cs.CLJul 8, 2026

Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning

Authors: Chen Tang, Yizhou Wang, Jianyu Wu, Lintao Wang, Shixiang Tang, Pengze Li, Encheng Su, Jun Yao, +21 more

Organizations: Shanghai Artificial Intelligence Laboratory, China. · The Chinese University of Hong Kong, Hong Kong. · Shanghai Jiao Tong University, China. · University of Sydney, Australia. · Fudan University, China. · The University of Science and Technology of China, China. · Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, China. · University of Chinese Academy of Sciences, China. · Stanford University, USA. · Nanjing University, China. · University of Oxford, UK.

Abstract

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 Fmax⁡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.

Explore similar work

CardsList