Rank-and-Reason: Multi-Agent Collaboration Accelerates Zero-Shot Protein Mutation Prediction

• URL: http://arxiv.org/abs/2602.00197v2
• Date: Tue, 03 Feb 2026 04:26:39 GMT
• Title: Rank-and-Reason: Multi-Agent Collaboration Accelerates Zero-Shot Protein Mutation Prediction
• Abstract summary: We propose Rank-and-Reason (VenusRAR), a two-stage agentic framework to automate the wet-lab validation process.<n>In the Rank-Stage, a Computational Expert and Virtual Biologist aggregate a context-aware multi-modal ensemble, establishing a new Spearman correlation record of 0.551 (vs. 0.518) on ProteinGym.<n>In the Reason-Stage, an agentic Expert Panel employs chain-of-thought reasoning to audit candidates against geometric and structural constraints, improving the Top-5 Hit Rate by up to 367% on ProteinGym-DMS99.
• Score: 20.82228986381723
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Zero-shot mutation prediction is vital for low-resource protein engineering, yet existing protein language models (PLMs) often yield statistically confident results that ignore fundamental biophysical constraints. Currently, selecting candidates for wet-lab validation relies on manual expert auditing of PLM outputs, a process that is inefficient, subjective, and highly dependent on domain expertise. To address this, we propose Rank-and-Reason (VenusRAR), a two-stage agentic framework to automate this workflow and maximize expected wet-lab fitness. In the Rank-Stage, a Computational Expert and Virtual Biologist aggregate a context-aware multi-modal ensemble, establishing a new Spearman correlation record of 0.551 (vs. 0.518) on ProteinGym. In the Reason-Stage, an agentic Expert Panel employs chain-of-thought reasoning to audit candidates against geometric and structural constraints, improving the Top-5 Hit Rate by up to 367% on ProteinGym-DMS99. The wet-lab validation on Cas12i3 nuclease further confirms the framework's efficacy, achieving a 46.7% positive rate and identifying two novel mutants with 4.23-fold and 5.05-fold activity improvements. Code and datasets are released on GitHub (https://github.com/ai4protein/VenusRAR/).

Related papers

• Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization [85.4863852505905]
  We introduce unsupervised reward optimization of protein language models (PLMs)<n>Our key insight is that task-agnostic rewards, which combine intrinsic model uncertainty with semantic consistency informed by protein representation models, exhibit strong correlation with controllability measures across base models and temperature regimes.<n>Our framework provides a scalable pathway toward controllable biomolecular design in settings where labeled preferences or experimental feedback are scarce or unavailable.
  arXiv  Detail & Related papers  (2026-06-17T11:42:01Z)
• Decomposing the Generalization Gap in PROTAC Activity Prediction: Variance Attribution and the Inter-Laboratory Ceiling [11.472625518731173]
  We frame this as an evaluation-science question and use targeted protein degradation as the empirical test bed.<n>We release PROTAC-Bench (10,748 measurements, 173 targets, 65 LOTO folds), the variance-deduplication framework, the per-target calibration protocol, and the evaluation code.
  arXiv  Detail & Related papers  (2026-05-12T08:35:02Z)
• ProtSent: Protein Sentence Transformers [6.657830371527077]
  Protein language models (pLMs) produce per-residue representations that capture evolutionary and structural information.<n>We present Protein Sentence Transformers (ProtSent), a contrastive fine-tuning framework for adapting PLMs into general-purpose embedding models.
  arXiv  Detail & Related papers  (2026-05-07T18:33:49Z)
• OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation [57.505743202759646]
  OccuBench is a benchmark covering 100 real-world professional task scenarios across 10 industry categories and 65 specialized domains.<n>Our multi-agent synthesis pipeline automatically produces evaluation instances with guaranteed solvability, calibrated difficulty, and document-grounded diversity.
  arXiv  Detail & Related papers  (2026-04-13T00:27:32Z)
• Self Distillation Fine-Tuning of Protein Language Models Improves Versatility in Protein Design [61.2846583160056]
  Supervised fine-tuning (SFT) is a standard approach for adapting large language models to specialized domains.<n>This is in part because high-quality annotated data are far more difficult to obtain for proteins than for natural language.<n>We present a simple and general recipe for fast SFT of PLMs, designed to improve the fidelity, reliability, and novelty of generated protein sequences.
  arXiv  Detail & Related papers  (2025-12-10T05:34:47Z)
• Low-N Protein Activity Optimization with FolDE [15.733324207723328]
  We present FolDE, an ALDE method designed to maximize end-of-campaign success.<n>In simulations across 20 protein targets, FolDE discovers 23% more top 10% mutants than the best baseline method.<n>We also introduce a constant-liar batch selector, which improves batch diversity.
  arXiv  Detail & Related papers  (2025-10-28T04:24:39Z)
• Meta-Learning for Cross-Task Generalization in Protein Mutation Property Prediction [9.083239192939661]
  We introduce the first application of Model-Agnostic Meta-Learning (MAML) to protein mutation property prediction.<n>We also introduce a novel mutation encoding strategy using separator tokens to directly incorporate mutations into sequence context.<n>Our mutation encoding addresses the critical limitation where standard transformers treat mutation positions as unknown tokens, significantly degrading performance.
  arXiv  Detail & Related papers  (2025-10-23T19:09:06Z)
• ProteinAE: Protein Diffusion Autoencoders for Structure Encoding [64.77182442408254]
  We introduce ProteinAE, a novel and streamlined protein diffusion autoencoder.<n>ProteinAE directly maps protein backbone coordinates from E(3) into a continuous, compact latent space.<n>We demonstrate that ProteinAE achieves state-of-the-art reconstruction quality, outperforming existing autoencoders.
  arXiv  Detail & Related papers  (2025-10-12T14:30:32Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• DISPROTBENCH: A Disorder-Aware, Task-Rich Benchmark for Evaluating Protein Structure Prediction in Realistic Biological Contexts [76.59606029593085]
  DisProtBench is a benchmark for evaluating protein structure prediction models (PSPMs) under structural disorder and complex biological conditions.<n>DisProtBench spans three key axes: data complexity, task diversity, and Interpretability.<n>Results reveal significant variability in model robustness under disorder, with low-confidence regions linked to functional prediction failures.
  arXiv  Detail & Related papers  (2025-06-18T23:58:22Z)
• ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning [49.2607661375311]
  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.
  arXiv  Detail & Related papers  (2025-06-09T06:08:59Z)
• ProtCLIP: Function-Informed Protein Multi-Modal Learning [18.61302416993122]
  We develop ProtCLIP, a multi-modality foundation model that represents function-aware protein embeddings.<n>Our ProtCLIP consistently achieves SOTA performance, with remarkable improvements of 75% on average in five cross-modal transformation benchmarks.<n>The experimental results verify the extraordinary potential of ProtCLIP serving as the protein multi-modality foundation model.
  arXiv  Detail & Related papers  (2024-12-28T04:23:47Z)
• DisorderUnetLM: Validating ProteinUnet for efficient protein intrinsic disorder prediction [0.0]
  The prediction of intrinsic disorder regions has significant implications for understanding protein functions and dynamics. Recently, a new generation of predictors based on protein language models (pLMs) is emerging. The article introduces the new DisorderUnetLM disorder predictor, which builds upon the idea of ProteinUnet.
  arXiv  Detail & Related papers  (2024-04-11T20:14:14Z)
• Efficiently Predicting Protein Stability Changes Upon Single-point Mutation with Large Language Models [51.57843608615827]
  The ability to precisely predict protein thermostability is pivotal for various subfields and applications in biochemistry. We introduce an ESM-assisted efficient approach that integrates protein sequence and structural features to predict the thermostability changes in protein upon single-point mutations.
  arXiv  Detail & Related papers  (2023-12-07T03:25:49Z)

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.