Bo Xia

High-throughput in silico screen uncovers key regulators of 3D genome architecture

The paper identifies ZNF654 and JMJD6 as novel factors defining TAD boundaries through in silico screens and experimental validation.

Decoding the gene regulatory landscape through multimodal learning of protein-DNA interactions

Chromnitron predicts protein-DNA binding landscapes across cell types and proteins using multimodal learning, revealing new regulators of T cell exhaustion and dynamic shifts during neurogenesis.

scRNA-seq reveals transcriptional dynamics of Encephalitozoon intestinalis parasites in human macrophages

This study uses scRNA-seq to analyze transcriptional changes in human macrophages and Encephalitozoon intestinalis parasites during infection, revealing parasite developmental dynamics and host response.

Characterization of tumor heterogeneity through segmentation-free representation learning

The paper introduces a segmentation-free vision transformer, CANVAS, to discover and characterize tumor microenvironment signatures from high-dimensional multiplexed images, identifying a monocytic signature linked to poor prognosis.

Integrative Multi-omic Profiling of Two Human Decedents Receiving Pig Heart Xenografts Reveals Strong Perturbations in Early Immune-Cell and Cellular Metabolism Responses.

The paper analyzes multi-omic data from two pig heart xenografts in human decedents to identify immune and metabolic responses associated with rejection and injury.

Cell type-specific prediction of 3D chromatin organization enables high-throughput in silico genetic screening

This study introduces C.Origami, a deep learning model that predicts cell type-specific 3D chromatin organization, enabling in silico genetic screening to identify genomic regions affecting chromatin structure.