Xianyang Zhang

Kintsugi improves spatial transcriptomics by letting data decide how much to borrow from neighbors and genes, showing it can identify epithelial programs and distinguish fibroblastic foci by composition rather than RNA amount.

Leverage-weighted sketching plus sparse spatial regularization deconvolves 1.6 million Visium HD bins in 153 seconds on commodity hardware, revealing tissue-specific resolution limits where cell-type co-localization can reverse sign.

FlashS identifies spatially variable genes at atlas scale by using a frequency-domain kernel test, achieving high accuracy and efficiency across multiple datasets.

The paper introduces EdgeMap to assess conditional heritability of ligand-receptor gene annotations in spatial transcriptomics data, finding higher edge z-scores in biologically matched tissues.

The paper introduces a multi-LLM consensus framework that improves cell type annotation accuracy for scRNA-seq data by 15% across 50 datasets.

ChatSpatial enables reproducible spatial transcriptomics analysis by using an LLM to select and orchestrate tools with schema enforcement, improving parameter validity and workflow consistency.

BMDD improves microbiome data imputation by modeling bimodal abundance distributions, outperforming existing methods in accuracy and uncertainty estimation.

STAREG identifies replicable spatially variable genes across spatial transcriptomic studies using an empirical Bayesian approach with improved power and false discovery rate control.