Heinemann Joshua
Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, USA.
Joint BioEnergy Institute, Emeryville, CA, USA.
Methods Mol Biol. 2019;1859:287-299. doi: 10.1007/978-1-4939-8757-3_17.
Machine learning is a form of artificial intelligence (AI) that provides computers with the ability to learn generally without being explicitly programmed. Machine learning refers to the ability of computer programs to adapt when exposed to new data. Here we examine the use of machine learning for use with untargeted metabolomics data, when it is appropriate to use, and questions it can answer. We provide an example workflow for training and testing a simple binary classifier, a multiclass classifier and a support vector machine using the Waikato Environment for Knowledge Analysis (Weka), a toolkit for machine learning. This workflow should provide a framework for greater integration of machine learning with metabolomics study.
机器学习是人工智能（AI）的一种形式，它使计算机能够在无需明确编程的情况下进行一般意义上的学习。机器学习指的是计算机程序在接触新数据时进行自适应的能力。在此，我们探讨机器学习在非靶向代谢组学数据中的应用、适用时机以及它能够回答的问题。我们提供了一个示例工作流程，用于使用怀卡托知识分析环境（Weka，一个机器学习工具包）训练和测试一个简单的二元分类器、多类分类器和支持向量机。这个工作流程应为机器学习与代谢组学研究的更深入整合提供一个框架。
