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

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 gen...

Full description

Saved in:
Bibliographic Details
Published in:Genome Biology 2023-05, Vol.24 (1), p.105-14, Article 105
Main Authors: Lee, Nicholas Keone, Tang, Ziqi, Toneyan, Shushan, Koo, Peter K
Format: Article
Language:English
Subjects:
Bias
Binding sites
Biology
Curricula
Data augmentations
Datasets
Deep learning
Evolution
Genetic diversity
Genetic transformation
Genomics
Genomics - methods
Model interpretability
Mutagenesis
Neural networks
Neural Networks, Computer
Nucleotide sequence
Regulatory genomics
Short Report
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1474-760X
1474-7596
1474-760X
DOI:10.1186/s13059-023-02941-w