Multi-label classification for multi-drug resistance prediction of Escherichia coli

Predicting S. aureus antimicrobial resistance with interpretable genomic space maps

Increasing antimicrobial resistance (AMR) represents a global healthcare threat. To decrease the spread of AMR and associated mortality, methods for rapid selection of optimal antibiotic treatment are urgently needed. Machine learning (ML) models based on genomic data to predict resistant phenotypes can serve as a fast screening tool prior to phenotypic testing. Nonetheless, many existing ML methods lack interpretability. Therefore, we present a methodology for visualization of sequence space and AMR prediction based on the non-linear dimensionality reduction method - generative topographic mapping (GTM). This approach, applied to AMR data of >5000 S. aureus isolates retrieved from the PATRIC database, yielded GTM models with reasonable accuracy for all drugs (balanced accuracy values ≥0.75). The Generative Topographic Maps (GTMs) represent data in the form of illustrative maps of the genomic space and allow for antibiotic-wise comparison of resistant phenotypes. The maps were also found to be useful for the analysis of genetic determinants responsible for drug resistance. Overall, the GTM-based methodology is a useful tool for both the illustrative exploration of the genomic sequence space and AMR prediction.

Tackling the Antimicrobial Resistance "Pandemic" with Machine Learning Tools: A Summary of Available Evidence

Antimicrobial resistance is recognised as one of the top threats healthcare is bound to face in the future. There have been various attempts to preserve the efficacy of existing antimicrobials, develop new and efficient antimicrobials, manage infections with multi-drug resistant strains, and improve patient outcomes, resulting in a growing mass of routinely available data, including electronic health records and microbiological information that can be employed to develop individualised antimicrobial stewardship. Machine learning methods have been developed to predict antimicrobial resistance from whole-genome sequencing data, forecast medication susceptibility, recognise epidemic patterns for surveillance purposes, or propose new antibacterial treatments and accelerate scientific discovery. Unfortunately, there is an evident gap between the number of machine learning applications in science and the effective implementation of these systems. This narrative review highlights some of the outstanding opportunities that machine learning offers when applied in research related to antimicrobial resistance. In the future, machine learning tools may prove to be superbugs' kryptonite. This review aims to provide an overview of available publications to aid researchers that are looking to expand their work with new approaches and to acquaint them with the current application of machine learning techniques in this field.

Applications of tandem mass spectrometry (MS/MS) in antimicrobial peptides field: Current state and new applications

Antimicrobial peptides (AMPs) constitute a group of small molecular peptides that exhibit a wide range of antimicrobial activity. These peptides are abundantly present in the innate immune system of various organisms. Given the rise of multidrug-resistant bacteria, microbiological studies have identified AMPs as potential natural antibiotics. In the context of antimicrobial resistance across various human pathogens, AMPs hold considerable promise for clinical applications. However, numerous challenges exist in the detection of AMPs, particularly by immunological and molecular biological methods, especially when studying of newly discovered AMPs in proteomics. This review outlines the current status of AMPs research and the strategies employed in their development, considering resent discoveries and methodologies. Subsequently, we focus on the advanced techniques of mass spectrometry for the quantification of AMPs in diverse samples, and analyzes their application, advantages, and limitations. Additionally, we propose suggestions for the future development of tandem mass spectrometry for the detection of AMPs.

The antibacterial activity and mechanism of a novel peptide MR-22 against multidrug-resistant Escherichia coli

Introduction

Bacterial infections have become serious threats to human health, and the excessive use of antibiotics has led to the emergence of multidrug-resistant (MDR) bacteria. E. coli is a human bacterial pathogen, which can cause severe infectious. Antimicrobial peptides are considered the most promising alternative to traditional antibiotics.

Materials and methods

The minimum inhibitory concentration (MIC), minimum bactericidal concentration (MBC) and hemolytic activity were determined by the microdilution method. The antimicrobial kinetics of MR-22 against E. coli were studied by growth curves and time-killing curves. The cytotoxicity of MR-22 was detected by the CCK-8 assay. The antimicrobial activity of MR-22 in salt, serum, heat and trypsin was determined by the microdilution method. The antimicrobial mechanism of MR-22 against drug-resistant E. coli was studied by Scanning Electron Microscope, laser confocal microscopy, and Flow Cytometry. The in vivo antibacterial activity of MR-22 was evaluated by the mice model of peritonitis.

Results and discussion

In this study, MR-22 is a new antimicrobial peptide with good activity that has demonstrated against MDR E. coli. The antimicrobial activity of MR-22 exhibited stability under conditions of high temperature, 10% FBS, and Ca2+. However, a decline of the activity was observed in the presence of Na+, serum, and trypsin. MR-22 had no significant cytotoxicity or hemolysis in vitro. SEM and fluorescent images revealed that MR-22 could disrupt the integrity of cell membrane. DCFH-DA indicated that MR-22 increased the content of reactive oxygen species, while it decreased the content of intracellular ATP. In mice model of peritonitis, MR-22 exhibited potent antibacterial activity in vivo. These results indicated that MR-22 is a potential drug candidate against drug-resistant E. coli.

Machine learning and phylogenetic analysis allow for predicting antibiotic resistance in M. tuberculosis

BACKGROUND

Antimicrobial resistance (AMR) poses a significant global health threat, and an accurate prediction of bacterial resistance patterns is critical for effective treatment and control strategies. In recent years, machine learning (ML) approaches have emerged as powerful tools for analyzing large-scale bacterial AMR data. However, ML methods often ignore evolutionary relationships among bacterial strains, which can greatly impact performance of the ML methods, especially if resistance-associated features are attempted to be detected. Genome-wide association studies (GWAS) methods like linear mixed models accounts for the evolutionary relationships in bacteria, but they uncover only highly significant variants which have already been reported in literature.

RESULTS

In this work, we introduce a novel phylogeny-related parallelism score (PRPS), which measures whether a certain feature is correlated with the population structure of a set of samples. We demonstrate that PRPS can be used, in combination with SVM- and random forest-based models, to reduce the number of features in the analysis, while simultaneously increasing models' performance. We applied our pipeline to publicly available AMR data from PATRIC database for Mycobacterium tuberculosis against six common antibiotics.

CONCLUSIONS

Using our pipeline, we re-discovered known resistance-associated mutations as well as new candidate mutations which can be related to resistance and not previously reported in the literature. We demonstrated that taking into account phylogenetic relationships not only improves the model performance, but also yields more biologically relevant predicted most contributing resistance markers.

Multimodal learning in clinical proteomics: enhancing antimicrobial resistance prediction models with chemical information

MOTIVATION

Large-scale clinical proteomics datasets of infectious pathogens, combined with antimicrobial resistance outcomes, have recently opened the door for machine learning models which aim to improve clinical treatment by predicting resistance early. However, existing prediction frameworks typically train a separate model for each antimicrobial and species in order to predict a pathogen's resistance outcome, resulting in missed opportunities for chemical knowledge transfer and generalizability.

RESULTS

We demonstrate the effectiveness of multimodal learning over proteomic and chemical features by exploring two clinically relevant tasks for our proposed deep learning models: drug recommendation and generalized resistance prediction. By adopting this multi-view representation of the pathogenic samples and leveraging the scale of the available datasets, our models outperformed the previous single-drug and single-species predictive models by statistically significant margins. We extensively validated the multi-drug setting, highlighting the challenges in generalizing beyond the training data distribution, and quantitatively demonstrate how suitable representations of antimicrobial drugs constitute a crucial tool in the development of clinically relevant predictive models.

AVAILABILITY AND IMPLEMENTATION

The code used to produce the results presented in this article is available at https://github.com/BorgwardtLab/MultimodalAMR.

Prevalence of Multidrug-Resistant Pathogens Causing Neonatal Early and Late Onset Sepsis, a Retrospective Study from the Tertiary Referral Children's Hospital

Introduction

Sepsis is the most severe infectious disease with the highest mortality rate, particularly among neonates admitted to the neonatal intensive care unit (NICU). This study retrospectively analyzed the epidemiology, antibiotic resistance profiles, and prevalence of multidrug-resistant (MDR) bacteria isolated from blood or cerebrospinal fluid (CSF) cultures in order to evaluate the appropriateness of initial empirical therapy for neonatal sepsis.

Methods

A retrospective study was conducted in the NICU from January 1, 2015, to December 31, 2022. Microbiological data from patients admitted to the NICU were anonymously extracted from the Laboratory of Microbiology database. Neonatal sepsis was classified into two types: early-onset sepsis (EOS), which occurs within the first 72 hours of life, and late-onset sepsis (LOS) for those begins later.

Results

A total of 679 bacterial strains, 543 from blood and 136 from CSF, were detected in 631 neonates. Among these, 378 isolates (55.67%) were Gram-positive bacteria, and 301 isolates (44.33%) were Gram-negative bacteria. The most frequently isolated pathogens were Coagulase-negative staphylococci (CoNS) (36.52%), followed by Klebsiella pneumoniae (20.47%) and Escherichia coli (13.84%). In EOS, 121 strains were found, CoNS represented the majority (33.88%), followed by Klebsiella pneumoniae (23.97%) and Escherichia coli (8.26%). Early-onset septicemia exhibited 67 (55.37%) MDR bacteria. In LOS, 558 strains were isolated, CoNS represented the majority of pathogens (37.10%), followed by Klebsiella pneumoniae (19.71%) and Escherichia coli (15.05%). Late-onset septicemia showed 332 (59.50%) MDR bacteria. High rates of MDR were found in CoNS (76.21%), carbapenem-resistant Klebsiella pneumoniae (66.91%), and MRSA (33.33%).

Conclusion

The study revealed an alarming prevalence of MDR strains isolated from neonatal sepsis, emphasizing the necessity of finding effective prevention and treatment measures. Colistin can be used for MDR Gram-negative bacteria, while vancomycin and teicoplanin can be considered treatment therapies for staphylococcal infections.

Developing a Warning Model of Potentially Inappropriate Medications in Older Chinese Outpatients in Tertiary Hospitals: A Machine-Learning Study

Due to multiple comorbid illnesses, polypharmacy, and age-related changes in pharmacokinetics and pharmacodynamics in older adults, the prevalence of potentially inappropriate medications (PIMs) is high, which affects the quality of life of older adults. Building an effective warning model is necessary for the early identification of PIMs to prevent harm caused by medication in geriatric patients. The purpose of this study was to develop a machine learning-based model for the warning of PIMs in older Chinese outpatients. This retrospective study was conducted among geriatric outpatients in nine tertiary hospitals in Chengdu from January 2018 to December 2018. The Beers criteria 2019 were used to assess PIMs in geriatric outpatients. Three problem transformation methods were used to tackle the multilabel classification problem in prescriptions. After the division of patient prescriptions into the training and test sets (8:2), we adopted six widely used classification algorithms to conduct the classification task and assessed the discriminative performance by the accuracy, precision, recall, F1 scores, subset accuracy (ss Acc), and Hamming loss (hm) of each model. The results showed that among 11,741 older patient prescriptions, 5816 PIMs were identified in 4038 (34.39%) patient prescriptions. A total of 41 types of PIMs were identified in these prescriptions. The three-problem transformation methods included label power set (LP), classifier chains (CC), and binary relevance (BR). Six classification algorithms were used to establish the warning models, including Random Forest (RF), Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting (XGBoost), CatBoost, Deep Forest (DF), and TabNet. The CC + CatBoost model had the highest accuracy value (97.83%), recall value (89.34%), F1 value (90.69%), and ss Acc value (97.79%) with a good precision value (92.18%) and the lowest hm value (0.0006). Therefore, the CC + CatBoost model was selected to predict the occurrence of PIM in geriatric Chinese patients. This study’s novelty establishes a warning model for PIMs in geriatric patients by using machine learning. With the popularity of electronic patient record systems, sophisticated computer algorithms can be implemented at the bedside to improve medication use safety in geriatric patients in the future.

A new complex of silver(I) with probenecid: Synthesis, characterization, and studies of antibacterial and extended spectrum β-lactamases (ESBL) inhibition activities

This article describes the in vitro antibacterial and β-lactamase inhibition of a novel silver(I) complex with the sulfonamide probenecid (Ag-PROB). The formula Ag₂C₂₆H₃₆N2O₈S₂·2H₂O for the Ag-PROB complex was proposed based on elemental analysis. High-resolution mass spectrometric studies revealed the existence of the complex in its dimeric form. Infrared, nuclear magnetic resonance spectroscopies and Density Functional Theory calculations indicated a bidentate coordination of probenecid to the silver ions by the oxygen atoms of the carboxylate. In vitro antibacterial activities of Ag-PROB showed significant growth inhibitory activity over Mycobacterium tuberculosis, S. aureus, and P. aeruginosa PA01biofilm-producers, B. cereus, and E. coli. The Ag-PROB complex was active over multi-drug resistant of uropathogenic E. coli extended spectrum β-lactamases (ESBL) producing (EC958 and BR43), enterohemorrhagic E. coli (O157:H7) and enteroaggregative E. coli (O104:H4). Ag-PROB was able to inhibit CTX-M-15 and TEM-1B ESBL classes, at concentrations below the minimum inhibitory concentration for Ag-PROB, in the presence of ampicillin (AMP) concentration in which EC958 and BR43 bacteria were resistant in the absence of Ag-PROB. These results indicate that, in addition to ESBL inhibition, there is a synergistic antibacterial effect between AMP and the Ag-PROB. Molecular docking results revealed potential key residues involved in interactions between Ag-PROB, CTX-M-15 and TEM1B, suggesting the molecular mechanism of the ESBL inhibition. The obtained results added to the absence of mutagenic activity and low cytotoxic activity over non-tumor cell of the Ag-PROB complex open a new perspective for future in vivo tests demonstrating its potential of use as an antibacterial agent.