Robert Salomone

The paper uses a deep ensemble approach to improve CRISPR guide RNA selection by incorporating uncertainty quantification, achieving over 91% precision in guide identification for most mouse genes.

The paper evaluates and optimizes sequence-based gene regulatory deep learning models using a DREAM Challenge dataset, showing improvements through architectural and training strategy refinements.

This paper calibrates agent-based models of tumour growth using approximate Bayesian computation to estimate parameters and quantify uncertainty in biphasic growth models.

This paper introduces Crackling++, a faster and scalable method for off-target assessment of CRISPR guide RNAs by using non-contiguous exact matches, outperforming existing tools.