EvoAug: improving generalization and interpretability of genomic deep neural networks with evolution-inspired data augmentations

Lee, Nicholas Keone, Tang, Ziqi, Toneyan, Shushan, Koo, Peter K (May 2023) EvoAug: improving generalization and interpretability of genomic deep neural networks with evolution-inspired data augmentations. Genome Biology, 24 (1). p. 105. ISSN 1474-760X

PDF EvoAug improving generalization and interpretability of genomic deep neural networks with evolution-inspired data augmentati.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB)

Abstract

Deep neural networks (DNNs) hold promise for functional genomics prediction, but their generalization capability may be limited by the amount of available data. To address this, we propose EvoAug, a suite of evolution-inspired augmentations that enhance the training of genomic DNNs by increasing genetic variation. Random transformation of DNA sequences can potentially alter their function in unknown ways, so we employ a fine-tuning procedure using the original non-transformed data to preserve functional integrity. Our results demonstrate that EvoAug substantially improves the generalization and interpretability of established DNNs across prominent regulatory genomics prediction tasks, offering a robust solution for genomic DNNs.

Item Type:	Paper
Subjects:	bioinformatics bioinformatics > genomics and proteomics evolution organs, tissues, organelles, cell types and functions > tissues types and functions > neural networks
CSHL Authors:	Tang, Ziqi Toneyan, Shushan Koo, Peter K Lee, Nicholas
Communities:	CSHL Cancer Center Program CSHL Cancer Center Program > Gene Regulation and Inheritance Program CSHL labs > Koo Lab School of Biological Sciences > Publications
SWORD Depositor:	CSHL Elements
Depositing User:	CSHL Elements
Date:	5 May 2023
Date Deposited:	28 Sep 2023 19:29
Last Modified:	29 Feb 2024 18:12
PMCID:	PMC10161416
Related URLs:	Publisher
URI:	https://repository.cshl.edu/id/eprint/41047

Actions (login required)

Administrator's edit/view item