生物医药与药物发现 颠覆级 有讲解视频
发表时间
2026-09-29
arXiv
2609.34654

收录解读

蛋白质适应度预测是蛋白质工程和序列-功能关系理解的核心问题。随着深度学习的发展,蛋白质基础模型被广泛用于此任务,但近期分析表明这些模型存在训练语料偏好,且不可靠输入会扭曲预测结果。家族特异性进化证据和结构上下文可以提供互补约束,从而弥补这些局限。

本文提出VenusREM-Harness(VRH),一种通用、模型无关、无需训练的检索增强突变框架。它根据模型不确定性融合冻结模型分数与多序列比对(MSA)证据,然后基于结构置信度和溶剂暴露度应用门控背景校正和分数收缩。该方法可即插即用于任何蛋白质基础模型。

在ProteinGym、VenusMutHub和新构建的病毒基准VenusViroHub上,共1,211个测定和310万变异上进行评估。所有71种配置在所有三个基准上的Spearman相关性平均提升0.073,并在五个指标上均有广泛增益。基于VRH构建的VenusREM2首次在所有功能、分类、MSA深度和突变深度类别中排名最高,ProteinGym平均Spearman达到0.556,比先前最佳高0.038。

该工作提供了一种通用、高效的蛋白质适应度预测增强方案,显著提升了现有基础模型的预测能力,并建立了新的基准。其模型无关和无需训练的特性使其易于推广,但方法本质上是现有技术的系统集成与优化,未提出全新的学习范式。

原始摘要

Accurate fitness prediction is central to protein engineering and understanding sequence-function relationships. With advances in deep learning, protein foundation models (PFMs) have become widely used for this task. Recent analyses, however, show that these models share preferences reflecting their training corpora, while unreliable inputs can further distort fitness predictions. Family-specific evolutionary evidence and structural context can help address these limitations by providing complementary constraints on model scores, motivating VenusREM-Harness (VRH), a general, model-agnostic, training-free Retrieval-Enhanced Mutation harness. It fuses frozen model scores with multiple sequence alignment (MSA) evidence according to model uncertainty, then applies gated background correction and score shrinkage based on structural confidence and solvent exposure. Across 1,211 assays and 3.1 million measured variants from ProteinGym, VenusMutHub, and the newly curated viral benchmark VenusViroHub, all 71 configurations improve Spearman correlation on all 3 benchmarks by 0.073 on average, with broad gains across 5 metrics. Extended analyses relate retrieval gains to model-MSA preference differences, assess domain-level gains and immune-escape cases, and quantify computational speedups. Built with VRH, VenusREM2 is the first to rank highest in all function, taxon, MSA-depth, and mutation-depth categories, with a ProteinGym Average Spearman of 0.556, 0.038 above the prior best.

解读视频

相关论文

链接