Xin Zhou

MAPA uses large language models to reduce redundancy in pathway analysis and improve biological interpretation of multi-omics data.

An LLM agent with a literature-mined environment of 150 tools, 105 packages and 59 databases plans in code, matching reported human accuracy on database and sequence question answering.

The paper examines microbiome and immune changes in depression during a psychosocial intervention, finding a protective role for Prevotella-dominant microbiomes and reduced inflammation.

The paper introduces the iPhylo suite, an interactive platform for building and annotating biological and chemical taxonomic trees, with web and command-line modules for analysis and visualization.

This paper introduces a novel large-scale EV production strategy with upstream fed-batch suspension cell culture and downstream chromatographic purification for clinical applications.

The paper develops a pipeline to profile both host expression and microbial abundance from spatial transcriptomic data, demonstrating host-microbe interactions and method efficiency.

This study identifies KMT2D-NOTCH signaling defects in HLHS coronary artery endothelial cells, showing impaired differentiation and proliferation due to suppressed NOTCH target genes.

This study integrates longitudinal personal exposome and multi-omics data to show dynamic interactions between environmental exposures and internal biomolecules, highlighting key agrochemicals and fungi.

CELESTA identifies cell types in multiplexed in situ images by integrating protein expression and spatial information, revealing novel spatial biology associated with lymph node metastasis.