Chong Wu

Mendel is a foundation model trained on human whole genome sequences to prioritize regulatory variants and improve gene expression prediction.

PRIORITI uses language models to predict target-indication success in drug discovery, achieving high accuracy and robustness across different benchmarks.

Domain-grounded prompting lets GPT-5 produce genetic evidence for 13,022 drug target-indication pairs that predicts clinical success as well as expert curation, with wider coverage.

The paper constructs a multi-ancestry methylome atlas of purified monocytes, identifies population-specific methylation quantitative trait loci, and performs methylome-wide association studies for 41 traits, revealing novel associations for type 2 diabetes.

This paper develops a zero-inflated hierarchical generalized transformation model to improve cell-type deconvolution in spatial transcriptomics data from oral squamous cell carcinomas.

This study integrates large-scale omics and electronic health records to identify risk proteins and drugs for cancer prevention, finding 101 novel proteins and three drugs associated with reduced colorectal cancer risk.

This study benchmarks five DNA foundation models across genomic tasks, finding that mean token embeddings improve classification performance and specialized models outperform general ones in gene expression and QTL prediction.

The paper develops M2AE, a multi-task multi-view model to impute blood SCFA levels using gut metagenomic data, dietary features, and host characteristics, showing improved performance over existing methods.

omicsMIC benchmarks 28 imputation methods for mass spectrometry-based omics data, enabling researchers to evaluate and select methods based on real-time visualizations.

SUMMIT-FA improves gene expression prediction accuracy using functional annotations and eQTL data, enhancing gene-trait association detection in GWAS.

The paper introduces BLISS, a framework for training proteome-wide association models using pQTL summary statistics, enabling multi-ancestry analysis of protein-phenotype associations.

MIMOSA improves DNA methylation prediction and MWAS power by integrating summary-level mQTL data, identifying more CpG-phenotype associations in whole blood.

SUMMIT improves transcriptomic data imputation and TWAS power by using large eQTL summary datasets, identifying 11 causal genes for COVID-19 severity.

The paper introduces a machine learning method to detect brain connectomic biomarkers differentiating Alzheimer's disease and mild cognitive impairment using FDG-PET data.

This paper introduces a gene-level methylome-wide association analysis method called CMO that identifies novel Alzheimer's disease genes by integrating DNA methylation and enhancer-promoter interactions with GWAS data.

The paper introduces aMAT, a novel multi-trait analysis method, and applies it to brain imaging phenotypes from UK Biobank, identifying 24 risk loci, 13 new to standard GWAS.

The paper introduces a new algorithm for de novo discovery of mutated driver pathways in cancer, showing improved efficiency and scalability over existing methods.