Da Zhuan Xu

This paper adapts co-folding models for structure-based protein-protein docking by replacing their template module with a docking module and training with a flow-matching objective, showing competitive performance on specific targets.

LEMONmethyl-seq profiles DNA methylation dynamics in mammalian cells, revealing CRISPR-induced changes and endogenous patterns, including non-canonical CpH methylation.

This paper examines whether diffusion models can extract physics-like energies for protein docking, finding they can recover energy funnels comparable to Rosetta in 9 out of 25 cases.

This paper introduces RENDER, a method for transient delivery of CRISPR-based epigenome editors as ribonucleoproteins to modulate gene expression in human cells, achieving durable epigenetic silencing.

This study uses cryo-EM and deep learning to analyze conformational changes in ribonucleotide reductase during turnover, revealing dynamic asymmetry and transient states essential for catalysis.

This paper describes a protocol for CRISPRoff epigenetic editing to silence genes in human cells without DNA breaks, showing heritable transcriptional repression.

The paper improves CNN-based cryo-EM micrograph filtering by using fine-tuning and Fourier space information, resulting in higher prediction accuracy.

The paper performs a comprehensive phylogenetic analysis of ribonucleotide reductase (RNR) family to identify an ancestral clade and trace evolutionary diversification through insertions and extensions.