发表机构
The Hong Kong University of Science and Technology (Guangzhou); Southwest Minzu University; Guangzhou University of Chinese Medicine（香港科技大学（广州）; 西南民族大学; 广州中医药大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FlexEvo提出一种模型无关的进化框架，在推理时基于单一构象进行几何约束双目标优化，将跨构象性能下降从47.8%降至4.4%，实现鲁棒生物分子复合物设计。
AI 中文摘要
蛋白质会形成构象集合体，然而基于结构的生物分子设计通常针对单一目标构象来优化候选分子。因此，当目标采用另一种构象时，适合某一状态的候选分子可能会失去有利的相互作用或产生空间位阻。我们提出了FlexEvo，一个与模型无关的进化框架，它在推理时仅根据单一目标构象对候选分子进行一次适应，以提高其与适应过程中未见过的替代天然构象的兼容性，而无需重新训练源模型或要求构象集合。FlexEvo将跨状态适应视为几何约束的双目标优化，在保持输入状态相互作用与对合理构象扰动的鲁棒性之间取得平衡。为了限制搜索空间并减少无效的结构编辑，几何衍生的FlexBoxes定义了受保护的锚定区域、用于局部探索的可适应区域以及用于避免冲突的禁止区域。统一的原子级表示支持跨不同粘合剂类别的拓扑保持适应，而Pareto选择则在两个目标之间保留非支配候选。我们在多个生成基线和九个代表性粘合剂类别（涵盖不同分子大小和结构拓扑）上评估了FlexEvo。FlexEvo将类别平衡的平均相对性能下降从47.8%降至4.4%，同时每个样本仅增加1.4至3.1分钟的适应时间。这些结果表明，单状态推理时适应是实现跨蛋白质构象景观的鲁棒生物分子复合物设计的实用途径。
英文摘要
Proteins populate conformational ensembles, yet structure-based biomolecular design typically optimizes candidates against a single target conformation. Consequently, a candidate that fits one state can lose favorable interactions or develop steric clashes when the target adopts another. We introduce FlexEvo, a model-agnostic evolutionary framework that adapts candidates once at inference time from a single target conformation to improve compatibility with alternative natural conformations unseen during adaptation, without retraining the source model or requiring a conformational ensemble. FlexEvo casts cross-state adaptation as geometry-constrained bi-objective optimization, balancing preservation of input-state interactions against robustness to plausible conformational perturbations. To limit the search space and reduce invalid structural edits, geometry-derived FlexBoxes define protected anchor regions, adaptable regions for local exploration, and forbidden regions for clash avoidance. A unified all-atom representation supports topology-preserving adaptation across diverse binder categories, while Pareto selection preserves nondominated candidates across the two objectives. We evaluate FlexEvo across multiple generation baselines and nine representative binder categories spanning diverse molecular sizes and structural topologies. FlexEvo reduces the category-balanced mean relative performance degradation from 47.8% to 4.4%, while adding only 1.4--3.1 minutes of adaptation per sample. These results establish single-state inference-time adaptation as a practical route toward robust biomolecular complex design across protein conformational landscapes.
