A Novel Approach Utilizing Domain Adversarial Neural Networks for the Detection and Classification of Selective Sweeps

Hui Song; Jinyu Chu; Wangjiao Li; Xinyun Li; Lingzhao Fang; Jianlin Han; Shuhong Zhao; Yunlong Ma

doi:10.1002/advs.202304842

A Novel Approach Utilizing Domain Adversarial Neural Networks for the Detection and Classification of Selective Sweeps

Hui Song, Jinyu Chu, Wangjiao Li, Xinyun Li, Lingzhao Fang, Jianlin Han, Shuhong Zhao^*, Yunlong Ma^*

^*Corresponding author af dette arbejde

Center for Kvantitativ Genetik og Genomforskning, Aarhus

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

2 Citationer (Scopus)

Abstract

The identification and classification of selective sweeps are of great significance for improving the understanding of biological evolution and exploring opportunities for precision medicine and genetic improvement. Here, a domain adaptation sweep detection and classification (DASDC) method is presented to balance the alignment of two domains and the classification performance through a domain-adversarial neural network and its adversarial learning modules. DASDC effectively addresses the issue of mismatch between training data and real genomic data in deep learning models, leading to a significant improvement in its generalization capability, prediction robustness, and accuracy. The DASDC method demonstrates improved identification performance compared to existing methods and excels in classification performance, particularly in scenarios where there is a mismatch between application data and training data. The successful implementation of DASDC in real data of three distinct species highlights its potential as a useful tool for identifying crucial functional genes and investigating adaptive evolutionary mechanisms, particularly with the increasing availability of genomic data.

Originalsprog	Engelsk
Artikelnummer	2304842
Tidsskrift	Advanced Science
Vol/bind	11
Nummer	14
ISSN	2198-3844
DOI	https://doi.org/10.1002/advs.202304842
Status	Udgivet - apr. 2024

Adgang til dokumentet

10.1002/advs.202304842

Andre filer og links

Link to publication in Scopus

Citationsformater

@article{7b93479a948a4ce3b09b844512256b6f,

title = "A Novel Approach Utilizing Domain Adversarial Neural Networks for the Detection and Classification of Selective Sweeps",

abstract = "The identification and classification of selective sweeps are of great significance for improving the understanding of biological evolution and exploring opportunities for precision medicine and genetic improvement. Here, a domain adaptation sweep detection and classification (DASDC) method is presented to balance the alignment of two domains and the classification performance through a domain-adversarial neural network and its adversarial learning modules. DASDC effectively addresses the issue of mismatch between training data and real genomic data in deep learning models, leading to a significant improvement in its generalization capability, prediction robustness, and accuracy. The DASDC method demonstrates improved identification performance compared to existing methods and excels in classification performance, particularly in scenarios where there is a mismatch between application data and training data. The successful implementation of DASDC in real data of three distinct species highlights its potential as a useful tool for identifying crucial functional genes and investigating adaptive evolutionary mechanisms, particularly with the increasing availability of genomic data.",

keywords = "deep learning, domain adaptation, genomics, robustness, selective sweep, Biological Evolution, Neural Networks, Computer, Genomics",

author = "Hui Song and Jinyu Chu and Wangjiao Li and Xinyun Li and Lingzhao Fang and Jianlin Han and Shuhong Zhao and Yunlong Ma",

note = "Publisher Copyright: {\textcopyright} 2024 The Authors. Advanced Science published by Wiley-VCH GmbH.",

year = "2024",

month = apr,

doi = "10.1002/advs.202304842",

language = "English",

volume = "11",

journal = "Advanced Science",

issn = "2198-3844",

publisher = "John Wiley & Sons Inc.",

number = "14",

}

TY - JOUR

T1 - A Novel Approach Utilizing Domain Adversarial Neural Networks for the Detection and Classification of Selective Sweeps

AU - Song, Hui

AU - Chu, Jinyu

AU - Li, Wangjiao

AU - Li, Xinyun

AU - Fang, Lingzhao

AU - Han, Jianlin

AU - Zhao, Shuhong

AU - Ma, Yunlong

PY - 2024/4

Y1 - 2024/4

N2 - The identification and classification of selective sweeps are of great significance for improving the understanding of biological evolution and exploring opportunities for precision medicine and genetic improvement. Here, a domain adaptation sweep detection and classification (DASDC) method is presented to balance the alignment of two domains and the classification performance through a domain-adversarial neural network and its adversarial learning modules. DASDC effectively addresses the issue of mismatch between training data and real genomic data in deep learning models, leading to a significant improvement in its generalization capability, prediction robustness, and accuracy. The DASDC method demonstrates improved identification performance compared to existing methods and excels in classification performance, particularly in scenarios where there is a mismatch between application data and training data. The successful implementation of DASDC in real data of three distinct species highlights its potential as a useful tool for identifying crucial functional genes and investigating adaptive evolutionary mechanisms, particularly with the increasing availability of genomic data.

AB - The identification and classification of selective sweeps are of great significance for improving the understanding of biological evolution and exploring opportunities for precision medicine and genetic improvement. Here, a domain adaptation sweep detection and classification (DASDC) method is presented to balance the alignment of two domains and the classification performance through a domain-adversarial neural network and its adversarial learning modules. DASDC effectively addresses the issue of mismatch between training data and real genomic data in deep learning models, leading to a significant improvement in its generalization capability, prediction robustness, and accuracy. The DASDC method demonstrates improved identification performance compared to existing methods and excels in classification performance, particularly in scenarios where there is a mismatch between application data and training data. The successful implementation of DASDC in real data of three distinct species highlights its potential as a useful tool for identifying crucial functional genes and investigating adaptive evolutionary mechanisms, particularly with the increasing availability of genomic data.

KW - deep learning

KW - domain adaptation

KW - genomics

KW - robustness

KW - selective sweep

KW - Biological Evolution

KW - Neural Networks, Computer

KW - Genomics

UR - http://www.scopus.com/inward/record.url?scp=85183771105&partnerID=8YFLogxK

U2 - 10.1002/advs.202304842

DO - 10.1002/advs.202304842

M3 - Journal article

C2 - 38308186

AN - SCOPUS:85183771105

SN - 2198-3844

VL - 11

JO - Advanced Science

JF - Advanced Science

IS - 14

M1 - 2304842

ER -

A Novel Approach Utilizing Domain Adversarial Neural Networks for the Detection and Classification of Selective Sweeps

Abstract

Adgang til dokumentet

Andre filer og links

Fingeraftryk

Citationsformater