Zhuo Chen

This paper introduces DQHTFI, a framework for drug-target interaction classification and binding affinity regression, achieving competitive results on benchmark datasets.

PG-MLD transfers dynamic 3D physical knowledge to SMILES-based molecular models, improving property prediction without requiring 3D conformer generation.

Bulk2Space deconvolves bulk RNA-seq data to reveal spatial and cellular heterogeneity using single-cell and spatial transcriptomics references, identifying immune cell spatial variance and novel gene patterns in mouse brain regions.