Leying Guan

The paper benchmarks computational models predicting B. pertussis booster vaccine responses using multi-omics data from three cohorts, identifying key predictors of immunity and establishing a community resource for systems vaccinology.

scCRAFT+ improves scRNA-seq integration by incorporating marker gene information via virtual adversarial training, enhancing accuracy and robustness to noisy annotations.

This study benchmarks semi-supervised scRNA-seq integration methods against unsupervised baselines across six datasets and five annotation scenarios, finding limited practical benefits of semi-supervised approaches.

MIXPRS improves multi-population polygenic risk score prediction by integrating GWAS summary statistics without individual-level data, outperforming existing methods across multiple traits and populations.

JointPRS improves genetic risk prediction for non-European populations by integrating genetic correlation and multi-population data without individual-level tuning data.

The paper introduces scCRAFT, an autoencoder for scRNA-seq batch integration that outperforms existing methods by preserving biological heterogeneity and handling unbalanced batches and rare cell types.

The paper benchmarks 49 algorithms for predicting B. pertussis vaccination outcomes, finding that purpose-built models outperform literature-based ones due to better handling of nonlinearities and data preprocessing.

The paper identifies a multi-omics recovery factor predictive of long COVID using data from the IMPACC study, showing it can predict LC risk early after infection.

This study identifies immune subtypes in hospitalized COVID-19 patients linked to clinical outcomes and long COVID risk through longitudinal multi-omics analysis.

This study investigates viral reactivation in COVID-19 patients, finding associations between reactivation of specific virus families and clinical outcomes, including mortality and PASC symptoms.

This paper introduces a supervised Bayesian factor model to improve multi-omics signature discovery by integrating dimensionality reduction and predictive modeling.

The paper evaluates computational models predicting immune responses to Pertussis Booster vaccinations using a new community resource, finding that existing models perform poorly and new models show variable performance based on features and strategies.

PAC-MAN enables scalable analysis of multi-sample CyTOF data by clustering and aligning subpopulations across samples to identify dataset-level cellular states.