AUTHOR=Gai Xiao , Qian Peng , Guo Benqiong , Zheng Yixin , Fu Zhihao , Yang Decai , Zhu Chunmei , Cao Yang , Niu Jingbin , Ling Jianghong , Zhao Jin , Shi Hailian , Liu Guoping TITLE=Heptadecanoic acid and pentadecanoic acid crosstalk with fecal-derived gut microbiota are potential non-invasive biomarkers for chronic atrophic gastritis JOURNAL=Frontiers in Cellular and Infection Microbiology VOLUME=Volume 12 - 2022 YEAR=2023 URL=https://www.frontiersin.org/journals/cellular-and-infection-microbiology/articles/10.3389/fcimb.2022.1064737 DOI=10.3389/fcimb.2022.1064737 ISSN=2235-2988 ABSTRACT=Chronic atrophic gastritis (CAG), premalignant lesions of gastric cancer (GC), greatly increases the risk of GC. Gastroscopy with tissue biopsy is the most commonly used technology for CAG diagnosis. However, due to the invasive nature, both ordinary gastroscope and painless gastroscope result in a certain degree of injury to the esophagus as well as inducing psychological pressure on patients. In addition, patients need fast for at least half a day and take laxatives. In this study, alteration of fecal metabolites and microbiota profiles was found in CAG patients, compared with healthy volunteers detected by metabolomics and 16S rRNA V4-V5 region sequencing. To identify the most relevant features, 7 fecal metabolites and 4 microbiota were selected by random forest (RF), from A and B sample sets, respectively. Furthermore, we constructed support vector machines (SVM) classification model using 7 fecal metabolites or 4 gut microbes, or 7 fecal metabolites with 4 gut microbes, respectively, on C sample set. The accuracy of classification model was 0.714, 0.857, 0.857, respectively, and the AUC was 0.71, 0.88, 0.9, respectively. In C sample set, Spearman’s rank correlation analysis demonstrated heptadecanoic acid and pentadecanoic acid were significantly negatively correlated to Erysipelotrichaceae_UCG-003 and Haemophilus, respectively. We constructed SVM classification model using 2 correlated fecal metabolites and 2 correlated gut microbes on C sample set. The accuracy of classification model was 0.857, and the AUC was 0.88. Therefore, heptadecanoic acid and pentadecanoic acid, crosstalk with fecal-derived gut microbiota namely Erysipelotrichaceae_UCG-003 and Haemophilus, are potential non-invasive biomarkers for CAG diagnosis.