Parameter estimation from phylogenetic trees using neural networks and ensemble learning

Species diversification is characterized by speciation and extinction, the rates of which can, under some assumptions, be estimated from time-calibrated phylogenies. However, maximum likelihood estimation methods (MLE) for inferring rates are limited to simpler models and can show bias, particularly in small phylogenies. Likelihood-free methods to estimate parameters of diversification models using deep learning have started to emerge, but how robust neural network methods are at handling the intricate nature of phylogenetic data remains an open question. Here, we present a new ensemble neural network approach to estimate diversification parameters from phylogenetic trees that leverages different classes of neural networks (dense neural network, graph neural network, and long short-term memory recurrent network) and simultaneously learns from graph representations of phylogenies, their branching times, and their summary statistics. Our best-performing ensemble neural network (which adju..., , , # Data from: Parameter estimation from phylogenetic trees using neural networks and ensemble learning

[https://doi.org/10.1093/sysbio/syaf060](https://doi.org/10.1093/sysbio/syaf060)

## Description of the data and file structure

* We are providing all of our research outputs from a complete run, which includes simulation, maximum likelihood estimation, neural network training, and testing from our computing cluster. The outputs are contained in two files: an R workspace and an R script file. To reproduce the figures presented in our paper, please load the workspace using your preferred R-compatible IDE and run the code provided in the R script file.

* For all functions and scripts related to simulations, maximum likelihood estimation, and neural network training and testing, please refer to our codebase hosted at [EvoLandEco/eveGNN: Codebase for Phylogenetic Tree Parameter Estimation with Neural Networks (github.com)](https://github.com/EvoLandEco/eveGNN)

* For illustration on usin...,

物种分化以物种形成与灭绝为核心特征，在特定假设前提下，可通过时间校准的系统发育树（time-calibrated phylogenies）对其发生速率进行估算。然而，用于推断分化速率的最大似然估计法（maximum likelihood estimation, MLE）仅适用于简化模型，且易产生估计偏差，在小型系统发育树场景中尤为显著。近年来，借助深度学习开展物种分化模型参数估计的无似然方法逐渐兴起，但神经网络方法在处理系统发育数据复杂特性时的稳健性仍属待解问题。
本研究提出一种全新的集成神经网络方法，用于从系统发育树中估算物种分化参数：该方法整合了三类神经网络——全连接神经网络（dense neural network）、图神经网络（graph neural network）与长短期记忆循环神经网络（long short-term memory recurrent network），并同时从系统发育树的图表示、分支时间及其汇总统计量中学习特征信息。本研究表现最优的集成神经网络（调整细节暂略……）# 数据来源：基于神经网络与集成学习的系统发育树参数估计
https://doi.org/10.1093/sysbio/syaf060

## 数据与文件结构说明
* 本研究提供了计算集群上完整运行流程生成的全部研究成果，涵盖模拟实验、最大似然估计、神经网络训练与测试环节。所有成果存储于两个文件中：一个R工作空间文件与一个R脚本文件。若需复现论文中展示的图表，请使用支持R的集成开发环境加载该工作空间，并运行R脚本文件中提供的代码。
* 所有与模拟实验、最大似然估计、神经网络训练与测试相关的函数及脚本，请参见本研究托管于[EvoLandEco/eveGNN: 基于神经网络的系统发育树参数估计代码库 (github.com)](https://github.com/EvoLandEco/eveGNN)的代码仓库。
* 关于使用方法的示例说明……