Laura Y. Zhou

TorchGWAS2 improves genome-wide association testing in related samples by using a deterministic variance-correction algorithm, achieving faster and more powerful results across large-scale omics data.

HAUDI improves polygenic score construction for admixed populations by efficiently extending the GAUDI method to multi-way admixture with faster computation and better performance.

This paper improves polygenic prediction of height in an admixed Latino cohort by incorporating genetic ancestry, achieving a 0.1 increase in R² compared to using polygenic scores alone.

The paper analyzes circulating metabolites using genome-wide association data from the TOPMed program, identifying 1,778 loci and highlighting sex-specific genetic contributions.

This study introduces VAE-PRS, a deep learning model that improves polygenic prediction for blood cell traits by capturing interaction effects and outperforming traditional methods in 14 out of 16 traits.

This study compares old and new local ancestry inference methods in Hispanic/Latino populations using HCHS/SOL data, finding high similarity but some regional discrepancies.

The paper develops PEPPRMINT, a statistical model to predict HLA-I peptide presentation, and applies it to identify immunogenic neoantigens in melanoma patients.