Generative Adversarial Networks for Omics Data: An Overview and Future Directions for Livestock Applications
- 1Department of Animal Sciences University of Illinois at Urbana‐Champaign Urbana Illinois USA
- 2Center for Digital Agriculture University of Illinois at Urbana‐Champaign Urbana Illinois USA
Abstract
Generative adversarial networks (GANs) are artificial intelligence models designed to generate novel data that is indistinguishable from real data. Originally developed to generate images to complement existing datasets and create more diverse samples, GAN‐based data can enhance downstream analysis for machine learning and deep learning applications. GAN‐based approaches are also versatile and suitable for augmenting omics data, improving downstream analyses such as genotype prediction, biomarker detection, and protein de novo design. In addition, GANs can preserve and reconstruct genomic regions under selective pressure, increase sample sizes from underrepresented groups, and mitigate class imbalance effects in genomic analyses, transcriptomics, and single‐cell omics. Recent work also demonstrates that GAN‐generated data can support privacy‐preserving data sharing and the design of novel biological sequences and proteins. This literature review presents the foundational concepts of GANs, explores diverse applications across omics fields, and highlights novel opportunities for applying GAN approaches in livestock genomics.
Related
- Hi-cGAN: Prediction of Hi-C interaction matrices with conditional generative adversarial networks
- Conditional Generative Adversarial Network for the simulation of seabird trajectories based on environmental data
- DHAFGan: A dense hybrid attention fusion generative adversarial network for infrared and visible image fusion
- Long Non-Coding RNAs: Key Regulators of Economic Traits in Livestock From Mechanisms to Breeding Applications.
- From Movement to Spread: Generating Livestock Contact Networks that Preserve Infection Dynamics
BibTeX
@article{vargas2026generative,
title = {{Generative Adversarial Networks for Omics Data: An Overview and Future Directions for Livestock Applications}},
author = {Edgar Caballero Vargas and Tiago Bresolin},
journal = {Animal Genetics},
year = {2026},
month = oct,
doi = {10.1002/age.70226},
url = {https://doi.org/10.1002/age.70226},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Generative Adversarial Networks for Omics Data: An Overview and Future Directions for Livestock Applications
AU - Edgar Caballero Vargas
AU - Tiago Bresolin
PY - 2026
DA - 2026/10/27
JO - Animal Genetics
DO - 10.1002/age.70226
UR - https://doi.org/10.1002/age.70226
AB - Generative adversarial networks (GANs) are artificial intelligence models designed to generate novel data that is indistinguishable from real data. Originally developed to generate images to complement existing datasets and create more diverse samples, GAN‐based data can enhance downstream analysis for machine learning and deep learning applications. GAN‐based approaches are also versatile and suitable for augmenting omics data, improving downstream analyses such as genotype prediction, biomarker detection, and protein de novo design. In addition, GANs can preserve and reconstruct genomic regions under selective pressure, increase sample sizes from underrepresented groups, and mitigate class imbalance effects in genomic analyses, transcriptomics, and single‐cell omics. Recent work also demonstrates that GAN‐generated data can support privacy‐preserving data sharing and the design of novel biological sequences and proteins. This literature review presents the foundational concepts of GANs, explores diverse applications across omics fields, and highlights novel opportunities for applying GAN approaches in livestock genomics.
SN - 0268-9146
SN - 1365-2052
ER -