Dataset Information

Using random forest to predict antimicrobial minimum inhibitory concentrations of nontyphoidal Salmonella in Taiwan.

ABSTRACT: Antimicrobial resistance (AMR) is a global health issue and surveillance of AMR can be useful for understanding AMR trends and planning intervention strategies. Salmonella, widely distributed in food-producing animals, has been considered the first priority for inclusion in the AMR surveillance program by the World Health Organization (WHO). Recent advances in rapid and affordable whole-genome sequencing (WGS) techniques lead to the emergence of WGS as a one-stop test to predict the antimicrobial susceptibility. Since the variation of sequencing and minimum inhibitory concentration (MIC) measurement methods could result in different results, this study aimed to develop WGS-based random forest models for predicting MIC values of 24 drugs using data generated from the same laboratories in Taiwan. The WGS data have been transformed as a feature vector of 10-mers for machine learning. Based on rigorous validation and independent tests, a good performance was obtained with an average mean absolute error (MAE) less than 1 for both validation and independent test. Feature selection was then applied to identify top-ranked 10-mers that can further improve the prediction performance. For surveillance purposes, the genome sequence-based machine learning methods could be utilized to monitor the difference between predicted and experimental MIC, where a large difference might be worthy of investigation on the emerging genomic determinants.

SUBMITTER: Wang CC

PROVIDER: S-EPMC9903507 | biostudies-literature | 2023 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using random forest to predict antimicrobial minimum inhibitory concentrations of nontyphoidal Salmonella in Taiwan.

Wang Chia-Chi CC Hung Yu-Ting YT Chou Che-Yu CY Hsuan Shih-Ling SL Chen Zeng-Weng ZW Chang Pei-Yu PY Jan Tong-Rong TR Tung Chun-Wei CW

Veterinary research 20230206 1

Antimicrobial resistance (AMR) is a global health issue and surveillance of AMR can be useful for understanding AMR trends and planning intervention strategies. Salmonella, widely distributed in food-producing animals, has been considered the first priority for inclusion in the AMR surveillance program by the World Health Organization (WHO). Recent advances in rapid and affordable whole-genome sequencing (WGS) techniques lead to the emergence of WGS as a one-stop test to predict the antimicrobia ...[more]

PMID: 36747286

Similar Datasets

Project description:Antimicrobial resistance was investigated in 2,341 nontyphoidal Salmonella (NTS) isolates recovered from humans in Taiwan from 2017 to 2018 using antimicrobial susceptibility testing. Azithromycin resistance determinants were detected in 175 selected isolates using PCR and confirmed in 81 selected isolates using whole-genome sequencing. Multidrug resistance was found in 47.3% of total isolates and 96.2% of Salmonella enterica serovar Anatum and 81.7% of S. enterica serovar Typhimurium isolates. Resistance to the conventional first-line drugs (ampicillin, chloramphenicol, and cotrimoxazole), cefotaxime and ceftazidime, and ciprofloxacin was found in 32.5 to 49.0%, 20.3 to 20.4%, and 3.2% of isolates, respectively. A total of 76 (3.1%) isolates were resistant to azithromycin, which was associated with mph(A), erm(42), erm(B), and possibly the enhanced expression of efflux pump(s) due to ramAp or defective ramR. mph(A) was found in 53% of the 76 azithromycin-resistant isolates from 11 serovars and located in an IS26-mph(A)-mrx(A)-mphR(A)-IS6100 unit in various incompatibility plasmids and the chromosomes. erm(42) in S. enterica serovar Albany was carried by an integrative and conjugative element, ICE_erm42, and in S. enterica serovar Enteritidis and S. Typhimurium was located in IS26 composite transposons in the chromosomes. erm(B) was carried by IncI1-I(α) plasmids in S. Enteritidis and S. Typhimurium. ramAp was a plasmid-borne ramA, a regulatory activator of efflux pump(s), found in only S. enterica serovar Goldcoast. Since the azithromycin resistance determinants are primarily carried on mobile genetic elements, they could easily be disseminated among human bacterial pathogens. The ramAp-carrying S. Goldcoast isolates displayed azithromycin MICs of 16 to 32 mg/L. Thus, the epidemiological cutoff value of ≤16 mg/L of azithromycin proposed for wild-type NTS should be reconsidered. IMPORTANCE Antimicrobial resistance in NTS isolates is a major public health concern in Taiwan, and the mechanisms of azithromycin resistance are rarely investigated. Azithromycin and carbapenems are the last resort for the treatment of invasive salmonellosis caused by multidrug-resistant (MDR) and extensively drug-resistant Salmonella strains. Our study reports the epidemiological trend of resistance in NTS in Taiwan and the genetic determinants involved in azithromycin resistance. We point out that nearly half of NTS isolates from 2017 to 2018 are MDR, and 20% are resistant to third-generation cephalosporins. The azithromycin resistance rate (3.1%) for the NTS isolates from Taiwan is much higher than those for the NTS isolates from the United States and Europe. Our study also indicates that azithromycin resistance is primarily mediated by mph(A), erm(42), erm(B), and ramAp, which are frequently carried on mobile genetic elements. Thus, the azithromycin resistance determinants could be expected to be disseminated among diverse bacterial pathogens.

Dataset Information

Using random forest to predict antimicrobial minimum inhibitory concentrations of nontyphoidal Salmonella in Taiwan.

Publications

Using random forest to predict antimicrobial minimum inhibitory concentrations of nontyphoidal Salmonella in Taiwan.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets