activity
20242026
collaborators

11 papers

cs.CE2026

Exploring the Alignment of Generation and Understanding in Protein Structure Modeling

Junde Xu, Yuansheng Huang, Zijun Gao +5

Understanding and generation are often treated as two separate paradigms in training deep neural networks, despite the fact that both are trained with closely related objectives su…

q-bio.BM2026

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.…

cs.CE2026

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…

q-bio.BM2026

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…

q-bio.BM2025

CONFIDE: Hallucination Assessment for Reliable Biomolecular Structure Prediction and Design

Zijun Gao, Mutian He, Shijia Sun +8

Reliable evaluation of protein structure predictions remains challenging, as metrics like pLDDT capture energetic stability but often miss subtle errors such as atomic clashes or c…

cs.CE2025

Learning the PTM Code through a Coarse-to-Fine, Mechanism-Aware Framework

Jingjie Zhang, Hanqun Cao, Zijun Gao +8

Post-translational modifications (PTMs) form a combinatorial "code" that regulates protein function, yet deciphering this code - linking modified sites to their catalytic enzymes -…