Chao Zhang

This paper improves histology-based molecular receptor prediction by integrating RNA-seq data during training, showing that gene selection strategy is key to model performance.

This paper introduces TEAMKidney, a deep learning framework for automated segmentation and quantification of TEM images, showing improved accuracy and efficiency over existing methods.

VaMiAnalyzer is an open-source Python tool for automated quantification of vasculogenic mimicry structures in 3D in vitro assays, providing consistent results faster than manual methods.

This paper designs and validates opto-interfaced microbe-computer interaction units for programmable cross-life communication in biomedical and environmental applications.

The paper investigates the reliability of mitochondrial DNA variants as lineage markers, finding that most are pre-existing heteroplasmy rather than de novo mutations, and introduces a score to identify reliable markers.

This paper develops a deep learning method to automate measurement of glomerular basement membrane and podocyte foot process widths in TEM images of podocytopathy mouse models, showing comparable accuracy to manual methods.

This study benchmarks 15 DNA methylation age prediction methods across 142 datasets, finding that model performance depends on training data characteristics and providing a resource for future research.

This study shows that breast cancer disrupts hypothalamic GC rhythms by altering PVNCRH neuron activity, and that targeting these neurons can reduce tumor progression.

The paper identifies novel persistent viruses in Aedes aegypti mosquitoes using small RNA sequencing and confirms their replication and transmissibility in cell lines.

CellDiffusion improves scRNA-seq data integration by accurately inferring cell-cell associations and correcting batch effects across diverse datasets.

This paper presents a pipeline to unify RNA-seq data from different studies by removing batch effects, enabling cross-study analysis.