18 papers
SF-Cluster: Frustration-Guided MSA Subsampling for Alternative Protein Conformation Recovery
Hanqun Cao, Zijun Gao, Chunbin Gu +3
Deep-learning structure predictors are sensitive to their multiple sequence alignment (MSA) input, making MSA subsampling a practical route to recovering alternative conformations.…
AlloGen: Conformation-Selective Binder Generation with Differential State Scoring
Hanqun Cao, Zachary Quinn, Aastha Pal +4
Protein binder design has largely optimized for affinity alone, leaving conformational selectivity unaddressed: for allosteric targets such as kinases, nuclear receptors, and GPCRs…
Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards
Fang Wu, Aaron Tu, Weihao Xuan +21
Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue tha…
GeoCycler: Reward-Aligned 3D Diffusion for Constraint-Conditioned Cyclic Peptide Design
Jingjie Zhang, Hanqun Cao, Haosen Shi +10
Cyclic peptides are attractive therapeutic modalities because their closed-ring topology can improve stability and target specificity. However, de novo cyclic peptide design remain…
TD3B: Transition-Directed Discrete Diffusion for Allosteric Binder Generation
Hanqun Cao, Aastha Pal, Sophia Tang +4
Protein function is often controlled by ligands that bias the direction of state transitions, such as agonists and antagonists, rather than stabilizing a single conformation. This…
CA-DEL: An Open Multi-Target, Multi-Modal Benchmark for Learning from DNA-Encoded Library Screens
Mutian He, Hanqun Cao, Cheng Tan +4
The success of machine learning in drug discovery hinges on learning the relationship between a chemical structure and its biological activity. While DNA-Encoded Library (DEL) tech…