AI 译本 · Equalang
新上架PDF · 2026年11月翻译
加载中…
加载中…
arXiv · 2026
基于 MSA 组织优化蛋白质-蛋白质复合物结构预测的自动研究智能体
Zilu Zhang, Jing Bao, Lifeng Qiao, Sheng Xu et al.
Protein-complex structure prediction with AlphaFold 3 depends on MSA content, depth, and cross-chain pairing. Current pipelines apply uniform recipes, typically maximizing depth and pairing by species, yet even whether cross-chain pairing helps AF3 remains contested. We show that the value of both depth and pairing is strongly target-dependent, so no single recipe is optimal across interfaces. We introduce an autonomous agent that treats a frozen AF3 as a black-box experimental instrument. For each target, the agent formulates biological hypotheses, analyzes and reorganizes the MSA, and iteratively refines sequence selection and pairing using predictor label-free signals alone. On 1{,}015 protein--protein interfaces from three benchmarks released after AF3's training cutoff, the agent improves overall interface DockQ over AF3's default pipeline and fixed MSA recipes on every benchmark, while using on average 60\% fewer MSA sequences than the default. Gains are largest for inter-species heteromers, where species-based pairing is unreliable: mean DockQ increases from 0.465 to 0.612 on FoldBench and from 0.482 to 0.562 on HD439. The improvements arise from both sequence construction and pairing policy, including deliberate non-pairing. These results recast MSA design as a target-specific problem and show that an autonomous agent can adapt it at test time through biological reasoning and self-directed, confidence-guided experimentation.
使用 AlphaFold 3 预测蛋白质复合物结构，取决于 MSA 的内容、深度以及跨链配对情况。现有流程通常采用统一方案，倾向于按物种最大化 MSA 深度和配对数量；然而，跨链配对是否有助于 AF3，至今仍存在争议。我们发现，深度和配对的价值都高度依赖具体目标，因此不存在适用于所有界面的最优统一方案。我们提出了一种自主智能体，将冻结的 AF3 视为黑箱实验工具。针对每个目标，该智能体会提出生物学假设、分析并重新组织 MSA，然后仅依靠不使用预测器标签的信号，迭代优化序列选择与配对策略。在 AF3 训练截止日期之后发布的三个基准中，我们对 1,015 个蛋白质-蛋白质界面进行了评估。该智能体在每个基准上的总体界面 DockQ 均优于 AF3 的默认流程和固定 MSA 方案，同时使用的 MSA 序列平均比默认流程少 60%。对于跨物种异源复合物，提升最为显著，因为基于物种的配对在这类复合物中并不可靠：FoldBench 上的平均 DockQ 从 0.465 提升至 0.612，HD439 上则从 0.482 提升至 0.562。提升既来自序列构建，也来自配对策略，其中包括有意不进行配对。这些结果表明，MSA 设计应视为针对具体目标的问题，并证明自主智能体能够在测试时通过生物学推理以及自主开展、由置信度信号引导的实验来调整 MSA。
PDF · 2026年11月翻译