精确、跨学科且透明的结构-性质理解：深度原生结构推理

摘要

结构-性质关系是生物学、化学和材料科学的基础，其中功能、反应性和物理响应源于空间、化学和周期性的组织。要从机理上解释这些关系，需要借助科学原理和物理约束来解读结构证据，包括立体化学、成键、对称性、能量学和周期序。然而，将人工智能应用于这一过程带来了表征与推理的双重挑战：模型必须在保留领域原生结构信息的同时，展示特定证据如何在上述约束下支持预测。在此，我们提出SciReasoner，一个面向蛋白质、小分子和无机晶体的原生结构推理多模态科学基础模型。SciReasoner将坐标、拓扑结构和周期连接离散化为统一的结构感知词汇，在推理过程中将结构词元视为可寻址的证据单元。在同源性控制的基因本体预测中，SciReasoner对低同源性和类孤儿蛋白的细胞组分标注有所改进，将F_{max}从0.42提升至0.55。在化学领域，它将单步逆合成准确率从0.63提高到0.72，同时生成了碎片级断键和前体验证轨迹。在材料科学领域，其表征能够区分元素相与化合物相，并分辨高带隙和低带隙区间。在86个基准测试中，SciReasoner在67项任务上达到了最先进水平。双盲专家评估显示，在98%的案例中，其推理轨迹被认为优于或至少与前沿大语言模型相当。通过将结构作为在科学约束下可检查的推理基底，SciReasoner将准确预测与可解释的科学推理联系起来。

English

Structure-property relationships are foundational to biology, chemistry and materials science, where function, reactivity and physical response emerge from spatial, chemical and periodic organization. Mechanistically explaining these relationships requires interpreting structural evidence through scientific principles and physical constraints, from stereochemistry and bonding to symmetry, energetics and periodic order. However, applying artificial intelligence to this process presents a joint challenge of representation and reasoning: models must preserve domain-native structural information while showing how specific evidence supports predictions under these constraints. Here we introduce SciReasoner, a multimodal scientific foundation model for native structural reasoning across proteins, small molecules and inorganic crystals. SciReasoner discretizes coordinates, topologies and periodic connectivities into a unified structure-aware vocabulary, treating structural tokens as addressable evidence units during reasoning. In homology-controlled Gene Ontology prediction, SciReasoner improves Cellular Component annotation for low-homology and orphan-like proteins, increasing F_{max} from 0.42 to 0.55. In chemistry, it raises single-step retrosynthesis accuracy from 0.63 to 0.72 while generating fragment-level disconnection and precursor-verification traces. In materials science, its representations separate elemental and compound phases and resolve high- and low-band-gap regimes. Across 86 benchmarks, SciReasoner achieves state-of-the-art performance on 67 tasks. Double-blind expert evaluation rates its reasoning traces as preferred or at least comparable to those of a frontier large language model in 98% of cases. By making structure an inspectable substrate for reasoning under scientific constraints, SciReasoner connects accurate prediction with interpretable scientific inference.