Brendan D. O’Fallon

EventHorizon is a foundation model for clinical flow cytometry that uses self-supervised learning to generate embeddings for diagnostic use, achieving high accuracy in identifying genetic abnormalities.

This paper introduces a deep generative model for haplotype prediction in NGS data, showing superior accuracy compared to statistical methods for variant detection.

Jovian uses a deep learning model to directly infer germline haplotypes from short reads, achieving high sensitivity and precision in variant detection.

This paper improves CNV detection in NGS data using algorithmic adaptations in an HMM framework, achieving better PPV with similar sensitivity compared to existing tools.