Jian Zhou

This paper introduces a sequence-to-distribution framework to predict single-molecule chromatin states from DNA sequence, revealing new regulatory mechanisms and variant effects.

TriFlow, discrete flow-matching sequence designer with global three-track structure attention, raises in silico binder success over ProteinMPNN in RFdiffusion and BindCraft-style pipelines on 500 targets and flags functional sites.

GALILEO autonomously discovers therapeutic peptides by combining AI reasoning with lab experiments, identifying peptides that block membrane currents and modulate immune responses.

This study develops CIRCmap to profile cell-surface and intracellular RNAs, identifies cancer-associated csRNAs, and demonstrates oligonucleotide-drug conjugates targeting these RNAs show broad antitumor activity.

The paper identifies a silencer element lost in ADLD patients that specifically targets oligodendrocyte overexpression of LMNB1, linking it to disease pathogenesis.

This study identifies key sequence patterns that determine transcription initiation in human promoters using deep learning and experimental validation, showing conservation across mammalian species.

The paper introduces Sei, a deep learning framework that maps sequence-based regulatory activities to predict variant effects on traits and diseases using human genetics data.

This paper introduces Orca, a deep learning model that predicts genome 3D architecture from sequence data across multiple scales and identifies sequence determinants of chromatin structure.

This paper introduces a quasilinear framework for single-cell data analysis that improves interpretability and generalizability across datasets, revealing new insights into cell lineage and neuronal populations.

The paper identifies RBP target site dysregulation as a major contributor to psychiatric disorder risk, revealing new insights into disease heritability and providing a resource for further research.

The paper identifies a convergent defect in neural progenitor cell transitions during fetal development associated with autism and epilepsy using single-cell RNA sequencing and gene co-expression analysis.

The paper uses deep learning to analyze whole-genome data from ASD families, showing noncoding mutations significantly impact transcriptional and post-transcriptional regulation and contribute to autism.

Selene is a PyTorch-based deep learning library for biological sequences, enabling model development, training, and application for various biological data.

The paper identifies 279 new genetic signals for lung function across multiple ancestries, showing associations with COPD and pleiotropic effects.

The paper identifies a transcriptional signature of glomerular disease using single-cell profiling of human kidney organoids and validates it in disease cohorts.

This study uses single-cell transcriptomics to analyze human fetal kidney development, identifying 17 cell clusters and their lineage trajectories.