Yuan He

RegDesign-Bench: Benchmarking computational methods for cell-type-specific regulatory DNA design

RegDesign-Bench evaluates computational methods for designing cell-type-specific regulatory DNA, showing that performance on individual metrics does not guarantee overall effectiveness.

Reconstructing sequence-grammar trajectories enables interpretable and tunable cis-regulatory element design

This paper introduces GO-CRE, a method for designing cell-type-specific cis-regulatory elements by reconstructing sequence-grammar trajectories and using reinforcement learning with predictor guidance.

HoloCell: A Generative Foundation Model for Holistic Cellular Modeling

HoloCell is a generative foundation model that integrates epigenomics, transcriptomics, and proteomics data across single-cell multi-omics modalities, demonstrating superior performance in representation learning and cross-modal generation.

GENERator-v2: Reconciling Coarse Tokenization with Single-Nucleotide Resolution in Genomic Language Modeling

This paper introduces improved genomic language models that balance long-range context with single-nucleotide resolution, achieving better performance and efficiency than prior methods.

Illuminating the Virosphere's Dark Matter using Hierarchical Deep Learning

DeepVirus identifies and classifies viral dark matter in metagenomic data using a hierarchical transformer framework, revealing novel viral lineages and expanding known RNA virus diversity.