Interpreting <i>cis</i>-regulatory mechanisms from genomic deep neural networks using surrogate models.

ABSTRACT: Deep neural networks (DNNs) have greatly advanced the ability to predict genome function from sequence. However, elucidating underlying biological mechanisms from genomic DNNs remains challenging. Existing interpretability methods, such as attribution maps, have their origins in non-biological machine learning applications and therefore have the potential to be improved by incorporating domain-specific interpretation strategies. Here we introduce SQUID, a genomic DNN interpretability framework based on domain-specific surrogate modeling. SQUID approximates genomic DNNs in user-specified regions of sequence space using surrogate models-simpler quantitative models that have inherently interpretable mathematical forms. SQUID leverages domain knowledge to model cis-regulatory mechanisms

SUBMITTER: Seitz EE 

PROVIDER: S-EPMC11823438 | biostudies-literature | 2024 Jun

REPOSITORIES: biostudies-literature