Evaluation of Machine Learning Models for Predicting Antimicrobial Resistance of Actinobacillus pleuropneumoniae From Whole Genome Sequences

Liu, Zhichang; Deng, Dun; Lu, Huijie; Sun, Jian; Lv, Luchao; Li, Shuhong; Guang-hui, Peng; Ma, Xianyong; Li, Jiazhou; Li, Zhenming; Rong, Ting; Wang, Gang

doi:10.3389/fmicb.2020.00048

Cited by 62 publications

(51 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One major drawback of using WGS-based antimicrobial resistance prediction is that only known genes associated with resistance development can be reliably interpreted. However, some machine-learning algorithms for reliable prediction of novel antimicrobial resistance determinants have been developed and successively optimized [ 70 , 71 ].…”

Section: Resultsmentioning

confidence: 99%

Outcome of Different Sequencing and Assembly Approaches on the Detection of Plasmids and Localization of Antimicrobial Resistance Genes in Commensal Escherichia coli

et al. 2021

View full text Add to dashboard Cite

Antimicrobial resistance (AMR) is a major threat to public health worldwide. Currently, AMR typing changes from phenotypic testing to whole-genome sequence (WGS)-based detection of resistance determinants for a better understanding of the isolate diversity and elements involved in gene transmission (e.g., plasmids, bacteriophages, transposons). However, the use of WGS data in monitoring purposes requires suitable techniques, standardized parameters and approved guidelines for reliable AMR gene detection and prediction of their association with mobile genetic elements (plasmids). In this study, different sequencing and assembly strategies were tested for their suitability in AMR monitoring in Escherichia coli in the routines of the German National Reference Laboratory for Antimicrobial Resistances. To assess the outcomes of the different approaches, results from in silico predictions were compared with conventional phenotypic- and genotypic-typing data. With the focus on (fluoro)quinolone-resistant E.coli, five qnrS-positive isolates with multiple extrachromosomal elements were subjected to WGS with NextSeq (Illumina), PacBio (Pacific BioSciences) and ONT (Oxford Nanopore) for in depth characterization of the qnrS1-carrying plasmids. Raw reads from short- and long-read sequencing were assembled individually by Unicycler or Flye or a combination of both (hybrid assembly). The generated contigs were subjected to bioinformatics analysis. Based on the generated data, assembly of long-read sequences are error prone and can yield in a loss of small plasmid genomes. In contrast, short-read sequencing was shown to be insufficient for the prediction of a linkage of AMR genes (e.g., qnrS1) to specific plasmid sequences. Furthermore, short-read sequencing failed to detect certain duplications and was unsuitable for genome finishing. Overall, the hybrid assembly led to the most comprehensive typing results, especially in predicting associations of AMR genes and mobile genetic elements. Thus, the use of different sequencing technologies and hybrid assemblies currently represents the best approach for reliable AMR typing and risk assessment.

show abstract

Section: Resultsmentioning

confidence: 99%

Outcome of Different Sequencing and Assembly Approaches on the Detection of Plasmids and Localization of Antimicrobial Resistance Genes in Commensal Escherichia coli

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The challenges of obtaining evidencebased AMR surveillance remain the lack of standardized data and periodic updates [194,[205][206][207]. AI techniques used different methods to improve AST that include the combination of flow cytometer-assisted antimicrobial susceptibility test (FAST) and machine learning techniques [203] and IR-spectrometer method that combines infrared (IR) spectroscopy with the artificial neural network [208]. For WGS-AST, the Support Vector Machine (SVM) and the Set Covering Machine (SCM) models are used to learn and predict AMR phenotypes [179,209].The SCM model allows genotype-to-phenotype predictions [192].…”

Section: Capitalizing On New Technologiesmentioning

confidence: 99%

Surveillance of antimicrobial resistance in low- and middle-income countries: a scattered picture

Iskandar

Molinier

Hallit

et al. 2021

Antimicrob Resist Infect Control

232

144

View full text Add to dashboard Cite

Data on comprehensive population-based surveillance of antimicrobial resistance is lacking. In low- and middle-income countries, the challenges are high due to weak laboratory capacity, poor health systems governance, lack of health information systems, and limited resources. Developing countries struggle with political and social dilemma, and bear a high health and economic burden of communicable diseases. Available data are fragmented and lack representativeness which limits their use to advice health policy makers and orientate the efficient allocation of funding and financial resources on programs to mitigate resistance. Low-quality data means soaring rates of antimicrobial resistance and the inability to track and map the spread of resistance, detect early outbreaks, and set national health policy to tackle resistance. Here, we review the barriers and limitations of conducting effective antimicrobial resistance surveillance, and we highlight multiple incremental approaches that may offer opportunities to strengthen population-based surveillance if tailored to the context of each country.

show abstract

“…They can also study these illustrations in an automatic manner and mapping the molecules into vector which are afterwards used to forecast their attributes. 43 Lui and co-workers 44 carried out a research by applying the Support Vector Machine (SVM) and Set Covering Machine (SCM) algorithm to precisely foretell their phenotypic appear ance versus five agents of antimicrobial which are: Tetracycline, Ampicillin, Sulfisoxazole, Trimethoprim, and Enrofloxacinfrom the whole genomes of 96 isolates of A. pleuropneumoniae. Amidst the five agents of antimicrobial, the resistant activity of A. pleuropneumoniae versus tetracycline is more difficult than the others.…”

Section: Citationmentioning

confidence: 99%

“…58 phenotype resistant strains were available, with 50 isolates transporting tet (B), 5 isolates transporting tet (H), and in 3 isolates, the resistance genes of tetracycline were not noticed. 44…”

Section: Citationmentioning

confidence: 99%

War against antimicrobial resistance

Akinwotu¹,

Fapohunda²

2020

JMEN

View full text Add to dashboard Cite

Resistance to antimicrobials is a global threat that demands immediate response. The excessive use and misuse of antimicrobials has led to the development of multidrug resistant strains of microorganisms. As the consumption rate of these drugs increases, the resistance rate also increases, resulting in high cost of medical treatment and increased mortality rate. To war against antimicrobial resistance, the biochemical and genetic mechanism of resistance in microorganisms is a key factor to be considered. Recent articles from reputable journals/archives including PubMed, Scopus, Google Scholar, ResearchGate etc were retrieved and studied and we discovered that much have been researched on the importance of drugs in the treatment of antimicrobial resistance and in recent decade researchers have been delving into important botanicals that could address multidrug resistance with several opinions. Researchers have opinionated that phytoconstituents could be potential drugs that would address antimicrobial resistance with little or no side effect and they are relatively cheap and readily available to low-income people. However, the future is largely going to be machine driven and little have been reported on the emerging technologies that could adequately tackle this menace of antimicrobial resistance. Here we succinctly discussed how some of these promising technologies could be employed in combating the resistance of microorganism to antibiotics; the use of vaccine technologies, the use of Artificial Intelligence coupled with machine learning algorithms, the use of nanosystems and the use of CRISPR-cas technology.

show abstract

Evaluation of Machine Learning Models for Predicting Antimicrobial Resistance of Actinobacillus pleuropneumoniae From Whole Genome Sequences

Cited by 62 publications

References 18 publications

Outcome of Different Sequencing and Assembly Approaches on the Detection of Plasmids and Localization of Antimicrobial Resistance Genes in Commensal Escherichia coli

Outcome of Different Sequencing and Assembly Approaches on the Detection of Plasmids and Localization of Antimicrobial Resistance Genes in Commensal Escherichia coli

Surveillance of antimicrobial resistance in low- and middle-income countries: a scattered picture

War against antimicrobial resistance

Contact Info

Product

Resources

About