractable online feedback, we introduce efficient proxy reward models based on ESM-fold and a novel rapid ddG predictor that significantly accelerates evaluation speed. ProteinZero employs a general RL framework balancing multi-reward maximization, KL-divergence from a reference model, and a novel protein-embedding level diversity regularization that prevents mode collapse while promoting higher sequence diversity. Through extensive experiments, we demonstrate that ProteinZero substantially outperforms existing methods across every key metric in protein design, achieving significant improvements in structural accuracy, designability, thermodynamic stability, and sequence diversity. Most impressively, ProteinZero reduces design failure rates by approximately 36% - 48% compared to widely-used methods like ProteinMPNN, ESM-IF and InstructPLM, consistently achieving success rates exceeding 90% across diverse and complex protein folds. Notably, the entire RL run on CATH-4.3 can be done with a single 8 X GPU node in under 3 days, including reward computation. Our work establishes a new paradigm for protein design where models evolve continuously from their own generated outputs, opening new possibilities for exploring the vast protein design space.

Related papers

• AMix-1: A Pathway to Test-Time Scalable Protein Foundation Model [92.51919604882984]
  We introduce AMix-1, a powerful protein foundation model built on Flow Bayesian Networks.<n>AMix-1 is empowered by a systematic training methodology, encompassing pretraining scaling laws, emergent capability analysis, in-context learning mechanism, and test-time scaling algorithm.<n>Building on this foundation, we devise a multiple sequence alignment (MSA)-based in-context learning strategy to unify protein design into a general framework.
  arXiv  Detail & Related papers  (2025-07-11T17:02:25Z)
• The Dance of Atoms-De Novo Protein Design with Diffusion Model [9.521115574728915]
  De novo protein design refers to creating proteins with specific structures and functions that do not naturally exist.<n>In recent years, the accumulation of high-quality protein structure and sequence data and technological advancements have paved the way for the successful application of generative artificial intelligence (AI) models in protein design.<n>Among various generative AI models, diffusion models have yielded the most promising results in protein design.
  arXiv  Detail & Related papers  (2025-04-23T07:45:00Z)
• Proteina: Scaling Flow-based Protein Structure Generative Models [36.49892014289605]
  Proteina is a large-scale flow-based protein backbone generator that relies on hierarchical fold class labels for conditioning.<n>Proteina achieves state-of-the-art performance on de novo protein backbone design and produces diverse and designable proteins at unprecedented length, up to 800 residues.
  arXiv  Detail & Related papers  (2025-03-02T03:21:49Z)
• SFM-Protein: Integrative Co-evolutionary Pre-training for Advanced Protein Sequence Representation [97.99658944212675]
  We introduce a novel pre-training strategy for protein foundation models. It emphasizes the interactions among amino acid residues to enhance the extraction of both short-range and long-range co-evolutionary features. Trained on a large-scale protein sequence dataset, our model demonstrates superior generalization ability.
  arXiv  Detail & Related papers  (2024-10-31T15:22:03Z)
• Model-based reinforcement learning for protein backbone design [1.7383284836821535]
  We propose the use of AlphaZero to generate protein backbones, meeting shape and structural scoring requirements. We extend an existing Monte Carlo tree search (MCTS) framework by incorporating a novel threshold-based reward and secondary objectives. AlphaZero consistently surpasses baseline MCTS by more than 100% in top-down protein design tasks.
  arXiv  Detail & Related papers  (2024-05-03T10:24:33Z)
• Efficiently Predicting Mutational Effect on Homologous Proteins by Evolution Encoding [7.067145619709089]
  EvolMPNN is an efficient model to learn evolution-aware protein embeddings. Our model shows up to 6.4% better than state-of-the-art methods and attains 36X inference speedup.
  arXiv  Detail & Related papers  (2024-02-20T23:06:21Z)
• xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein [74.64101864289572]
  We propose a unified protein language model, xTrimoPGLM, to address protein understanding and generation tasks simultaneously.<n>xTrimoPGLM significantly outperforms other advanced baselines in 18 protein understanding benchmarks across four categories.<n>It can also generate de novo protein sequences following the principles of natural ones, and can perform programmable generation after supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-01-11T15:03:17Z)
• Structure-informed Language Models Are Protein Designers [69.70134899296912]
  We present LM-Design, a generic approach to reprogramming sequence-based protein language models (pLMs) We conduct a structural surgery on pLMs, where a lightweight structural adapter is implanted into pLMs and endows it with structural awareness. Experiments show that our approach outperforms the state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2023-02-03T10:49:52Z)
• Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMC [1.0499611180329804]
  A long-standing goal of machine-learning-based protein engineering is to accelerate the discovery of novel mutations. We introduce a sampling framework for evolving proteins in silico that supports mixing and matching a variety of unsupervised models. By composing these models, we aim to improve our ability to evaluate unseen mutations and constrain search to regions of sequence space likely to contain functional proteins.
  arXiv  Detail & Related papers  (2022-12-20T00:26:23Z)
• Learning Geometrically Disentangled Representations of Protein Folding Simulations [72.03095377508856]
  This work focuses on learning a generative neural network on a structural ensemble of a drug-target protein. Model tasks involve characterizing the distinct structural fluctuations of the protein bound to various drug molecules. Results show that our geometric learning-based method enjoys both accuracy and efficiency for generating complex structural variations.
  arXiv  Detail & Related papers  (2022-05-20T19:38:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.