Dispersal inference from population genetic variation using a convolutional neural network.

Dispersal inference from population genetic variation using a convolutional neural network.
复制标题

DOI:
10.1093/genetics/iyad068
复制
发表时间:
2023-05-26
期刊:
影响因子:
3.3
通讯作者:
Kern, Andrew D.
Kern, Andrew D.
中科院分区:
生物学2区
文献类型:
--
作者:
Smith, Chris C. R.;Tittes, Silas;Ralph, Peter L.;Kern, Andrew D.

文献摘要

参考文献

被引文献

相似文献

生物扩散的地理性质塑造了景观遗传变异的模式,使得从遗传变异数据推断扩散特性成为可能。在这里,我们提出了一个推理工具,它使用地理分布的基因型数据与卷积神经网络相结合来估计一个关键的种群参数:平均每代扩散距离。通过大量的模拟,我们证明了我们的深度学习方法与最先进的方法相比具有竞争力或优于最先进的方法,特别是在小样本量的情况下。此外,我们在训练过程中评估不同的滋扰参数,包括人口密度,人口统计学的历史,栖息地的大小,和采样面积,并表明这种策略是有效的估计扩散距离时,其他模型参数是未知的。而竞争的方法依赖于当地的人口密度或准确推断的身份由血统道的信息,我们的方法只使用单核苷酸多态性数据和采样的空间尺度作为输入。引人注目的是,与其他方法不同,我们的方法不使用基因型个体的地理坐标。这些功能使我们的方法,我们称之为“disperseNN”,一个潜在的有价值的新工具,用于估计扩散距离的非模型系统与全基因组数据或减少代表性数据。我们将disperseNN应用于12个不同的物种,并提供了公开的数据,对大多数物种进行了合理的估计。重要的是,我们的方法估计一致较大的传播距离比标记-重捕计算在同一物种,这可能是由于有限的地理采样区域所涵盖的一些标记-重捕研究。因此,像我们这样的遗传工具补充了直接方法,以提高我们对传播的理解。
The geographic nature of biological dispersal shapes patterns of genetic variation over landscapes, making it possible to infer properties of dispersal from genetic variation data. Here, we present an inference tool that uses geographically distributed genotype data in combination with a convolutional neural network to estimate a critical population parameter: the mean per-generation dispersal distance. Using extensive simulation, we show that our deep learning approach is competitive with or outperforms state-of-the-art methods, particularly at small sample sizes. In addition, we evaluate varying nuisance parameters during training—including population density, demographic history, habitat size, and sampling area—and show that this strategy is effective for estimating dispersal distance when other model parameters are unknown. Whereas competing methods depend on information about local population density or accurate inference of identity-by-descent tracts, our method uses only single-nucleotide-polymorphism data and the spatial scale of sampling as input. Strikingly, and unlike other methods, our method does not use the geographic coordinates of the genotyped individuals. These features make our method, which we call “disperseNN,” a potentially valuable new tool for estimating dispersal distance in nonmodel systems with whole genome data or reduced representation data. We apply disperseNN to 12 different species with publicly available data, yielding reasonable estimates for most species. Importantly, our method estimated consistently larger dispersal distances than mark-recapture calculations in the same species, which may be due to the limited geographic sampling area covered by some mark-recapture studies. Thus genetic tools like ours complement direct methods for improving our understanding of dispersal.
DOI: 10.1534/genetics.116.197632
发表时间: 2017-04
期刊: Genetics
影响因子: 3.3
作者:
Beaghton A;Hammond A;Nolan T;Crisanti A;Godfray HC;Burt A
通讯作者: Burt A
DOI: 10.1371/journal.pone.0003376
发表时间: 2008
期刊: PloS one
影响因子: 3.7
作者:
Baird NA;Etter PD;Atwood TS;Currey MC;Shiver AL;Lewis ZA;Selker EU;Cresko WA;Johnson EA
通讯作者: Johnson EA
DOI: 10.1016/j.tpb.2015.11.005
发表时间: 2016-04-01
影响因子: 1.4
作者:
Beaghton, Andrea;Beaghton, Pantelis John;Burt, Austin
通讯作者: Burt, Austin
DOI: 10.1093/molbev/msaa038
发表时间: 2020-06-01
影响因子: 10.7
作者:
Adrion, Jeffrey R.;Galloway, Jared G.;Kern, Andrew D.
通讯作者: Kern, Andrew D.
DOI: 10.1006/tpbi.2001.1557
发表时间: 2002-02-01
影响因子: 1.4
作者:
Barton, NH;Depaulis, F;Etheridge, AM
通讯作者: Etheridge, AM