Fast and flexible Bayesian phylogenetics via modern machine learning

通过现代机器学习快速灵活的贝叶斯系统发育学

基本信息

批准号：
10266670
负责人：
Frederick Albert Matsen
金额：
$ 32.13万
依托单位：
FRED HUTCHINSON CANCER RESEARCH CENTER
依托单位国家：
美国
项目类别：
财政年份：
2021
资助国家：
美国
起止时间：
2021-07-01 至 2022-03-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10266670
关键词：
Age Algorithms Back Bayesian Method COVID-19 pandemic Code Collection Complex Computational Biology Custom Data Data Set Diagnostic Discipline Disease Disease Outbreaks Epidemic Foundations Functional disorder Genome Graph Heterogeneity Learning Libraries Location Machine Learning Markov chain Monte Carlo methodology Methods Modeling Modernization Modification Nature Neural Network Simulation Pattern Phylogenetic Analysis Predisposition Procedures Public Health Research Personnel Sampling Statistical Models Structural Models Structure Technology TensorFlow Time Training Trees Uncertainty Update Variant Viral Viral Genome Work base cloud based data modeling epidemiologic data flexibility genomic data high dimensionality insight knowledge base mathematical algorithm mathematical methods migration neural network novel strategies open source pathogen prevent scale up social exclusion theories tool transmission process user-friendly viral genomics viral transmission

项目摘要

Project Abstract/Summary The SARS-CoV-2 pandemic underlines both our susceptibility to and the toll of a global pathogen outbreak. Phylogenetic analysis of viral genomes provides key insight into disease pathophysiology, spread and po- tential control. However, if these methods are to be used in a viral control strategy they must reliably account for uncertainty and be able to perform inference on 1,000s of genomes in actionable time. Scaling Bayesian phylogenet- ics to meet this need is a grand challenge that is unlikely to be met by optimizing existing algorithms. We will meet this challenge with a radically new approach: Bayesian variational inference for phylogenet- ics (VIP) using ﬂexible distributions on phylogenetic trees that are ﬁt using gradient-based methods analogous to how one efﬁciently trains massive neural networks. By taking a variational approach we will also be able to integrate phylogenetic analysis into very powerful open-source modeling frameworks such as TensorFlow and PyTorch. This will open up new classes of models, such as neural network models, to integrate data such as sampling location and migration patterns with phylogenetic inference. These ﬂexible models will inform strategies for viral control. In Aim 1 we will develop the theory necessary for scalable and reliable VIP, including subtree marginal- ization, local gradient updates needed for online algorithms, convergence diagnostics, and parameter support estimates. We will implement these algorithms in our C++ foundation library for VIP. In Aim 2 we will develop a ﬂexible TensorFlow-based modeling platform for phylogenetics, enabling a whole new realm of phylogenetic models based on neural networks to learn phylodynamic heterogeneity with minimal program- ming effort. We will provide efﬁcient gradients to this implementation via our C++ library. In Aim 3 we will use the fact that VIP posteriors are durable and extensible descriptions of the full data posterior to enable dynamic online computation of variational posteriors, including divide-and-conquer Bayesian phylogenetics. This work will enable a cloud-based viral phylogenetics solution to rapidly update our current estimate of the posterior distribution when new data arrive or the model is modiﬁed. 1

项目摘要/总结 SARS-CoV-2 大流行凸显了我们对全球病原体爆发的易感性和造成的损失。病毒基因组的系统发育分析为疾病病理生理学、传播和传播提供了重要的见解。然而，如果要在病毒控制策略中使用这些方法，它们必须可靠地考虑。不确定性，并能够在可行的时间内对数千个基因组进行推断。满足这一需求的集成电路是一项巨大的挑战，不可能通过优化现有算法来解决。我们将用一种全新的方法来应对这一挑战：系统发育的贝叶斯变分推理 ics（VIP）在系统发育树上使用灵活的分布，该树使用基于梯度的类似方法进行拟合通过采用变分方法，我们也将能够有效地训练大规模神经网络。将系统发育分析集成到非常强大的开源建模框架（例如 TensorFlow）中和 PyTorch，这将开辟新的模型类别，例如神经网络模型，以集成数据，例如这些灵活的模型将提供系统发育推断的采样位置和迁移模式。病毒控制策略。在目标 1 中，我们将开发可扩展且可靠的 VIP 所需的理论，包括子树边际- 在线算法所需的局部梯度更新、收敛诊断和参数支持估计我们将在我们的 VIP 的 C++ 基础库中实现这些算法。开发一个灵活的基于 TensorFlow 的系统发育建模平台，实现一个全新的领域基于神经网络的系统发育模型，以最小的程序学习系统动力学异质性我们将通过我们的 C++ 库为该实现提供有效的梯度。利用 VIP 后验是完整数据后验的持久且可扩展的描述这一事实来启用变分后验的动态在线计算，包括分而治之的贝叶斯系统发育学。这项工作将使基于云的病毒系统发育解决方案能够快速更新我们目前对病毒的估计新数据到达或模型修改时的后验分布。 1