Improving representations of genomic sequence motifs in convolutional networks with exponential activations.

Koo, Peter K, Ploenzke, Matt (March 2021) Improving representations of genomic sequence motifs in convolutional networks with exponential activations. Nature Machine Intelligence, 3 (3). pp. 258-266. ISSN 2522-5839

DOI: 10.1038/s42256-020-00291-x

Abstract

Deep convolutional neural networks (CNNs) trained on regulatory genomic sequences tend to build representations in a distributed manner, making it a challenge to extract learned features that are biologically meaningful, such as sequence motifs. Here we perform a comprehensive analysis of synthetic sequences to investigate the role that CNN activations have on model interpretability. We show that employing an exponential activation in the first layer filters consistently leads to interpretable and robust representations of motifs compared with other commonly used activations. Strikingly, we demonstrate that CNNs with better test performance do not necessarily imply more interpretable representations with attribution methods. We find that CNNs with exponential activations significantly improve the efficacy of recovering biologically meaningful representations with attribution methods. We demonstrate that these results generalize to real DNA sequences across several in vivo datasets. Together, this work demonstrates how a small modification to existing CNNs (that is, setting exponential activations in the first layer) can substantially improve the robustness and interpretabilty of learned representations directly in convolutional filters and indirectly with attribution methods.

Item Type: Paper
Subjects: bioinformatics > genomics and proteomics > genetics & nucleic acid processing > genomes
bioinformatics > computational biology > algorithms > machine learning
CSHL Authors:
Communities: CSHL labs > Koo Lab
SWORD Depositor: CSHL Elements
Depositing User: CSHL Elements
Date: March 2021
Date Deposited: 07 May 2021 20:10
Last Modified: 07 May 2021 20:10
Related URLs:
URI: https://repository.cshl.edu/id/eprint/40065

Actions (login required)

Administrator's edit/view item Administrator's edit/view item
CSHL HomeAbout CSHLResearchEducationNews & FeaturesCampus & Public EventsCareersGiving