Novel symmetry-preserving neural network model for phylogenetic inference
Novel symmetry-preserving neural network model for phylogenetic inference
复制标题
DOI：
10.1093/bioadv/vbae022
复制
发表时间：
2024-04-18
期刊：
影响因子：
--
通讯作者：
Solis-Lemus，Claudia
中科院分区：
文献类型：
--
作者：
Tang，Xudong;Zepeda-Nunez，Leonardo;Solis-Lemus，Claudia
全世界的科学家们正在共同努力，以了解我们在地球上看到的生物多样性是如何从生命起源的单细胞生物进化而来的，这一多样化过程通过生命之树来表示。低采样率和高异质性的进化速度跨网站和谱系产生的现象表示“长分支吸引力”（LBA），其中长非姐妹谱系估计为姐妹篇，而不管他们真正的进化关系。LBA一直是一个普遍存在的问题，影响不同类型的方法，从距离为基础的系统发育推断的可能性based.ResultsHere，我们提出了一种新的神经网络模型，优于标准的系统发育方法和其他神经网络的实现下LBA设置。此外，与遗传学中现有的神经网络模型不同，我们的模型通过置换不变函数自然地解释了树的同构，这最终导致更低的内存，并允许无缝扩展到更大的trees.Availability和implementationWe实现我们的新理论上的开源公开可用的GitHub存储库：https://github.com/crsl4/nn-phylogenetics。
MotivationScientists world-wide are putting together massive efforts to understand how the biodiversity that we see on Earth evolved from single-cell organisms at the origin of life and this diversification process is represented through the Tree of Life. Low sampling rates and high heterogeneity in the rate of evolution across sites and lineages produce a phenomenon denoted “long branch attraction” (LBA) in which long nonsister lineages are estimated to be sisters regardless of their true evolutionary relationship. LBA has been a pervasive problem in phylogenetic inference affecting different types of methodologies from distance-based to likelihood-based.ResultsHere, we present a novel neural network model that outperforms standard phylogenetic methods and other neural network implementations under LBA settings. Furthermore, unlike existing neural network models in phylogenetics, our model naturally accounts for the tree isomorphisms via permutation invariant functions which ultimately result in lower memory and allows the seamless extension to larger trees.Availability and implementationWe implement our novel theory on an open-source publicly available GitHub repository: https://github.com/crsl4/nn-phylogenetics.