Machine Learning and Control Principles for Computational Biology

计算生物学的机器学习和控制原理

• 批准号: 10276879
• 负责人: Travis Eli Gibson
• 金额: $ 44.75万
• 依托单位: BRIGHAM AND WOMEN'S HOSPITAL
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-01 至 2026-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10276879
• 关键词: Algorithms; Alternative Therapies; Area; Bacteria; Biological; Biological Models; Biological Sciences; Biology; Certification; Clinic; Clinical; Communities; Complex; Computational Biology; Computer software; Data; Data Set; Development; Diagnostic; Diagnostics Research; Engineering; Ensure; Equus caballus; Germ-Free; Grant; Healthcare; Hospitals; In Vitro; Lead; Machine Learning; Measurement; Measures; Methods; Modeling; Mus; Organism; Pharmaceutical Preparations; Process; Property; Reproducibility; Research; Resources; Savings; Scheme; Series; System; Techniques; Time; Training; Uncertainty; Work; base; computational reasoning; computerized tools; deep learning; deep neural network; design; digital health; dynamic system; experimental study; flexibility; health record; in vivo; in vivo Model; mathematical learning; member; microbial community; microbiota; success; tool

Summary/Abstract With our increasing ability to measure biological data at scale and the digitalization of health records, computational thinking is becoming ever more important in the biological science and healthcare. The research directions proposed in this grant look to build robust machine learning models and tool for computational biology by including principles and analysis from other engineering fields, like control, that have a proven record of incorporating robustness into the systems they have automated. This increased robustness will save resources during the development of these machine learning models. It will also lead to more reliable diagnostics, clinical tools, and machine learning based biological discoveries. We have proposed three future research directions at the intersection of machine learning, control, and computational biology (a) modeling dynamical systems, (b) robust optimization schemes (c) control principles for in vivo modeling of microbial communities. The first proposed research area involves the development of flexible models for performing inference on dynamical systems models with time-series data. Dynamical systems models are able to learn mathematically causal relationships between variables, compared to other models whose parameters may only have correlative relationships. Our flexible models will be differentiable allowing them to be trained using the same efficient algorithms and hardware that have propelled deep learning models into the spotlight. These differentiable methods will allow for us to more easily integrate the uncertainty associated with biological measurements into our models. The second research area looks to develop more robust gradient optimization algorithms, the work horse for training deep neural networks. Many of the popular algorithms used to train deep neural networks were not explicitly designed to be robust. By developing more robust optimization techniques machine learning models trained on disparate data sets at different hospital or labs will be more reproducible and will require less time for tuning parameters, ultimately saving resources as well. These robust optimization techniques will also aid in the certification of machine learning based tools that will ultimately be deployed in the clinic. The third research area we propose is an approach for the discovery and design of robust microbial communities. Communities of commensal, or engineered, bacteria have long been proposed as alternative therapies for the treatment of gut related illness (“bugs as drugs”). We propose a top down approach to identifying putative microbial consortia members from time-series experiments with germ free mice colonized by complex flora. By beginning the consortia design process in vivo we hope to overcome the challenge that many other attempts at consortia construction have encountered where in vitro designed communities do not reproduce their intended properties once transferred into living host organisms. The tools from this work will be built using open access software and all data will be made easily accessible and explorable to the public.

摘要/摘要 随着我们大规模测量生物数据和健康记录数字化的能力不断增强， 计算思维在生物科学和医疗保健中变得越来越重要。研究 该资助提出的方向旨在为计算生物学建立强大的机器学习模型和工具 通过纳入其他工程领域（例如控制）的原理和分析，这些领域有经过验证的记录 将稳健性融入到他们自动化的系统中。这种增强的稳健性将节省资源 在这些机器学习模型的开发过程中。它还将带来更可靠的诊断、临床 工具和基于机器学习的生物发现。我们提出了三个未来的研究方向 机器学习、控制和计算生物学的交叉点 (a) 动态系统建模，(b) 稳健的优化方案（c）微生物群落体内建模的控制原理。第一个 拟议的研究领域涉及开发用于对动态进行推理的灵活模型 具有时间序列数据的系统模型。动力系统模型能够学习数学因果关系 与参数可能仅具有相关性的其他模型相比，变量之间的关系 关系。我们灵活的模型将是可微分的，允许使用相同的效率来训练它们 使深度学习模型成为人们关注的算法和硬件。这些可微的 方法将使我们能够更轻松地将与生物测量相关的不确定性整合到 我们的模型。第二个研究领域着眼于开发更鲁棒的梯度优化算法，这项工作 用于训练深度神经网络的马。许多用于训练深度神经网络的流行算法都是 没有明确设计为稳健。通过开发更强大的优化技术机器学习模型 在不同医院或实验室的不同数据集上进行培训将更具可重复性，并且需要更少的时间 调整参数，最终也节省资源。这些强大的优化技术也将有助于 对最终将在诊所部署的基于机器学习的工具进行认证。第三研究领域 我们提出了一种发现和设计强大微生物群落的方法。社区 长期以来，共生细菌或工程细菌一直被提议作为治疗肠道疾病的替代疗法 相关疾病（“虫子作为药物”）。我们提出了一种自上而下的方法来识别假定的微生物群落 来自对无菌小鼠进行时间序列实验的成员，这些小鼠被复杂的菌群定殖。通过开始 在体内的联盟设计过程中，我们希望能够克服联盟中许多其他尝试所面临的挑战 施工中遇到了体外设计的群落无法重现其预期特性的情况 一旦转移到活的宿主生物体中。这项工作的工具将使用开放获取软件构建 所有数据都将可供公众轻松访问和探索。