Deciphering signatures of natural selection via deep learning

Xinghu Qin; Charleston Chiang; Oscar Eduardo Gaggiotti

doi:10.1093/bib/bbac354

Deciphering signatures of natural selection via deep learning

Xinghu Qin^*, Charleston Chiang, Oscar Eduardo Gaggiotti^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

Identifying genomic regions influenced by natural selection provides fundamental insights into the genetic basis of local adaptation. However, it remains challenging to detect loci under complex spatially varying selection. We propose a deep learning-based framework, DeepGenomeScan, which can detect signatures of spatially varying selection. We demonstrate that DeepGenomeScan outperformed principal component analysis- and redundancy analysis-based genome scans in identifying loci underlying quantitative traits subject to complex spatial patterns of selection. Noticeably, DeepGenomeScan increases statistical power by up to 47.25% under nonlinear environmental selection patterns. We applied DeepGenomeScan to a European human genetic dataset and identified some well-known genes under selection and a substantial number of clinically important genes that were not identified by SPA, iHS, Fst and Bayenv when applied to the same dataset.

Original language	English
Article number	bbac354
Number of pages	10
Journal	Briefings in Bioinformatics
Volume	23
Issue number	5
Early online date	2 Sept 2022
DOIs	https://doi.org/10.1093/bib/bbac354
Publication status	Published - Sept 2022

Keywords

Deep learning
Genome scan
Genome-wide association studies
Signatures of natural selection

Access to Document

10.1093/bib/bbac354Licence: CC BY-NC

Qin_2022_Bib_Deciphering-signatures_CC
Copyright © The Author(s) 2022. Published by Oxford University Press. This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (https://creativecommons.org/licenses/by-nc/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited. For commercial re-use, please contact [email protected].
Final published version, 1.02 MBLicence: CC BY-NC

Deciphering signatures of natural selection via deep learning (code)
Gaggiotti, O. E. (Creator), GitHub, 2022
https://github.com/xinghuq/DeepGenomeScan
Dataset: Software

Cite this

@article{15dab49e2c554b52b5f516dfba3cd2b8,

title = "Deciphering signatures of natural selection via deep learning",

abstract = "Identifying genomic regions influenced by natural selection provides fundamental insights into the genetic basis of local adaptation. However, it remains challenging to detect loci under complex spatially varying selection. We propose a deep learning-based framework, DeepGenomeScan, which can detect signatures of spatially varying selection. We demonstrate that DeepGenomeScan outperformed principal component analysis- and redundancy analysis-based genome scans in identifying loci underlying quantitative traits subject to complex spatial patterns of selection. Noticeably, DeepGenomeScan increases statistical power by up to 47.25% under nonlinear environmental selection patterns. We applied DeepGenomeScan to a European human genetic dataset and identified some well-known genes under selection and a substantial number of clinically important genes that were not identified by SPA, iHS, Fst and Bayenv when applied to the same dataset.",

keywords = "Deep learning, Genome scan, Genome-wide association studies, Signatures of natural selection",

author = "Xinghu Qin and Charleston Chiang and Gaggiotti, {Oscar Eduardo}",

note = "XQ was supported by a PhD scholarship from the China Scholarship Council and now is supported by International Postdoctoral Exchange Fellowship Program (Talent-Introduction Program) from China Postdoc Council. CWKC is supported in part by National Institute of General Medical Sciences (NIGMS) of the National Institute of Health (award number R35GM142783). Computation for this work is supported in part by USC{\textquoteright}s Center for Advanced Research Computing (https://www.carc.usc.edu/). ",

year = "2022",

month = sep,

doi = "10.1093/bib/bbac354",

language = "English",

volume = "23",

journal = "Briefings in Bioinformatics",

issn = "1467-5463",

publisher = "Oxford University Press",

number = "5",

}

TY - JOUR

T1 - Deciphering signatures of natural selection via deep learning

AU - Qin, Xinghu

AU - Chiang, Charleston

AU - Gaggiotti, Oscar Eduardo

N1 - XQ was supported by a PhD scholarship from the China Scholarship Council and now is supported by International Postdoctoral Exchange Fellowship Program (Talent-Introduction Program) from China Postdoc Council. CWKC is supported in part by National Institute of General Medical Sciences (NIGMS) of the National Institute of Health (award number R35GM142783). Computation for this work is supported in part by USC’s Center for Advanced Research Computing (https://www.carc.usc.edu/).

PY - 2022/9

Y1 - 2022/9

N2 - Identifying genomic regions influenced by natural selection provides fundamental insights into the genetic basis of local adaptation. However, it remains challenging to detect loci under complex spatially varying selection. We propose a deep learning-based framework, DeepGenomeScan, which can detect signatures of spatially varying selection. We demonstrate that DeepGenomeScan outperformed principal component analysis- and redundancy analysis-based genome scans in identifying loci underlying quantitative traits subject to complex spatial patterns of selection. Noticeably, DeepGenomeScan increases statistical power by up to 47.25% under nonlinear environmental selection patterns. We applied DeepGenomeScan to a European human genetic dataset and identified some well-known genes under selection and a substantial number of clinically important genes that were not identified by SPA, iHS, Fst and Bayenv when applied to the same dataset.

AB - Identifying genomic regions influenced by natural selection provides fundamental insights into the genetic basis of local adaptation. However, it remains challenging to detect loci under complex spatially varying selection. We propose a deep learning-based framework, DeepGenomeScan, which can detect signatures of spatially varying selection. We demonstrate that DeepGenomeScan outperformed principal component analysis- and redundancy analysis-based genome scans in identifying loci underlying quantitative traits subject to complex spatial patterns of selection. Noticeably, DeepGenomeScan increases statistical power by up to 47.25% under nonlinear environmental selection patterns. We applied DeepGenomeScan to a European human genetic dataset and identified some well-known genes under selection and a substantial number of clinically important genes that were not identified by SPA, iHS, Fst and Bayenv when applied to the same dataset.

KW - Deep learning

KW - Genome scan

KW - Genome-wide association studies

KW - Signatures of natural selection

U2 - 10.1093/bib/bbac354

DO - 10.1093/bib/bbac354

M3 - Article

SN - 1467-5463

VL - 23

JO - Briefings in Bioinformatics

JF - Briefings in Bioinformatics

IS - 5

M1 - bbac354

ER -

Deciphering signatures of natural selection via deep learning

Abstract

Keywords

Access to Document

Fingerprint

Datasets

Deciphering signatures of natural selection via deep learning (code)

Cite this