辽宁省高等学校国(境)外培养项目(2018LNGXGJWPY-YB006);中国科协优秀中外青年交流计划(2018CASTQNJL50);辽宁省重点研发计划(2019JH2/10300041);沈阳市科技计划项目(18-014-4-34,F16-205-1-51,17-65-7-00,17-231-1-04)
Hongsheng Liu
School of Life Sciences, Liaoning University, Shenyang 110036, Liaoning Province, China;Research Center for Computer Simulating and Information Processing of Bio-macromolecules of Liaoning Province, Liaoning University, Shenyang 110036, Liaoning Province, China;Engineering Laboratory of Molecular Modeling and Design for Drug of Liaoning Province, Liaoning University, Shenyang 110036, Liaoning Province, ChinaLi Zhang
School of Life Sciences, Liaoning University, Shenyang 110036, Liaoning Province, China;Research Center for Computer Simulating and Information Processing of Bio-macromolecules of Liaoning Province, Liaoning University, Shenyang 110036, Liaoning Province, China;Engineering Laboratory of Molecular Modeling and Design for Drug of Liaoning Province, Liaoning University, Shenyang 110036, Liaoning Province, China基质辅助激光解吸/电离飞行时间质谱(matrix-assisted laser desorption/ionization time-of-flight mass spectrometry,MALDI-TOF MS)是一种新兴的高通量技术,已广泛应用于临床微生物、食品微生物和水产微生物的快速鉴定。如何进一步提高MALDI-TOF MS在微生物鉴定中的分辨率是该技术当前面临的一大挑战。为了高效处理大量高维微生物MALDI-TOF MS数据,各种机器学习算法得到了应用。本文综述了机器学习在微生物MALDI-TOF MS鉴定中的应用。首先,本文在介绍机器学习在微生物MALDI-TOF MS分类中的工作流程后,进一步对MALDI-TOF MS的数据特征、MALDI-TOF MS数据库、数据的预处理和模型的性能评估进行了描述。然后讨论了典型的机器学习分类算法和集成学习算法的应用。简单的机器学习算法很难满足微生物MALDI-TOF MS分类的高分辨率的需求,而组合不同机器学习算法和集成学习算法可以获得更好的微生物分类性能。在MALDI-TOF MS数据的预处理方面,小波算法和遗传算法的应用最广,它们结合分类算法可以有效提高MALDI-TOF MS的分类性能。随着微生物MALDI-TOF MS数据量的不断增加,在未来的研究工作中应更重视分类算法的改进、不同算法的选择或组合以及预处理算法的改进。
Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) is a novel high-throughput technology widely used in rapid identification of clinical microorganisms, food microorganisms and aquatic microorganisms. Currently, however, how to further improve the resolution of MALDI-TOF MS in microbial identification is a major challenge for this technology. To effectively deal with the large amounts of high-dimensional microbial MALDI-TOF MS data, a variety of machine learning algorithms have been applied. This paper reviews the applications of machine learning in MALDI-TOF MS identification of microorganisms. Herein, the workflow of machine learning in the classification of microbial MALDI-TOF MS is introduced. Then, the characteristics of MALDI-TOF MS data, MALDI-TOF MS database, the preprocessing of the MALDI-TOF MS data, and the performance evaluation of the model are further described. The applications of typical machine learning classification algorithms and ensemble learning algorithms are also discussed.
刘宏生,冯华炜,张力,孟金蕙,董雪. 机器学习在MALDI-TOF MS鉴定微生物中的应用[J]. 微生物学报, 2020, 60(5): 841-855
复制您是本站第 5576849 访问者
通信地址:北京市朝阳区北辰西路1号院3号 中国科学院微生物研究所 邮编:100101
电话:010-64807516 E-mail:actamicro@im.ac.cn
版权所有:微生物学报 ® 2025 版权所有