Kui Hua

Serval is a modular framework for decoding spatial transcriptomics data that introduces Cosine, a method improving transcript recovery and correlation with expression references.

This paper introduces RECODR, a computational pipeline that tracks transcriptome changes in cancer development and treatment to predict resistance mechanisms and design effective therapies.

The paper introduces UniCoord, a joint-VAE model that learns a universal coordinate system for single-cell transcriptomic data to capture heterogeneity and enable data generation and analysis.

The paper introduces hECA, a cell-centric human Ensemble Cell Atlas, which integrates scRNA-seq data from multiple studies to enable targeted data retrieval, multi-view presentations, and customizable reference creation for cell type annotations.

DeepCAGE predicts chromatin accessible regions using deep learning, integrating sequence data and transcription factor activity, and identifies disease-associated variants.

SOMDE identifies spatially variable genes in large-scale spatial transcriptomic data efficiently using self-organizing maps and Gaussian Processes.

HGC enables efficient multiresolution clustering of large-scale single-cell data by combining graph-based and hierarchical clustering methods, achieving state-of-the-art accuracy.

NeuronMotif decodes cis-regulatory motifs from DCNNs by analyzing neuron activations, revealing motif combinations and improving model performance.

VPAC is a variational projection-based method for accurate single-cell transcriptomic clustering, validated across diverse datasets and showing robust performance.

This study reproduces a human cell atlas publication on blood dendritic cells to assess reproducibility in single-cell RNA-seq analysis and identifies factors affecting results.

SIP provides an interchangeable pipeline for scRNA-seq data processing, enabling easy integration and customization of analysis steps.