Han Yuan

Cerberus: bidirectional state space blocks improve accuracy and efficiency of regulatory sequence models

The paper introduces Cerberus, an improved regulatory sequence model using bidirectional state space blocks, achieving higher accuracy and efficiency than existing models like Borzoi.

Scalable saturation mutagenesis reveals gene regulatory architecture and rare variant effects

The paper introduces Multi-ISM, a scalable framework for saturation mutagenesis that reduces computational cost while maintaining accuracy, and applies it to 5,000 genes to map regulatory elements and rare variant effects.

Borzoi-informed fine mapping improves causal variant prioritization in complex trait GWAS

Sniff improves causal variant prioritization in GWAS by integrating Borzoi-predicted variant effects with functional annotations, identifying more fine-mapped variants with higher posterior inclusion probabilities.

Predicting cell type-specific coverage profiles from DNA sequence

The paper trains a model on single-cell 3-seq data to predict cell type-specific coverage profiles and improves variant interpretation across diverse cell types.

Parameter-Efficient Fine-Tuning of a Supervised Regulatory Sequence Model

This study evaluates parameter-efficient fine-tuning of the Borzoi model to improve gene regulation analysis across new RNA-seq datasets with high accuracy and efficiency.

Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation

This paper introduces Borzoi, a model that predicts RNA-seq coverage from DNA sequence, enabling variant effect scoring across multiple regulatory layers and outperforming existing methods on QTLs.

The complete cell atlas of an aging multicellular organism

This paper creates a single-cell atlas of aging in C. elegans, revealing cell-type specific aging patterns and identifying transcription factors that regulate aging rates.

BindVAE: Dirichlet variational autoencoders for de novo motif discovery from accessible chromatin

BindVAE is a deep learning method for discovering TF motifs from open chromatin data, achieving higher precision than existing methods but with lower recall.

scBasset: Sequence-based modeling of single cell ATAC-seq using convolutional neural networks

scBasset uses convolutional neural networks to model scATAC data, achieving state-of-the-art results in cell type identification and other tasks.

Revisiting the Hayflick Limit: Insights from an Integrated Analysis of Changing Transcripts, Proteins, Metabolites and Chromatin

The paper analyzes replicative senescence in WI-38 cells using multi-omics data, finding early senescence markers, myofibroblast-like transitions, and YAP1/TEAD1 regulation.

BindSpace: decoding transcription factor binding signals by large-scale joint embedding

BindSpace is a model that embeds DNA sequences and TF labels into a shared space, achieving state-of-the-art binding prediction for hundreds of TFs.