Scott D. Findlay

DeepRNAi predicts siRNA on- and off-target activity using deep learning, showing high accuracy across species and genomes, and highlights off-target concerns in potent siRNAs.

This paper introduces REPRESS, a deep learning model that predicts cell-type-specific microRNA binding and mRNA degradation from RNA sequences, outperforming existing methods in multiple tasks.

The paper identifies regulatory features in 3'UTR variants that are more likely to affect gene expression and phenotype, and introduces a tool to interpret these variants.

This study identifies disease-causing promoter and untranslated region variants in 8,040 undiagnosed rare disease patients using a new framework and finds 12 variants with potential pathogenicity.

This study investigates post-transcriptional regulation of human NODAL splice variants, showing differential processing and functional distinctions in embryonic stem cells and cancer cells.

This study identifies novel RNAs transcribed from the human NODAL locus, including antisense, circular, and splice variants, highlighting the complexity of NODAL expression.