I'm a PhD Student in Statistics at Texas A&M University, co-advised by Prof. Xianyang Zhang and Prof. Jun Chen at Mayo Clinic.
My research focuses on:
- LLM4omics: Using Large Language Models for omics data analysis
- Single-cell RNA-seq Analysis: Computational methods for scRNA-seq data
- Microbiome Analysis: Statistical methods for microbiome data
- LLMs for Productivity: Building tools to enhance daily workflows
mLLMCelltype · New Release
An iterative multi-LLM consensus framework for cell type annotation in single-cell RNA sequencing data. By leveraging the complementary strengths of multiple large language models (including GPT-4o/4.1, Claude-3.7/3.5, Gemini-2.0, Grok-3, and others), this framework significantly improves annotation accuracy while providing transparent uncertainty quantification.
- Paper: Large Language Model Consensus Substantially Improves the Cell Type Annotation Accuracy for scRNA-seq Data
- Key Achievement: Outperforms state-of-the-art methods by nearly 15% in mean accuracy (77.3% vs 61.3%) across 50 diverse datasets
MicrobiomeStat · 29K+ Downloads
Comprehensive R package for microbiome and multi-omics analysis
ggpicrust2 · 100+ Citations
R package for PICRUSt2 visualization and analysis
LLM-powered tool that converts text into calendar events
- 2025: Published mLLMCelltype in bioRxiv, a novel multi-LLM consensus framework for scRNA-seq cell type annotation
- 2025: ggpicrust2 paper reached 100 citations in Google Scholar
- 2024: Awarded the Su Binghua Distinguished Biostatistics Scholarship
- Published in Bioinformatics (2023)
- ggpicrust2: an R package for PICRUSt2 predicted functional profile analysis and visualization. (2023, Bioinformatics) - 132 citations
- Large Language Model Consensus Substantially Improves the Cell Type Annotation Accuracy for scRNA-seq Data (2025, bioRxiv) - New publication
- The microbiome at the interface between environmental stress and animal health: an example from the most threatened vertebrate group (2024, Proceedings of the Royal Society B) - 1 citations
