Department of Infectious Diseases, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine; Key Laboratory of Microbial Technology and Bioinformatics of Zhejiang Province; Regional Medical Center for National Institute of Respiratory Diseases, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, PR China.
Microb Genom. 2021 Sep;7(9). doi: 10.1099/mgen.0.000610.
Treatment failure of methicillin-resistant (MRSA) infections remains problematic in clinical practice because therapeutic options are limited. Penicillin plus potassium clavulanate combination (PENC) was shown to have potential for treating some MRSA infections. We investigated the susceptibility of MRSA isolates and constructed a drug susceptibility prediction model for the phenotype of the PENC. We determined the minimum inhibitory concentration of PENC for MRSA (=284) in a teaching hospital (SRRSH-MRSA). PENC susceptibility genotypes were analysed using a published genotyping scheme based on the sequence. expression in MRSA isolates was analysed by qPCR. We established a random forest model for predicting PENC-susceptible phenotypes using core genome allelic profiles from cgMLST analysis. We identified S2-R isolates with susceptible genotypes but PENC-resistant phenotypes; these isolates expressed at higher levels than did S2 MRSA (2.61 vs 0.98, <0.05), indicating the limitation of using a single factor for predicting drug susceptibility. Using the data of selected UK-sourced MRSA (=74) and MRSA collected in a previous national survey (NA-MRSA, =471) as a training set, we built a model with accuracies of 0.94 and 0.93 for SRRSH-MRSA and UK-sourced MRSA (=287, NAM-MRSA) validation sets. The AUROC of this model for SRRSH-MRSA and NAM-MRSA was 0.96 and 0.97. Although the source of the training set data affects the scope of application of the prediction model, our data demonstrated the power of the machine learning approach in predicting susceptibility from cgMLST results.
耐甲氧西林金黄色葡萄球菌（MRSA）感染的治疗失败仍然是临床实践中的一个问题，因为治疗选择有限。青霉素加克拉维酸钾联合（PENC）已被证明对治疗某些 MRSA 感染具有潜力。我们研究了 MRSA 分离株的敏感性，并构建了用于 PENC 表型的药敏预测模型。我们在教学医院（SRRSH-MRSA）中确定了 PENC 对 MRSA 的最小抑菌浓度（=284）。使用基于 序列的已发表基因分型方案分析 PENC 药敏基因型。通过 qPCR 分析 MRSA 分离株中的 表达。我们使用 cgMLST 分析的核心基因组等位基因谱建立了用于预测 PENC 敏感表型的随机森林模型。我们确定了具有敏感基因型但 PENC 耐药表型的 S2-R 分离株；这些分离株的 表达水平高于 S2 MRSA（2.61 对 0.98，<0.05），表明使用单一因素预测药物敏感性存在局限性。使用从选定的英国来源的 MRSA（=74）和之前的全国性调查中收集的 MRSA（NA-MRSA，=471）的数据作为训练集，我们构建了一个模型，对于 SRRSH-MRSA 和英国来源的 MRSA（=287，NAM-MRSA）验证集，其准确性分别为 0.94 和 0.93。该模型对 SRRSH-MRSA 和 NAM-MRSA 的 AUROC 分别为 0.96 和 0.97。尽管训练集数据的来源会影响预测模型的应用范围，但我们的数据证明了机器学习方法在从 cgMLST 结果预测敏感性方面的强大功能。
