Dataset Information

Prediction of antimicrobial minimal inhibitory concentrations for Neisseria gonorrhoeae using machine learning models

ABSTRACT: The lowest concentration of an antimicrobial agent that can inhibit the visible growth of a microorganism after overnight incubation is called as minimum inhibitory concentration (MIC) and the drug prescriptions are made on the basis of MIC data to ensure successful treatment outcomes. Therefore, reliable antimicrobial susceptibility data is crucial, and it will help clinicians about which drug to prescribe. Although few prediction studies based on strategies have been conducted, however, no single machine learning (ML) modelling has been carried out to predict MICs in N. gonorrhoeae. In this study, we propose a ML based approach that can predict MICs of a specific antibiotic using unitigs sequences data. We retrieved N. gonorrhoeae genomes from European Nucleotide Archive and NCBI and analysed them combined with their respective MIC data for cefixime, ciprofloxacin, and azithromycin and then we constructed unitigs by using de Brujin graphs. We built and compared 35 different ML regression models to predict MICs. Our results demonstrate that RandomForest and CATBoost models showed best performance in predicting MICs of the three antibiotics. The coefficient of determination, R2, (a statistical measure of how well the regression predictions approximate the real data points) for cefixime, ciprofloxacin, and azithromycin was 0.75787, 0.77241, and 0.79009 respectively using RandomForest. For CATBoost model, the R2 value was 0.74570, 0.77393, and 0.79317 for cefixime, ciprofloxacin, and azithromycin respectively. Lastly, using feature importance, we explore the important genomic regions identified by the models for predicting MICs. The major mutations which are responsible for resistance against these three antibiotics were chosen by ML models as a top feature in case of each antibiotics. CATBoost, DecisionTree, GradientBoosting, and RandomForest regression models chose the same unitigs which are responsible for resistance. This unitigs-based strategy for developing models for MIC prediction, clinical diagnostics, and surveillance can be applicable for other critical bacterial pathogens.

SUBMITTER: Yasir M

PROVIDER: S-EPMC9280306 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Minimum Inhibitory Concentrations (MICs) are the gold standard for quantitatively measuring antibiotic resistance. However, lab-based MIC determination can be time-consuming and suffers from low reproducibility, and interpretation as sensitive or resistant relies on guidelines which change over time. Genome sequencing and machine learning promise to allow in silico MIC prediction as an alternative approach which overcomes some of these difficulties, albeit the interpretation of MIC is still needed. Nevertheless, precisely how we should handle MIC data when dealing with predictive models remains unclear, since they are measured semi-quantitatively, with varying resolution, and are typically also left- and right-censored within varying ranges. We therefore investigated genome-based prediction of MICs in the pathogen Klebsiella pneumoniae using 4367 genomes with both simulated semi-quantitative traits and real MICs. As we were focused on clinical interpretation, we used interpretable rather than black-box machine learning models, namely, Elastic Net, Random Forests, and linear mixed models. Simulated traits were generated accounting for oligogenic, polygenic, and homoplastic genetic effects with different levels of heritability. Then we assessed how model prediction accuracy was affected when MICs were framed as regression and classification. Our results showed that treating the MICs differently depending on the number of concentration levels of antibiotic available was the most promising learning strategy. Specifically, to optimise both prediction accuracy and inference of the correct causal variants, we recommend considering the MICs as continuous and framing the learning problem as a regression when the number of observed antibiotic concentration levels is large, whereas with a smaller number of concentration levels they should be treated as a categorical variable and the learning problem should be framed as a classification. Our findings also underline how predictive models can be improved when prior biological knowledge is taken into account, due to the varying genetic architecture of each antibiotic resistance trait. Finally, we emphasise that incrementing the population database is pivotal for the future clinical implementation of these models to support routine machine-learning based diagnostics.

Project description:Escherichia coli is an important cause of bacterial infections worldwide, with multidrug-resistant strains incurring substantial costs on human lives. Besides therapeutic concentrations of antimicrobials in health care settings, the presence of subinhibitory antimicrobial residues in the environment and in clinics selects for antimicrobial resistance (AMR), but the underlying genetic repertoire is less well understood. Here, we used machine learning to predict the population doubling time and cell growth yield of 1,407 genetically diverse E. coli strains expanding under exposure to three subinhibitory concentrations of six classes of antimicrobials from single-nucleotide genetic variants, accessory gene variation, and the presence of known AMR genes. We predicted cell growth yields in the held-out test data with an average correlation (Spearman's ρ) of 0.63 (0.36 to 0.81 across concentrations) and cell doubling times with an average correlation of 0.59 (0.32 to 0.92 across concentrations), with moderate increases in sample size unlikely to improve predictions further. This finding points to the remaining missing heritability of growth under antimicrobial exposure being explained by effects that are too rare or weak to be captured unless sample size is dramatically increased, or by effects other than those conferred by the presence of individual single-nucleotide polymorphisms (SNPs) and genes. Predictions based on whole-genome information were generally superior to those based only on known AMR genes and were accurate for AMR resistance at therapeutic concentrations. We pinpointed genes and SNPs determining the predicted growth and thereby recapitulated many known AMR determinants. Finally, we estimated the effect sizes of resistance genes across the entire collection of strains, disclosing the growth effects for known resistance genes in each individual strain. Our results underscore the potential of predictive modeling of growth patterns from genomic data under subinhibitory concentrations of antimicrobials, although the remaining missing heritability poses a challenge for achieving the accuracy and precision required for clinical use. IMPORTANCE Predicting bacterial growth from genome sequences is important for a rapid characterization of strains in clinical diagnostics and to disclose candidate novel targets for anti-infective drugs. Previous studies have dissected the relationship between bacterial growth and genotype in mutant libraries for laboratory strains, yet no study so far has examined the predictive power of genome sequence in natural strains. In this study, we used a high-throughput phenotypic assay to measure the growth of a systematic collection of natural Escherichia coli strains and then employed machine learning models to predict bacterial growth from genomic data under nontherapeutic subinhibitory concentrations of antimicrobials that are common in nonclinical settings. We found a moderate to strong correlation between predicted and actual values for the different collected data sets. Moreover, we observed that the known resistance genes are still effective at sublethal concentrations, pointing to clinical implications of these concentrations.

Project description:BackgroundAntimicrobial-resistant (AMR) Neisseria gonorrhoeae is an urgent threat to public health, as strains resistant to at least one of the two last-line antibiotics used in empiric therapy of gonorrhoea, ceftriaxone and azithromycin, have spread internationally. Whole genome sequencing (WGS) data can be used to identify new AMR clones and transmission networks and inform the development of point-of-care tests for antimicrobial susceptibility, novel antimicrobials and vaccines. Community-driven tools that provide an easy access to and analysis of genomic and epidemiological data is the way forward for public health surveillance.MethodsHere we present a public health-focussed scheme for genomic epidemiology of N. gonorrhoeae at Pathogenwatch ( https://pathogen.watch/ngonorrhoeae ). An international advisory group of experts in epidemiology, public health, genetics and genomics of N. gonorrhoeae was convened to inform on the utility of current and future analytics in the platform. We implement backwards compatibility with MLST, NG-MAST and NG-STAR typing schemes as well as an exhaustive library of genetic AMR determinants linked to a genotypic prediction of resistance to eight antibiotics. A collection of over 12,000 N. gonorrhoeae genome sequences from public archives has been quality-checked, assembled and made public together with available metadata for contextualization.ResultsAMR prediction from genome data revealed specificity values over 99% for azithromycin, ciprofloxacin and ceftriaxone and sensitivity values around 99% for benzylpenicillin and tetracycline. A case study using the Pathogenwatch collection of N. gonorrhoeae public genomes showed the global expansion of an azithromycin-resistant lineage carrying a mosaic mtr over at least the last 10 years, emphasising the power of Pathogenwatch to explore and evaluate genomic epidemiology questions of public health concern.ConclusionsThe N. gonorrhoeae scheme in Pathogenwatch provides customised bioinformatic pipelines guided by expert opinion that can be adapted to public health agencies and departments with little expertise in bioinformatics and lower-resourced settings with internet connection but limited computational infrastructure. The advisory group will assess and identify ongoing public health needs in the field of gonorrhoea, particularly regarding gonococcal AMR, in order to further enhance utility with modified or new analytic methods.

Project description:Nitrogen is the most limiting nutrient for turfgrass growth. Instead of pursuing the maximum yield, most turfgrass managers use nitrogen (N) to maintain a sub-maximal growth rate. Few tools or soil tests exist to help managers guide N fertilizer decisions. Turf growth prediction models have the potential to be useful, but the currently existing turf growth prediction model only takes temperature into account, limiting its accuracy. This study developed machine-learning-based turf growth models using the random forest (RF) algorithm to estimate short-term turfgrass clipping yield. To build the RF model, a large set of variables were extracted as predictors including the 7-day weather, traffic intensity, soil moisture content, N fertilization rate, and the normalized difference red edge (NDRE) vegetation index. In this study, the data were collected from two putting greens where the turfgrass received 0 to 1,800 round/week traffic rates, various irrigation rates to maintain the soil moisture content between 9 and 29%, and N fertilization rates of 0 to 17.5 kg ha-1 applied biweekly. The RF model agreed with the actual clipping yield collected from the experimental results. The temperature and relative humidity were the most important weather factors. Including NDRE improved the prediction accuracy of the model. The highest coefficient of determination (R2) of the RF model was 0.64 for the training dataset and was 0.47 for the testing data set upon the evaluation of the model. This represented a large improvement over the existing growth prediction model (R 2 = 0.01). However, the machine-learning models created were not able to accurately predict the clipping production at other locations. Individual golf courses can create customized growth prediction models using clipping volume to eliminate the deviation caused by temporal and spatial variability. Overall, this study demonstrated the feasibility of creating machine-learning-based yield prediction models that may be able to guide N fertilization decisions on golf course putting greens and presumably other turfgrass areas.

Project description:BackgroundAccurate and reliable predictions of infectious disease can be valuable to public health organizations that plan interventions to decrease or prevent disease transmission. A great variety of models have been developed for this task. However, for different data series, the performance of these models varies. Hepatitis E, as an acute liver disease, has been a major public health problem. Which model is more appropriate for predicting the incidence of hepatitis E? In this paper, three different methods are used and the performance of the three methods is compared.MethodsAutoregressive integrated moving average(ARIMA), support vector machine(SVM) and long short-term memory(LSTM) recurrent neural network were adopted and compared. ARIMA was implemented by python with the help of statsmodels. SVM was accomplished by matlab with libSVM library. LSTM was designed by ourselves with Keras, a deep learning library. To tackle the problem of overfitting caused by limited training samples, we adopted dropout and regularization strategies in our LSTM model. Experimental data were obtained from the monthly incidence and cases number of hepatitis E from January 2005 to December 2017 in Shandong province, China. We selected data from July 2015 to December 2017 to validate the models, and the rest was taken as training set. Three metrics were applied to compare the performance of models, including root mean square error(RMSE), mean absolute percentage error(MAPE) and mean absolute error(MAE).ResultsBy analyzing data, we took ARIMA(1, 1, 1), ARIMA(3, 1, 2) as monthly incidence prediction model and cases number prediction model, respectively. Cross-validation and grid search were used to optimize parameters of SVM. Penalty coefficient C and kernel function parameter g were set 8, 0.125 for incidence prediction, and 22, 0.01 for cases number prediction. LSTM has 4 nodes. Dropout and L2 regularization parameters were set 0.15, 0.001, respectively. By the metrics of RMSE, we obtained 0.022, 0.0204, 0.01 for incidence prediction, using ARIMA, SVM and LSTM. And we obtained 22.25, 20.0368, 11.75 for cases number prediction, using three models. For MAPE metrics, the results were 23.5%, 21.7%, 15.08%, and 23.6%, 21.44%, 13.6%, for incidence prediction and cases number prediction, respectively. For MAE metrics, the results were 0.018, 0.0167, 0.011 and 18.003, 16.5815, 9.984, for incidence prediction and cases number prediction, respectively.ConclusionsComparing ARIMA, SVM and LSTM, we found that nonlinear models(SVM, LSTM) outperform linear models(ARIMA). LSTM obtained the best performance in all three metrics of RSME, MAPE, MAE. Hence, LSTM is the most suitable for predicting hepatitis E monthly incidence and cases number.

Dataset Information

Prediction of antimicrobial minimal inhibitory concentrations for Neisseria gonorrhoeae using machine learning models

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets