11 papers
UniField: RBF-Guided Electron Density Fusion for Enhanced Molecular Representations
Wei Zhang, Kun Li, Jiameng Chen +4
Current 3D geometric molecular representations predominantly focus on discrete atomic skeletons, inherently overlooking the continuous electron density (ED) field that fundamentall…
When Molecular Similarity Works: Property Cliffs Reveal Hidden Errors
Di Hu, Kun Li, Haojie Rao +6
Accurate prediction of molecular properties underpins drug discovery and material design, yet even state-of-the-art models remain vulnerable to localized failure modes that aggrega…
Learning to Select Source Domains: Proxy-Rewarded Policy Optimization for Molecular OOD Generalization
Zhuohao Lin, Kun Li, Jiameng Chen +4
Molecular property prediction under severe out-of-distribution (OOD) shifts remains challenging because conventional scaffold splits can retain local structural similarity between…
From Single-Step Edit Response to Multi-Step Molecular Optimization
Haojie Rao, Kun Li, Yida Xiong +5
Conditional molecular optimization aims to edit a molecule to realize a specified property shift. In practice, structurally similar molecule data is scarce, while decisions are inh…
Variational Bayesian Flow Network for Graph Generation
Yida Xiong, Jiameng Chen, Xiuwen Gong +3
Graph generation aims to sample discrete node and edge attributes while satisfying coupled structural constraints. Diffusion models for graphs often adopt largely factorized forwar…
PCEvo: Path-Consistent Molecular Representation via Virtual Evolutionary
Kun Li, Longtao Hu, Yida Xiong +6
Molecular representation learning aims to learn vector embeddings that capture molecular structure and geometry, thereby enabling property prediction and downstream scientific appl…
FP-AbDiff: Improving Score-based Antibody Design by Capturing Nonequilibrium Dynamics through the Underlying Fokker-Planck Equation
Jiameng Chen, Yida Xiong, Kun Li +4
Computational antibody design holds immense promise for therapeutic discovery, yet existing generative models are fundamentally limited by two core challenges: (i) a lack of dynami…
Transport-Coupled Bayesian Flows for Molecular Graph Generation
Yida Xiong, Jiameng Chen, Kun Li +5
Molecular graph generation (MGG) is essentially a multi-class generative task, aimed at predicting categories of atoms and bonds under strict chemical and structural constraints. H…
BSL: A Unified and Generalizable Multitask Learning Platform for Virtual Drug Discovery from Design to Synthesis
Kun Li, Zhennan Wu, Yida Xiong +8
Drug discovery is of great social significance in safeguarding human health, prolonging life, and addressing the challenges of major diseases. In recent years, artificial intellige…
Zero-Shot Learning with Subsequence Reordering Pretraining for Compound-Protein Interaction
Hongzhi Zhang, Zhonglie Liu, Kun Meng +6
Given the vastness of chemical space and the ongoing emergence of previously uncharacterized proteins, zero-shot compound-protein interaction (CPI) prediction better reflects the p…
Antibody Design and Optimization with Multi-scale Equivariant Graph Diffusion Models for Accurate Complex Antigen Binding
Jiameng Chen, Xiantao Cai, Jia Wu +1
Antibody design remains a critical challenge in therapeutic and diagnostic development, particularly for complex antigens with diverse binding interfaces. Current computational met…