Olga H. Nikolova

This paper introduces a Bayesian group factor analysis transfer learning framework that improves drug response prediction and tumor purity prediction across cancer datasets by modeling feature dependencies.

UniVI integrates multimodal single-cell data using a mixture-of-experts β-variational autoencoder, improving cross-modal alignment and label transfer across various data types and study designs.

This paper introduces Priori, a method to predict transcription factor activity from RNA sequencing data, showing it outperforms existing methods in detecting aberrant activity and identifying disease-related factors.