Dataset Information

Application of Machine Learning Classifier to Candida auris Drug Resistance Analysis

ABSTRACT: Candida auris (C. auris) is an emerging fungus associated with high morbidity. It has a unique transmission ability and is often resistant to multiple drugs. In this study, we evaluated the ability of different machine learning models to classify the drug resistance and predicted and ranked the drug resistance mutations of C. auris. Two C. auris strains were obtained. Combined with other 356 strains collected from the European Bioinformatics Institute (EBI) databases, the whole genome sequencing (WGS) data were analyzed by bioinformatics. Machine learning classifiers were used to build drug resistance models, which were evaluated and compared by various evaluation methods based on AUC value. Briefly, two strains were assigned to Clade III in the phylogenetic tree, which was consistent with previous studies; nevertheless, the phylogenetic tree was not completely consistent with the conclusion of clustering according to the geographical location discovered earlier. The clustering results of C. auris were related to its drug resistance. The resistance genes of C. auris were not under additional strong selection pressure, and the performance of different models varied greatly for different drugs. For drugs such as azoles and echinocandins, the models performed relatively well. In addition, two machine learning algorithms, based on the balanced test and imbalanced test, were designed and evaluated; for most drugs, the evaluation results on the balanced test set were better than on the imbalanced test set. The mutations strongly be associated with drug resistance of C. auris were predicted and ranked by Recursive Feature Elimination with Cross-Validation (RFECV) combined with a machine learning classifier. In addition to known drug resistance mutations, some new resistance mutations were predicted, such as Y501H and I466M mutation in the ERG11 gene and R278H mutation in the ERG10 gene, which may be associated with fluconazole (FCZ), micafungin (MCF), and amphotericin B (AmB) resistance, respectively; these mutations were in the “hot spot” regions of the ergosterol pathway. To sum up, this study suggested that machine learning classifiers are a useful and cost-effective method to identify fungal drug resistance-related mutations, which is of great significance for the research on the resistance mechanism of C. auris.

SUBMITTER: Li D

PROVIDER: S-EPMC8554202 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Candida auris is globally recognized as an opportunistic fungal pathogen of high concern, due to its extensive multidrug resistance (MDR). Still, molecular mechanisms of MDR are largely unexplored. This is the first account of genome-wide evolution of MDR in C. auris obtained through serial in vitro exposure to azoles, polyenes, and echinocandins. We show the stepwise accumulation of copy number variations and novel mutations in genes both known and unknown in antifungal drug resistance. Echinocandin resistance was accompanied by a codon deletion in FKS1 hot spot 1 and a substitution in FKS1 "novel" hot spot 3. Mutations in ERG3 and CIS2 further increased the echinocandin MIC. Decreased azole susceptibility was linked to a mutation in transcription factor TAC1b and overexpression of the drug efflux pump Cdr1, a segmental duplication of chromosome 1 containing ERG11, and a whole chromosome 5 duplication, which contains TAC1b The latter was associated with increased expression of ERG11, TAC1b, and CDR2 but not CDR1 The simultaneous emergence of nonsense mutations in ERG3 and ERG11 was shown to decrease amphotericin B susceptibility, accompanied with fluconazole cross-resistance. A mutation in MEC3, a gene mainly known for its role in DNA damage homeostasis, further increased the polyene MIC. Overall, this study shows the alarming potential for and diversity of MDR development in C. auris, even in a clade until now not associated with MDR (clade II), stressing its clinical importance and the urge for future research.IMPORTANCECandida auris is a recently discovered human fungal pathogen and has shown an alarming potential for developing multi- and pan-resistance toward all classes of antifungals most commonly used in the clinic. Currently, C. auris has been globally recognized as a nosocomial pathogen of high concern due to this evolutionary potential. So far, this is the first study in which the stepwise progression of multidrug resistance (MDR) in C. auris is monitored in vitro Multiple novel mutations in known resistance genes and genes previously not or vaguely associated with drug resistance reveal rapid MDR evolution in a C. auris clade II isolate. Additionally, this study shows that in vitro experimental evolution can be a powerful tool to discover new drug resistance mechanisms, although it has its limitations.

Dataset Information

Application of Machine Learning Classifier to Candida auris Drug Resistance Analysis

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets