Miki Ikebe, Kota Aoki, Mitsuko Hayashi-Nishino, Chikara Furusawa, Kunihiko Nishino
{"title":"生物信息学分析利用光学显微镜和深度学习揭示了细菌形态与抗生素耐药性之间的关联。","authors":"Miki Ikebe, Kota Aoki, Mitsuko Hayashi-Nishino, Chikara Furusawa, Kunihiko Nishino","doi":"10.3389/fmicb.2024.1450804","DOIUrl":null,"url":null,"abstract":"<p><p>Although it is well known that the morphology of Gram-negative rods changes on exposure to antibiotics, the morphology of antibiotic-resistant bacteria in the absence of antibiotics has not been widely investigated. Here, we studied the morphologies of 10 antibiotic-resistant strains of <i>Escherichia coli</i> and used bioinformatics tools to classify the resistant cells under light microscopy in the absence of antibiotics. The antibiotic-resistant strains showed differences in morphology from the sensitive parental strain, and the differences were most prominent in the quinolone-and β-lactam-resistant bacteria. A cluster analysis revealed increased proportions of fatter or shorter cells in the antibiotic-resistant strains. A correlation analysis of morphological features and gene expression suggested that genes related to energy metabolism and antibiotic resistance were highly correlated with the morphological characteristics of the resistant strains. Our newly proposed deep learning method for single-cell classification achieved a high level of performance in classifying quinolone-and β-lactam-resistant strains.</p>","PeriodicalId":12466,"journal":{"name":"Frontiers in Microbiology","volume":null,"pages":null},"PeriodicalIF":4.0000,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11446759/pdf/","citationCount":"0","resultStr":"{\"title\":\"Bioinformatic analysis reveals the association between bacterial morphology and antibiotic resistance using light microscopy with deep learning.\",\"authors\":\"Miki Ikebe, Kota Aoki, Mitsuko Hayashi-Nishino, Chikara Furusawa, Kunihiko Nishino\",\"doi\":\"10.3389/fmicb.2024.1450804\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Although it is well known that the morphology of Gram-negative rods changes on exposure to antibiotics, the morphology of antibiotic-resistant bacteria in the absence of antibiotics has not been widely investigated. Here, we studied the morphologies of 10 antibiotic-resistant strains of <i>Escherichia coli</i> and used bioinformatics tools to classify the resistant cells under light microscopy in the absence of antibiotics. The antibiotic-resistant strains showed differences in morphology from the sensitive parental strain, and the differences were most prominent in the quinolone-and β-lactam-resistant bacteria. A cluster analysis revealed increased proportions of fatter or shorter cells in the antibiotic-resistant strains. A correlation analysis of morphological features and gene expression suggested that genes related to energy metabolism and antibiotic resistance were highly correlated with the morphological characteristics of the resistant strains. Our newly proposed deep learning method for single-cell classification achieved a high level of performance in classifying quinolone-and β-lactam-resistant strains.</p>\",\"PeriodicalId\":12466,\"journal\":{\"name\":\"Frontiers in Microbiology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.0000,\"publicationDate\":\"2024-09-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11446759/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in Microbiology\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.3389/fmicb.2024.1450804\",\"RegionNum\":2,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"MICROBIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Microbiology","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.3389/fmicb.2024.1450804","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"MICROBIOLOGY","Score":null,"Total":0}
Bioinformatic analysis reveals the association between bacterial morphology and antibiotic resistance using light microscopy with deep learning.
Although it is well known that the morphology of Gram-negative rods changes on exposure to antibiotics, the morphology of antibiotic-resistant bacteria in the absence of antibiotics has not been widely investigated. Here, we studied the morphologies of 10 antibiotic-resistant strains of Escherichia coli and used bioinformatics tools to classify the resistant cells under light microscopy in the absence of antibiotics. The antibiotic-resistant strains showed differences in morphology from the sensitive parental strain, and the differences were most prominent in the quinolone-and β-lactam-resistant bacteria. A cluster analysis revealed increased proportions of fatter or shorter cells in the antibiotic-resistant strains. A correlation analysis of morphological features and gene expression suggested that genes related to energy metabolism and antibiotic resistance were highly correlated with the morphological characteristics of the resistant strains. Our newly proposed deep learning method for single-cell classification achieved a high level of performance in classifying quinolone-and β-lactam-resistant strains.
期刊介绍:
Frontiers in Microbiology is a leading journal in its field, publishing rigorously peer-reviewed research across the entire spectrum of microbiology. Field Chief Editor Martin G. Klotz at Washington State University is supported by an outstanding Editorial Board of international researchers. This multidisciplinary open-access journal is at the forefront of disseminating and communicating scientific knowledge and impactful discoveries to researchers, academics, clinicians and the public worldwide.