Loganathan Tamizhini, Priya Doss C George
Laboratory of Integrative Genomics, Department of Integrative Biology, School of BioSciences and Technology, Vellore Institute of Technology (VIT), Vellore 632014, Tamil Nadu, India.
Laboratory of Integrative Genomics, Department of Integrative Biology, School of BioSciences and Technology, Vellore Institute of Technology (VIT), Vellore 632014, Tamil Nadu, India.
Life Sci. 2022 Dec 15;311(Pt A):121118. doi: 10.1016/j.lfs.2022.121118. Epub 2022 Oct 28.
Gut microbial profiles induce cancer growth and impact treatment effectiveness, tolerance, and safety. There is still more to discover about the relationship between diseases and the microbiota and its clinical consequences. Even though much of the study is still in its early phases, the 'omics' technologies were widely used for microbiome analysis due to the increased size of datasets available in public databases. However, recognizing the potential of these new technologies is difficult at times, limiting our ability to analyze a vast amount of available data critically. In this context, two subsets of AI methods, Machine Learning (ML) and Deep Learning (DL), can aid clinicians in analyzing and comprehending these large datasets. Here, we reviewed the most up-to-date ML methodologies, databases, and tools used in human microbiome research. The proposed review forecast the use of ML in microbiome research involving associations and clinical applications for diagnostics, prognostics, and therapies.
肠道微生物谱会促进癌症生长，并影响治疗效果、耐受性和安全性。关于疾病与微生物群之间的关系及其临床后果，仍有更多有待发现之处。尽管大部分研究仍处于早期阶段，但由于公共数据库中可用数据集规模的增加，“组学”技术被广泛用于微生物组分析。然而，有时很难认识到这些新技术的潜力，这限制了我们批判性分析大量可用数据的能力。在这种背景下，人工智能方法的两个子集，即机器学习（ML）和深度学习（DL），可以帮助临床医生分析和理解这些大型数据集。在此，我们回顾了人类微生物组研究中使用的最新机器学习方法、数据库和工具。本综述预测了机器学习在微生物组研究中的应用，包括用于诊断、预后和治疗的关联研究及临床应用。
