ProTEUS: A mutation-resolved world model for closed-loop protein evolution
Authors: Yikun Zhang, Minghao Guo, Guangxue Xu, Peter Yichen Chen, Wojciech Matusik, Wengong Jin, Jingjing Chai, Kaiyi Jiang
Organizations: Foundry Bioscience Inc. Burlingame, CA, 94010, United States of America · Khoury College of Computer Sciences Northeastern University, Boston, MA, 02115, United States of America · Broad Institute of MIT and Harvard Cambridge, MA, 02142, United States of America · Department of Computer Science Massachusetts Institute of Technology Cambridge, MA, 02139, United States of America · Department of Pathology, Department of Genetics, Stanford University School of Medicine California, 94305, United States of America · Department of Computer Science The University of British Columbia Vancouver, BC Canada V6T 1Z4 · Omenn-Darling Bioengineering Institute Princeton University Princeton, NJ, 08540, United States of America
Protein engineering requires navigating rugged fitness landscapes, where small sequence changes can produce large functional differences, but experimental screening can only sample a small fraction of sequence space. Thus, a central challenge is to efficiently traverse the large combinatorial space of mutations in silico. We introduce ProTEUS, a mutation-resolved world model for closed-loop protein evolution. Pretrained on deep mutational scanning assays, ProTEUS learns a joint representation of sequence, evolutionary, and structural information using MutationFormer, a mutation-biased attention architecture. Variants are represented as states in this joint latent space, and mutations define actions whose functional consequences are predicted. To support exploration of many mutants, we developed a fast, physics-constrained all-atom predictor that utilizes explicit geometric constraint enforcement to achieve >10 fold increase in speed than AlphaFold3 with guaranteed physical validity. Lastly, ProTEUS refines its prediction and understanding of protein activity through closed loop experimental feedback to guide evolution toward a desired phenotype. ProTEUS surpasses established models in both zero-shot and supervised fine-tuning mutation prediction tasks. We experimentally demonstrate its utility in two closed-loop multi-objective engineering campaigns on aldehyde dehydrogenase and levansucrase, yielding variants with >10 fold higher activity than wild type. ProTEUS provides a world-model framework that connects virtual evaluation of mutational outcomes with experimental learning for efficient protein evolution.
Protein mutation effect prediction is fundamental to protein engineering and disease variant interpretation, yet experimentally measured mutation data remain accurate but extremely sparse. To provide scalable supplementary mutation signals, we construct a PDB-wide mutation augmentation dataset that exhaustively enumerates single-site substitutions on experimentally resolved protein structures and aligns mutation signals from physics-based energy models, protein language models, and inverse folding models. Large-scale analysis under a unified mutation preference representation reveals substantial differences in the consistency, concentration, and substitution patterns of mutation distributions across models, indicating that disagreement is pervasive and reflects conflicting inductive biases rather than random noise. Motivated by these observations, we propose an unsupervised multi-source mutation preference distillation framework that learns from relative mutation preferences while explicitly modeling cross-source disagreement. Without using any experimental mutation labels during training, our approach achieves the best overall performance among the evaluated zero-shot baselines and naive multi-source fusion strategies on ProteinGym. We release the dataset and evaluation pipeline to support reproducible studies of protein mutation effects.
Ruihan Guo, Chaoran Cheng, Zhanghan Ni +3
Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign, Urbana, IL, USA · DOE Center for Advanced Bioenergy and Bioproducts, University of Illinois Urbana-Champaign, Urbana, IL, USA
Protein optimization improves an existing protein through targeted mutations, but existing protein language models are poorly suited to it: autoregressive models require full sequence generation, masked language and discrete diffusion models rely on pre-specified mutation locations, and none naturally support insertions and deletions relative to a template. We introduce EvoFlows, a variable-length sequence-to-sequence approach that learns mutational trajectories between evolutionarily related proteins via edit flows, predicting not only which mutation to perform, but also where and how many should occur. Across diverse protein families from UniRef and OAS, EvoFlows generates variants that remain consistent with natural families while exploring farther from the template than leading baselines. In vitro validation of a VHH binder and an enzyme confirms that the large majority of generated variants remain functional and stable without computational downselection.
Nicolas Deutschmann, Constance Ferragu, Jonathan D. Ziegler +2
Predicting whether a protein sequence possesses a biochemical property of interest is important for understanding and designing protein functionality. Modern protein sequence databases provide valuable training data for functional prediction, but they exhibit survivorship bias: natural selection favors variants that support organismal survival while eliminating many others before they can be observed, complicating classifier training. This setting motivates positive-unlabeled (PU) learning, which treats observed functional sequences as positive and unobserved sequences as unlabeled rather than nonfunctional. However, existing protein PU methods do not account for cross-sequence heterogeneity in evolutionary accessibility: sequences one nucleotide mutation away from a common variant arise far more readily than distant ones. We introduce PULSE: PU Learning with Surveillance and Evolution, a framework that trains a probabilistic classifier for a target protein function using an evolution-aware observation likelihood. When considering functionality of proteins with high genomic sequence coverage, PULSE combines a probabilistic classifier that estimates whether an amino acid sequence performs the target function with an evolutionary model that estimates the likelihood that its encoding nucleotide sequences emerge and are detected based on mutational accessibility, parental prevalence, and surveillance e!ciency. By coupling these two components, PULSE treats the absence of an evolutionarily accessible sequence as stronger evidence of non-functionality than the absence of one unlikely to arise. Tested on eleven tasks focusing on multiple Spike protein properties spanning five SARS-CoV-2 variants, PULSE ranks first or second on all of them, and achieves the best overall performance among all methods, including standard PU learning, one-class classification methods, and protein language models.
Smith School of Chemical and Biomolecular Engineering, Cornell University, USA · Center for Applied Mathematics, Cornell University, USA · School of Operations Research and Information Engineering, Cornell University, USA