Wei Zhang

ST-DISTAL improves cell-type deconvolution in spatial transcriptomics by integrating spatial and molecular information through a dual-branch graph convolutional framework.

HistoMethyl links histopathology with DNA methylation to predict molecular features from H&E slides alone, improving mutation prediction and survival outcomes across multiple cancer cohorts.

X-intNMF improves multi-omics integration by modeling both cross-omics and intra-omics interactions, outperforming existing methods in cancer phenotype prediction and survival analysis.

SynOmics improves multi-omics integration by modeling feature interactions through a graph convolutional network, outperforming existing methods in biomedical classification tasks.

This study shows that CAMKK2 isoforms LF and SF have distinct roles in metabolic stress response and ferroptosis regulation in cancer cells.

MODE improves deconvolution by integrating multi-omic data through a multimodal autoencoder, outperforming existing methods in simulation and real data.

TLCellClassifier improves cell detection, tracking, and classification in time-lapse images using CNN, metric learning, and LSTM, outperforming existing tools in accuracy and efficiency.

APA-Scan identifies and visualizes 3'-UTR APA events using RNA-seq and 3'-end-seq data, improving accuracy over existing methods.

omicsGAT integrates graph-based learning with attention mechanisms to improve cancer subtype analysis using RNA-seq data.

This study introduces omicsGAN, a GAN model that integrates multi-omics data and interaction networks to generate synthetic data improving cancer outcome prediction.

AS-Quant detects and visualizes alternative splicing events using RNA-seq data through a three-step process, validated by RT-PCR.

The paper introduces a computational pipeline for analyzing large-scale time-lapse microscopy data to predict cancer drug response in patient-specific contexts.