Chromosome-scale inference of hybrid speciation and admixture with convolutional neural networks.
Chromosome-scale inference of hybrid speciation and admixture with convolutional neural networks.
复制标题
DOI：
10.1111/1755-0998.13355
复制
发表时间：
2021-11
影响因子：
7.7
通讯作者：
Gutenkunst RN
中科院分区：
文献类型：
--
作者：
Blischak PD;Barker MS;Gutenkunst RN
推断密切相关的生物之间杂交的频率和模式是理解物种形成过程的重要一步，并且可以帮助更普遍地揭示物种发生的网状模式。测试杂交存在的系统基因组方法有许多种类，并且通常通过在没有杂交的情况下利用预期的系谱不一致模式来操作。这些测试所做的一个重要假设是，数据（基因或SNP）在给定物种树的情况下是独立的。然而，当数据紧密相连时，考虑其非独立性尤为重要。最近，卷积神经网络（CNN）等深度学习技术已被用于执行群体遗传推断，其中关联的SNP被编码为二进制图像。在这里，我们使用CNN在候选杂交场景中进行选择，使用树拓扑（（（P1，P2），P3），Out）和在整个基因组的窗口中计算的成对核苷酸分歧矩阵（dXY）。使用合并模拟来训练和独立测试神经网络表明，我们的方法HyDe-CNN能够在广泛的参数空间中准确地执行混合场景的模型选择。然后，我们使用HyDe-CNN来测试Heliconius蝴蝶中的混合模型，并将其与基于遗传的渐渗统计进行比较。考虑到我们方法的灵活性，长读序测序成本的下降以及CNN架构的持续改进，我们预计使用像我们这样的深度学习方法进行杂交推断将有助于研究人员更好地了解他们研究生物体中的混合模式。
Inferring the frequency and mode of hybridization among closely related organisms is an important step for understanding the process of speciation, and can help to uncover reticulated patterns of phylogeny more generally. Phylogenomic methods to test for the presence of hybridization come in many varieties, and typically operate by leveraging expected patterns of genealogical discordance in the absence of hybridization. An important assumption made by these tests is that the data (genes or SNPs) are independent given the species tree. However, when the data are closely linked, it is especially important to consider their non-independence. Recently, deep learning techniques such as convolutional neural networks (CNNs) have been used to perform population genetic inferences with linked SNPs coded as binary images. Here we use CNNs for selecting among candidate hybridization scenarios using the tree topology (((P1, P2), P3), Out) and a matrix of pairwise nucleotide divergence (dXY) calculated in windows across the genome. Using coalescent simulations to train and independently test a neural network showed that our method, HyDe-CNN, was able to accurately perform model selection for hybridization scenarios across a wide-breath of parameter space. We then used HyDe-CNN to test models of admixture in Heliconius butterflies, as well as comparing it to phylogeny-based introgression statistics. Given the flexibility of our approach, the dropping cost of long-read sequencing, and the continued improvement of CNN architectures, we anticipate that inferences of hybridization using deep learning methods like ours will help researchers to better understand patterns of admixture in their study organisms.
登录
查看更多内容
影响因子：
64.8
作者：
Dasmahapatra, Kanchon K.;Walters, James R.;Briscoe, Adriana D.;Davey, John W.;Whibley, Annabel;Nadeau, Nicola J.;Zimin, Aleksey V.;Hughes, Daniel S. T.;Ferguson, Laura C.;Martin, Simon H.;Salazar, Camilo;Lewis, James J.;Adler, Sebastian;Ahn, Seung-Joon;Baker, Dean A.;Baxter, Simon W.;Chamberlain, Nicola L.;Chauhan, Ritika;Counterman, Brian A.;Dalmay, Tamas;Gilbert, Lawrence E.;Gordon, Karl;Heckel, David G.;Hines, Heather M.;Hoff, Katharina J.;Holland, Peter W. H.;Jacquin-Joly, Emmanuelle;Jiggins, Francis M.;Jones, Robert T.;Kapan, Durrell D.;Kersey, Paul;Lamas, Gerardo;Lawson, Daniel;Mapleson, Daniel;Maroja, Luana S.;Martin, Arnaud;Moxon, Simon;Palmer, William J.;Papa, Riccardo;Papanicolaou, Alexie;Pauchet, Yannick;Ray, David A.;Rosser, Neil;Salzberg, Steven L.;Supple, Megan A.;Surridge, Alison;Tenger-Trolander, Ayse;Vogel, Heiko;Wilkinson, Paul A.;Wilson, Derek;Yorke, James A.;Yuan, Furong;Balmuth, Alexi L.;Eland, Cathlene;Gharbi, Karim;Thomson, Marian;Gibbs, Richard A.;Han, Yi;Jayaseelan, Joy C.;Kovar, Christie;Mathew, Tittu;Muzny, Donna M.;Ongeri, Fiona;Pu, Ling-Ling;Qu, Jiaxin;Thornton, Rebecca L.;Worley, Kim C.;Wu, Yuan-Qing;Linares, Mauricio;Blaxter, Mark L.;Ffrench-Constant, Richard H.;Joron, Mathieu;Kronforst, Marcus R.;Mullen, Sean P.;Reed, Robert D.;Scherer, Steven E.;Richards, Stephen;Mallet, James;McMillan, W. Owen;Jiggins, Chris D.
通讯作者：
Jiggins, Chris D.
影响因子：
6.5
作者：
Blischak, Paul D.;Chifman, Julia;Kubatko, Laura S.
通讯作者：
Kubatko, Laura S.
影响因子：
10.7
作者：
Adrion, Jeffrey R.;Galloway, Jared G.;Kern, Andrew D.
通讯作者：
Kern, Andrew D.
影响因子：
10.7
作者：
Flagel, Lex;Brandvain, Yaniv;Schrider, Daniel R.
通讯作者：
Schrider, Daniel R.
DOI：
10.1126/science.1188021
发表时间：
2010-05-07
期刊：
Science (New York, N.Y.)
影响因子：
--
作者：
Green RE;Krause J;Briggs AW;Maricic T;Stenzel U;Kircher M;Patterson N;Li H;Zhai W;Fritz MH;Hansen NF;Durand EY;Malaspinas AS;Jensen JD;Marques-Bonet T;Alkan C;Prüfer K;Meyer M;Burbano HA;Good JM;Schultz R;Aximu-Petri A;Butthof A;Höber B;Höffner B;Siegemund M;Weihmann A;Nusbaum C;Lander ES;Russ C;Novod N;Affourtit J;Egholm M;Verna C;Rudan P;Brajkovic D;Kucan Ž;Gušic I;Doronichev VB;Golovanova LV;Lalueza-Fox C;de la Rasilla M;Fortea J;Rosas A;Schmitz RW;Johnson PLF;Eichler EE;Falush D;Birney E;Mullikin JC;Slatkin M;Nielsen R;Kelso J;Lachmann M;Reich D;Pääbo S
通讯作者：
Pääbo S