Detecting adaptive introgression in human evolution using convolutional neural networks
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Detecting adaptive introgression in human evolution using convolutional neural networks. / Gower, Graham; Iáñez Picazo, Pablo; Fumagalli, Matteo; Racimo, Fernando.
In: eLife, Vol. 10, e64669, 2021.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Detecting adaptive introgression in human evolution using convolutional neural networks
AU - Gower, Graham
AU - Iáñez Picazo, Pablo
AU - Fumagalli, Matteo
AU - Racimo, Fernando
PY - 2021
Y1 - 2021
N2 - Studies in a variety of species have shown evidence for positively selected variants introduced into a population via introgression from another, distantly related population-a process known as adaptive introgression. However, there are few explicit frameworks for jointly modelling introgression and positive selection, in order to detect these variants using genomic sequence data. Here, we develop an approach based on convolutional neural networks (CNNs). CNNs do not require the specification of an analytical model of allele frequency dynamics and have outperformed alternative methods for classification and parameter estimation tasks in various areas of population genetics. Thus, they are potentially well suited to the identification of adaptive introgression. Using simulations, we trained CNNs on genotype matrices derived from genomes sampled from the donor population, the recipient population and a related non-introgressed population, in order to distinguish regions of the genome evolving under adaptive introgression from those evolving neutrally or experiencing selective sweeps. Our CNN architecture exhibits 95% accuracy on simulated data, even when the genomes are unphased, and accuracy decreases only moderately in the presence of heterosis. As a proof of concept, we applied our trained CNNs to human genomic datasets-both phased and unphased-to detect candidates for adaptive introgression that shaped our evolutionary history.
AB - Studies in a variety of species have shown evidence for positively selected variants introduced into a population via introgression from another, distantly related population-a process known as adaptive introgression. However, there are few explicit frameworks for jointly modelling introgression and positive selection, in order to detect these variants using genomic sequence data. Here, we develop an approach based on convolutional neural networks (CNNs). CNNs do not require the specification of an analytical model of allele frequency dynamics and have outperformed alternative methods for classification and parameter estimation tasks in various areas of population genetics. Thus, they are potentially well suited to the identification of adaptive introgression. Using simulations, we trained CNNs on genotype matrices derived from genomes sampled from the donor population, the recipient population and a related non-introgressed population, in order to distinguish regions of the genome evolving under adaptive introgression from those evolving neutrally or experiencing selective sweeps. Our CNN architecture exhibits 95% accuracy on simulated data, even when the genomes are unphased, and accuracy decreases only moderately in the presence of heterosis. As a proof of concept, we applied our trained CNNs to human genomic datasets-both phased and unphased-to detect candidates for adaptive introgression that shaped our evolutionary history.
KW - adaptive introgression
KW - computational biology
KW - genetics
KW - genomics
KW - human
KW - machine learning
KW - simulation
KW - systems biology
U2 - 10.7554/eLife.64669
DO - 10.7554/eLife.64669
M3 - Journal article
C2 - 34032215
AN - SCOPUS:85108123849
VL - 10
JO - eLife
JF - eLife
SN - 2050-084X
M1 - e64669
ER -
ID: 273366204