Systematic analysis of supervised machine learning as an effective approach to predicate β-lactam resistance phenotype in Streptococcus pneumoniae

Prediction of genome-wide imipenem resistance features in Klebsiella pneumoniae using machine learning

Introduction. The resistance rate of Klebsiella pneumoniae (K. pneumoniae) to imipenem is increasing year by year, and the imipenem resistance mechanism of K. pneumoniae is complex. Therefore, it is urgent to develop new strategies to explore the resistance mechanism of imipenem for its effective and accurate use in clinical practice.Hypothesis/Gap sStatement. Machine learning could identify resistance features and biological process that influence microbial resistance from whole-genome sequencing (WGS) data.Aims. This work aimed to predict imipenem resistance genetic features in K. pneumoniae from whole-genome k-mer features, and analyse their function for understanding its resistance mechanism.Methods. This study analysed WGS data of K. pneumoniae combined with resistance phenotype for imipenem, and established K. pneumoniae to imipenem genotype-phenotype model to predict resistance features using chi-squared test and random forest. An external clinical dataset was used to verify prediction power of resistance features. The potential genes were identified through alignment the resistance features with the K. pneumoniae reference genome using blastn, the functions of potential genes were further analysed to explore its resistance-related signalling pathways with GO and KEGG analysis, the resistance sequence patterns were screened using streme software. Finally, the resistance features were combined and modelled through four machine-learning algorithms (logistic regression, SVM, GBDT and XGBoost) to evaluate their phenotype prediction ability.Results. A total of 16 670 imipenem resistance features were predicted from genotype-phenotype model. The 30 potential genes were identified by annotating the resistance features and corresponded to known antibiotic-related genes (mdtM, dedA, rne, etc.). GO and KEGG pathway analyses indicated the possible association of imipenem resistance with metabolism process and cell membrane. CRYCAGCDN and CGRDAAAN were found from the imipenem resistance features, which were widely presented in the reported β-lactam resistance genes (bla _SHV, bla _CTX-M, bla _TEM, etc.), and YCYAGCMCAST with metabolic functions (organic substance metabolic process, nitrogen compound metabolic process and cellular metabolic process) was identified from the top 50 resistance features. The 25 resistance genes in the training dataset included 19 genes in the external dataset, which verified the accuracy of prediction. The area under curve values of logistics regression, SVM, GBDT and XGBoost were 0.965, 0.966, 0.969 and 0.969, respectively, indicating that the imipenem resistance features have a strong prediction power.Conclusion. Machine-learning methods could effectively predict the imipenem resistance feature in K. pneumoniae, and provide resistance sequence profiles for predicting resistance phenotype and exploring potential resistance mechanisms. It provides an important insight into the potential therapeutic strategies of K. pneumoniae resistance to imipenem, and speed up the application of machine learning in routine diagnosis.

The human gut serves as a reservoir of hypervirulent Klebsiella pneumoniae

Hypervirulent Klebsiella pneumoniae (hvKp) can cause serious infections and has been increasingly reported clinically. However, we still lack the knowledge to what degree hvKp colonize the community. In this study, we investigated colonization of hvKp in healthy human gut and the relationship between gut hvKp and clinically important invasive strains. We compile global genomes of gut K. pneumoniae for in-depth genetic analysis and found most hvKp genomes originated from Chinese datasets; therefore, we collected gut K. pneumoniae isolates from healthy people around China. The results revealed a moderate carriage rate of hvKp in the healthy population (4%-5.19%). Phylogenetic analysis indicated a close relationship between gut hvKp and fatal clinical strains. These results demonstrate that the human gut may serve as a reservoir of hvKp and that gut hvKp can play a role in infection of other body parts.

Strengths and caveats of identifying resistance genes from whole genome sequencing data

INTRODUCTION

Antimicrobial resistance (AMR) continues to present major challenges to modern healthcare. Recent advances in whole-genome sequencing (WGS) have made the rapid molecular characterization of AMR a realistic possibility for diagnostic laboratories; yet major barriers to clinical implementation exist.

AREAS COVERED

We describe and compare short- and long-read sequencing platforms, typical components of bioinformatics pipelines, tools for AMR gene detection and the relative merits of read- or assembly-based approaches. The challenges of characterizing mobile genetic elements from genomic data are outlined, as well as the complexities inherent to the prediction of phenotypic resistance from WGS. Practical obstacles to implementation in diagnostic laboratories, the critical role of quality control and external quality assurance, as well as standardized reporting standards are also discussed. Future directions, such as the application of machine-learning and artificial intelligence algorithms, linked to clinically meaningful outcomes, may offer a new paradigm for the clinical application of AMR prediction.

EXPERT OPINION

AMR prediction from WGS data presents an exciting opportunity to advance our capacity to comprehensively characterize infectious pathogens in a rapid manner, ultimately aiming to improve patient outcomes. Collaborative efforts between clinicians, scientists, regulatory bodies and healthcare administrators will be critical to achieve the full promise of this approach.

Streptococcus sputorum, a Novel Member of Streptococcus with Multidrug Resistance, Exhibits Cytotoxicity

We describe the genomic and phenotypic characteristics of a novel member of Streptococcus with multidrug resistance (MDR) isolated from hospital samples. Strains SP218 and SP219 were identified as a novel Streptococcus, S. sputorum, using whole-genome sequencing and biochemical tests. Average nucleotide identity values of strains SP218 and SP219 with S. pseudopneumoniae IS7493 and S. pneumoniae ST556 were 94.3% and 93.3%, respectively. Genome-to-genome distance values of strains SP218 and SP219 with S. pseudopneumoniae IS7493 and S. pneumoniae ST556 were 56.70% (54–59.5%) and 56.40% (52.8–59.9%), respectively. The biochemical test results distinguished these strains from S. pseudopneumoniae and S. pneumoniae, particularly hydrolysis of equine urate and utilization of ribose to produce acid. These isolates were resistant to six major classes of antibiotics, which correlated with horizontal gene transfer and mutation. Notably, strain SP219 exhibited cytotoxicity against human lung epithelial cell line A549. Our results indicate the pathogenic potential of S. sputorum, and provide valuable insights into mitis group of streptococci.

Artificial intelligence and machine learning assisted drug delivery for effective treatment of infectious diseases

In the era of antimicrobial resistance, the prevalence of multidrug-resistant microorganisms that resist conventional antibiotic treatment has steadily increased. Thus, it is now unquestionable that infectious diseases are significant global burdens that urgently require innovative treatment strategies. Emerging studies have demonstrated that artificial intelligence (AI) can transform drug delivery to promote effective treatment of infectious diseases. In this review, we propose to evaluate the significance, essential principles, and popular tools of AI in drug delivery for infectious disease treatment. Specifically, we will focus on the achievements and key findings of current research, as well as the applications of AI on drug delivery throughout the whole antimicrobial treatment process, with an emphasis on drug development, treatment regimen optimization, drug delivery system and administration route design, and drug delivery outcome prediction. To that end, the challenges of AI in drug delivery for infectious disease treatments and their current solutions and future perspective will be presented and discussed.