首页    期刊浏览 2024年11月24日 星期日
登录注册

文章基本信息

  • 标题:SkinBug: an artificial intelligence approach to predict human skin microbiome-mediated metabolism of biotics and xenobiotics
  • 本地全文:下载
  • 作者:Shubham K. Jaiswal ; Shitij Manojkumar Agarwal ; Parikshit Thodum
  • 期刊名称:iScience
  • 印刷版ISSN:2589-0042
  • 出版年度:2021
  • 卷号:24
  • 期号:1
  • 页码:1-65
  • DOI:10.1016/j.isci.2020.101925
  • 语种:English
  • 出版社:Elsevier
  • 摘要:SummaryIn addition to being pivotal for the host health, the skin microbiome possesses a large reservoir of metabolic enzymes, which can metabolize molecules (cosmetics, medicines, pollutants, etc.) that form a major part of the skin exposome. Therefore, to predict the complete metabolism of any molecule by skin microbiome, a curated database of metabolic enzymes (1,094,153), reactions, and substrates from ∼900 bacterial species from 19 different skin sites were used to develop “SkinBug.” It integrates machine learning, neural networks, and chemoinformatics methods, and displays a multiclass multilabel accuracy of up to 82.4% and binary accuracy of up to 90.0%. SkinBug predicts all possible metabolic reactions and associated enzymes, reaction centers, skin microbiome species harboring the enzyme, and the respective skin sites. Thus, SkinBug will be an indispensable tool to predict xenobiotic/biotic metabolism by skin microbiome and will find applications in exposome and microbiome studies, dermatology, and skin cancer research.Graphical AbstractDisplay OmittedHighlights•SkinBug is AI/ML-based tool to predict metabolism of molecules by Skin microbiome•Database of 1,094,153 metabolic enzymes from 897 pangenomes of skin microbiome•Predicts enzymes, bacterial species, and skin sites for the predicted reactions•82.4% multilabel and 90.0% binary accuracy, and validated on 28 diverse real casesIn Silico Biology; Metabolomics; Systems Biology
国家哲学社会科学文献中心版权所有