Xiaoyang Chen

2 weeks ago | nature.com | Xuejian Cui |Qijin Yin |Zijing Gao |Zhen Li |Xiaoyang Chen |Shengquan Chen | +4 more

Cis-regulatory elements (CREs), including enhancers, silencers, promoters and insulators, play pivotal roles in orchestrating gene regulatory mechanisms that drive complex biological traits. However, current approaches for CRE identification are predominantly sequence-based and typically focus on individual CRE types, limiting insights into their cell-type-specific functions and regulatory dynamics. Here, we present CREATE, a multimodal deep learning framework based on Vector Quantized Variational AutoEncoder, tailored for comprehensive CRE identification and characterization. CREATE integrates genomic sequences, chromatin accessibility, and chromatin interaction data to generate discrete CRE embeddings, enabling accurate multi-class classification and robust characterization of CREs. CREATE excels in identifying cell-type-specific CREs, and provides quantitative and interpretable insights into CRE-specific features, uncovering the underlying regulatory codes. By facilitating large-scale prediction of CREs in specific cell types, CREATE enhances the recognition of disease- or phenotype-associated biological variabilities of CREs, thus advancing our understanding of gene regulatory landscapes and their roles in health and disease. Cui et al. present CREATE, a platform for the identification of multi-class cell-type-specific CREs by integrating multi-omics data. CREATE interpretably extracts discrete CRE embeddings, quantitatively unveils CRE-specific features, and effectively enables large scale prediction of CREs.

Jan 31, 2025 | nature.com | Yuyao Liu |Zhen Li |Xiaoyang Chen |Xuejian Cui |Zijing Gao

AbstractRecent advances in spatial epigenomic techniques have given rise to spatial assay for transposase-accessible chromatin using sequencing (spATAC-seq) data, enabling the characterization of epigenomic heterogeneity and spatial information simultaneously.

Jan 17, 2025 | biorxiv.org | Zhen Li |Xuejian Cui |Xiaoyang Chen |Zijing Gao

AbstractSpatially resolved sequencing technologies have revolutionized our understanding of biological regulatory processes within the microenvironment by accessing the states of genomic regions, genes and proteins as well as spatial coordinates of cells. However, discrepancies between different modalities and samples hinder the analysis of spatial omics data, necessitating the development of advanced computational methods.

Dec 30, 2024 | genomebiology.biomedcentral.com | Xiaoyang Chen |Keyi LI |Xiaoqing Wu |Zhen Li |Qun Jiang |Xuejian Cui | +3 more

To capture spatial accessibility pattern of each peak, Descart construct a spatial graph based on spatial locations of spots (can also be replaced by cells).

Dec 11, 2024 | biorxiv.org | Hao Zheng |Xiaoyang Chen |Hongming Li |Tingting Chen

AbstractDeep learning-based cortical surface reconstruction (CSR) methods heavily rely on pseudo ground truth (pGT) generated by conventional CSR pipelines as supervision, leading to dataset-specific challenges and lengthy training data preparation. We propose a new approach for reconstructing multiple cortical surfaces using weak supervision from brain MRI ribbon segmentations.