RT Journal Article
SR Electronic
T1 Correcting gradient-based interpretations of deep neural networks for genomics
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2022.04.29.490102
DO 10.1101/2022.04.29.490102
A1 Majdandzic, Antonio
A1 Rajesh, Chandana
A1 Koo, Peter K.
YR 2022
UL http://biorxiv.org/content/early/2022/08/23/2022.04.29.490102.abstract
AB Post-hoc attribution methods are widely applied to provide insights into patterns learned by deep neural networks (DNNs). Despite their success in regulatory genomics, DNNs can learn arbitrary functions outside the probabilistic simplex that defines one-hot encoded DNA. This introduces a random gradient component that manifests as noise in attribution scores. Here we demonstrate the pervasiveness of off-simplex gradient noise for genomic DNNs and introduce a statistical correction that is effective at improving the interpretability of attribution methods.Competing Interest StatementThe authors have declared no competing interest.