ウイルスゲノムの特徴量解析と自然宿主推定への応用

病毒基因组特征分析及其在自然宿主估计中的应用

• 批准号: 16J02715
• 负责人: Tessmer Heidi Lynn (2017)
• 金额: $ 0.83万
• 依托单位: Hokkaido University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for JSPS Fellows
• 财政年份: 2016
• 资助国家: 日本
• 起止时间: 2016-04-22 至 2018-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-16J02715/
• 关键词: 機械学習; 感染症; 基本再生産数; infectious disease; machine learning; mathematical modeling; epidemiology

I continued my research into machine learning, including server maintenance and optimization, learning and using different ML libraries, attending conferences, and exploring the latest papers, tutorials, and industry standards.Two co-authored papers:- Tessmer HL, Ito K, and Omori R. Can machines learn respiratory virus epidemiology?: A comparative study of likelihood-free methods for the estimation of epidemiological dynamics.- Sakon N, Komano J, Tessmer HL, and Omori R. High transmissibility of norovirus among infants and school children during the 2016/17 season in Osaka, Japan.Abstract: To estimate and predict the transmission dynamics of respiratory viruses, the estimation of the basic reproduction number, R0, is essential. Recently, approximate Bayesian computation methods have been used as likelihood free methods to estimate epidemiological model parameters, particularly R0. In this paper, we explore various machine learning approaches, the multi-layer perceptron, convolutional neural network, and long-short term memory, to learn and estimate the parameters. Further, we compare the accuracy of the estimates and time requirements for machine learning and the approximate Bayesian computation methods on both simulated and real-world epidemiological data from outbreaks of influenza A(H1N1)pdm09, mumps, and measles. We find that the machine learning approaches can be verified and tested faster than the approximate Bayesian computation method, but that the approximate Bayesian computation method is more robust across different datasets.

我继续我在机器学习方面的研究，包括服务器维护和优化，学习和使用不同的ML库，参加会议，并探索最新的论文、教程和行业标准。两篇合著论文：Tessmer HL，Ito K和Omori R.机器能学习呼吸道病毒流行病学吗？：估计流行病学动态的无似然方法的比较研究。-Sakon N，Komano J，Tessmer HL和Omori R。2016/17赛季在日本大阪，诺如病毒在婴儿和学龄儿童中的高传播率。摘要：为了估计和预测呼吸道病毒的传播动态，基本繁殖数量的估计，估计R0，是必不可少的。最近，近似贝叶斯计算方法已被用作估计流行病学模型参数，特别是R0的无似然方法。在本文中，我们探索了各种机器学习方法，多层感知器、卷积神经网络和长-短期记忆，以学习和估计参数。进一步，我们比较了机器学习和近似贝叶斯计算方法在甲型H1N1流感(H1N1)pdm09、腮腺炎和麻疹暴发的模拟和真实世界流行病学数据上的估计和时间要求的准确性。我们发现，机器学习方法可以比近似贝叶斯计算方法更快地进行验证和测试，但近似贝叶斯计算方法在不同数据集上的健壮性更强。

项目成果

SeoulNationalUniversity(韓国)

首尔国立大学（韩国）

Estimation of Basic Reproduction Number R0 using a Recurrent Neural Network

使用循环神经网络估计基本繁殖数 R0

• 发表时间: 2016
• 作者: Mayumbo Nyirenda;Ryosuke Omori;Heidi L. Tessmer;Hiroki Arimura;Kimihito Ito;澤浦亮平;Tessmer HL and Omori R
• 通讯作者: Tessmer HL and Omori R