Applications of Machine Learning to the Problem of Antimicrobial Resistance: an Emerging Model for Translational Research

Journal of Clinical Microbiology, Journal Year: 2021, Volume and Issue: 59(7)

Published: Jan. 29, 2021

Antimicrobial resistance (AMR) remains one of the most challenging phenomena modern medicine. Machine learning (ML) is a subfield artificial intelligence that focuses on development algorithms learn how to accurately predict outcome variables using large sets predictor are typically not hand selected and minimally curated.

Language: Английский

---

Machine Learning for Antimicrobial Resistance Prediction: Current Practice, Limitations, and Clinical Perspective

Clinical Microbiology Reviews, Journal Year: 2022, Volume and Issue: 35(3)

Published: May 25, 2022

Antimicrobial resistance (AMR) is a global health crisis that poses great threat to modern medicine. Effective prevention strategies are urgently required slow the emergence and further dissemination of AMR. Given availability data sets encompassing hundreds or thousands pathogen genomes, machine learning (ML) increasingly being used predict different antibiotics in pathogens based on gene content genome composition. A key objective this work advocate for incorporation ML into front-line settings but also highlight refinements necessary safely confidently incorporate these methods. The question what not trivial given existence quantitative qualitative laboratory measures models typically treat genes as independent predictors, with no consideration structural functional linkages; they may be accurate when new mutational variants known AMR emerge. Finally, have technology trusted by end users public settings, need transparent explainable ensure basis prediction clear. We strongly next set AMR-ML studies should focus refinement limitations able bridge gap diagnostic implementation.

Language: Английский

---

Artificial Intelligence for Antimicrobial Resistance Prediction: Challenges and Opportunities towards Practical Implementation

Antibiotics, Journal Year: 2023, Volume and Issue: 12(3), P. 523 - 523

Published: March 6, 2023

Antimicrobial resistance (AMR) is emerging as a potential threat to many lives worldwide. It very important understand and apply effective strategies counter the impact of AMR its mutation from medical treatment point view. The intersection artificial intelligence (AI), especially deep learning/machine learning, has led new direction in antimicrobial identification. Furthermore, presently, availability huge amounts data multiple sources made it more use these techniques identify interesting insights into genes such genes, mutations, drug identification, conditions favorable spread, so on. Therefore, this paper presents review state-of-the-art challenges opportunities. These include input features posing use, deep-learning/machine-learning models for robustness high accuracy, challenges, prospects practical purposes. concludes with encouragement AI sector intention diagnosis treatment, since presently most studies are at early stages minimal application practice disease.

Language: Английский

---

Applications of Raman Spectroscopy in Bacterial Infections: Principles, Advantages, and Shortcomings

Frontiers in Microbiology, Journal Year: 2021, Volume and Issue: 12

Published: July 19, 2021

Infectious diseases caused by bacterial pathogens are important public issues. In addition, due to the overuse of antibiotics, many multidrug-resistant have been widely encountered in clinical settings. Thus, fast identification bacteria and profiling antibiotic resistance could greatly facilitate precise treatment strategy infectious diseases. So far, conventional molecular methods, both manual or automatized, developed for vitro diagnostics, which proven be accurate, reliable, time efficient. Although Raman spectroscopy (RS) is an established technique various fields such as geochemistry material science, it still considered emerging tool research diagnosis Based on current studies, too early claim that RS may provide practical guidelines microbiologists clinicians because there a gap between basic implementation. However, promising prospects label-free detection noninvasive infections several single steps, necessary overview terms its strong points shortcomings. this review, we went through recent studies field diseases, highlighting application potentials also challenges prevent real-world applications.

Language: Английский

---

Application and Challenge of 3rd Generation Sequencing for Clinical Bacterial Studies

International Journal of Molecular Sciences, Journal Year: 2022, Volume and Issue: 23(3), P. 1395 - 1395

Published: Jan. 26, 2022

Over the past 25 years, powerful combination of genome sequencing and bioinformatics analysis has played a crucial role in interpreting information encoded bacterial genomes. High-throughput technologies have paved way towards understanding an increasingly wide range biological questions. This revolution enabled advances areas ranging from composition to how proteins interact with nucleic acids. created unprecedented opportunities through integration genomic data into clinics for diagnosis genetic traits associated disease. Since then, these continued evolve, recently, long-read overcome previous limitations terms accuracy, thus expanding its applications genomics, transcriptomics metagenomics. In this review, we describe brief history application public health molecular epidemiology. We present chronology that encompasses various technological developments: whole-genome shotgun sequencing, high-throughput sequencing. mainly discuss next-generation decipher Secondly, highlight go beyond traditional short-read intend provide description guiding principles 3rd generation ongoing improvements field microbial medical research.

Language: Английский

---

Current Uses and Future Perspectives of Genomic Technologies in Clinical Microbiology

Antibiotics, Journal Year: 2023, Volume and Issue: 12(11), P. 1580 - 1580

Published: Oct. 30, 2023

Recent advancements in sequencing technology and data analytics have led to a transformative era pathogen detection typing. These developments not only expedite the process, but also render it more cost-effective. Genomic analyses of infectious diseases are swiftly becoming standard for analysis control. Additionally, national surveillance systems can derive substantial benefits from genomic data, as they offer profound insights into epidemiology emergence antimicrobial-resistant strains. Antimicrobial resistance (AMR) is pressing global public health issue. While clinical laboratories traditionally relied on culture-based antimicrobial susceptibility testing, integration AMR holds immense promise. Genomic-based furnish swift, consistent, highly accurate predictions phenotypes specific strains or populations, all while contributing invaluable surveillance. Moreover, genome assumes pivotal role investigation hospital outbreaks. It aids identification infection sources, unveils genetic connections among isolates, informs strategies The One Health initiative, with its focus intricate interconnectedness humans, animals, environment, seeks develop comprehensive approaches disease surveillance, control, prevention. When integrated epidemiological systems, forecast expansion bacterial populations species transmissions. Consequently, this provides evolution relationships pathogens, hosts, environment.

Language: Английский

---

Benchmarking bacterial genome-wide association study methods using simulated genomes and phenotypes

Microbial Genomics, Journal Year: 2020, Volume and Issue: 6(3)

Published: Feb. 25, 2020

Genome-wide association studies (GWASs) have the potential to reveal genetics of microbial phenotypes such as antibiotic resistance and virulence. Capitalizing on growing wealth bacterial sequence data, GWAS methods aim identify causal genetic variants while ignoring spurious associations. Bacteria reproduce clonally, leading strong population structure genome-wide linkage, making it challenging separate true ‘hits’ (i.e. mutations that cause a phenotype) from non-causal linked mutations. attempt correct for in different ways, but their performance has not yet been systematically comprehensively evaluated under range evolutionary scenarios. Here, we developed simulator (BacGWASim) generate genomes with varying rates mutation, recombination other parameters, along subset underlying phenotype interest. We assessed (recall precision) three widely used single-locus approaches (cluster-based, dimensionality-reduction linear mixed models, implemented plink , pyseer gemma ) one relatively new multi-locus model pyseer, across simulated sample sizes, mutation effect sizes. As expected, all performed better larger sizes The clustering dimensionality reduction were considerably variable according choice parameters. Notably, elastic net (lasso) approach was consistently amongst highest-performing methods, had highest power detecting both low high Most reached level good >0.75) identifying size [log odds ratio (OR) ≥2] 2000 genomes. However, only nets reasonable (recall=0.35) markers weaker effects (log OR ~1) smaller samples. Elastic also showed superior precision recall controlling relative models. poorly highly clonal (low-recombining) genomes, suggesting room improvement method development. These findings show models improve performance. BacGWASim code data are publicly available enable further comparisons benchmarking methods.

Language: Английский

---

Forest and Trees: Exploring Bacterial Virulence with Genome-wide Association Studies and Machine Learning

Trends in Microbiology, Journal Year: 2021, Volume and Issue: 29(7), P. 621 - 633

Published: Jan. 14, 2021

Language: Английский

---

Predicting Phenotypic Polymyxin Resistance in Klebsiella pneumoniae through Machine Learning Analysis of Genomic Data

mSystems, Journal Year: 2020, Volume and Issue: 5(3)

Published: May 25, 2020

Polymyxins are last-resort antibiotics used to treat highly resistant Gram-negative bacteria. There increasing reports of polymyxin resistance emerging, raising concerns a postantibiotic era. Polymyxin is therefore significant public health threat, but current phenotypic methods for detection difficult and time-consuming perform. have been efforts use whole-genome sequencing antibiotic resistance, this has apply because its complex polygenic nature. The significance our research that we successfully applied machine learning predict in Klebsiella pneumoniae clonal group 258, common care-associated multidrug-resistant pathogen. Our findings highlight can be even forms represent contribution the literature could other bacteria antibiotics.

Language: Английский

---

Increased power from conditional bacterial genome-wide association identifies macrolide resistance mutations in Neisseria gonorrhoeae

Nature Communications, Journal Year: 2020, Volume and Issue: 11(1)

Published: Oct. 23, 2020

Abstract The emergence of resistance to azithromycin complicates treatment Neisseria gonorrhoeae , the etiologic agent gonorrhea. Substantial remains unexplained after accounting for known mutations. Bacterial genome-wide association studies (GWAS) can identify novel genes but must control genetic confounders while maintaining power. Here, we show that compared single-locus GWAS, conducting GWAS conditioned on mutations reduces number false positives and identifies a G70D mutation in RplD 50S ribosomal protein L4 as significantly associated with increased ( p -value = 1.08 × 10 −11 ). We experimentally confirm our results demonstrate other macrolide binding site are prevalent (present 5.42% 4850 isolates) widespread (identified 21/65 countries across two decades). Overall, findings utility conditional associations improving performance microbial advance understanding basis resistance.

Language: Английский

---