MACHINE LEARNING–BASED PREDICTION OF CIPROFLOXACIN, CEFOTAXIME, CEFTA. ZIDIME, AND GENTAMICIN RESISTANCE USING BACTERIAL GENOMIC FEATURES
Abstract
The rise in antimicrobial resistance has made the need for quick and accurate methods that can predict bacterial resistance to antibiotics from their genome data a pressing necessity. In this study, machine-learning models for the prediction of resistance to ciprofloxacin, cefotaxime, ceftazidime and gentamicin were developed from bacterial genomic characteristics. The phenotypic resistance data was matched to the corresponding matrix of genomic features, and individual binary classification models were created for each antibiotic. Stratified training and testing subsets were used to evaluate logistic regression, random forest, support vector machine and gradient boosting. The accuracy, balanced accuracy, precision, sensitivity, specificity, F1-score, ROC-AUC, and confusion matrices were used to measure the model's performance. Of the 668 matched isolates, prevalence of resistance was highest for ciprofloxacin (44.2%), followed by cefotaxime (40.7%), ceftazidime (32.8%) and gentamicin (20.8%). Over 50% of the isolates were resistant to at least one antibiotic and 12.7% were resistant to all four antibiotics. Random forest and support vector machine (SVM) had the highest ROC-AUC (0.948 and 90.3% respectively) for prediction of Ciprofloxacin resistance. The results indicated that the predictive performance of ceftazidime and cefotaxime was moderate while the resistance to gentamicin was harder to classify due to lower prevalence and class imbalance. The results show that the machine learning, based on genomic features, is effective in supporting antibiotic resistance prediction, but the predictive quality differs depending on the antibiotics and should be tested in external data before be used in clinical practice.
Downloads
References
2.Anahtar, M. N., Bramante, J. T., Xu, J., Desrosiers, L. A., Paer, J. M., Rosenberg, E. S., ... & Kwon, D. S. (2022). Prediction of antimicrobial resistance in clinical Enterococcus faecium isolates using a rules-based analysis of whole-genome sequences. Antimicrobial Agents and Chemotherapy, 66(1), e01196-21.
3.Ardila, C. M., Yadalam, P. K., & González-Arroyave, D. (2024). Integrating whole genome sequencing and machine learning for predicting antimicrobial resistance in critical pathogens: a systematic review of antimicrobial susceptibility tests. PeerJ, 12, e18213.
4.Bortolaia, V., Kaas, R. S., Ruppe, E., Roberts, M. C., Schwarz, S., Cattoir, V., ... & Aarestrup, F. M. (2020). ResFinder 4.0 for predictions of phenotypes from genotypes. Journal of Antimicrobial Chemotherapy, 75(12), 3491-3500.
5.Doyle, R. M., O'sullivan, D. M., Aller, S. D., Bruchmann, S., Clark, T., Coello Pelegrin, A., ... & Harris, K. A. (2020). Discordant bioinformatic predictions of antimicrobial resistance from whole-genome sequencing data of bacterial isolates: an inter-laboratory study. Microbial genomics, 6(2), e000335.
6.Heydecke, A., Yin, H., Tano, E., & Sütterlin, S. (2023). Limitations in predicting reduced susceptibility to third generation cephalosporins in Escherichia coli based on whole genome sequence data. Plos one, 18(11), e0295233.
7.Humphries, R. M., Bragin, E., Parkhill, J., Morales, G., Schmitz, J. E., & Rhodes, P. A. (2023). Machine-learning model for prediction of cefepime susceptibility in Escherichia coli from whole-genome sequencing data. Journal of Clinical Microbiology, 61(3), e01431-22.
8.Jia, H., Li, X., Zhuang, Y., Wu, Y., Shi, S., Sun, Q., ... & Ruan, Z. (2024). Neural network-based predictions of antimicrobial resistance phenotypes in multidrug-resistant Acinetobacter baumannii from whole genome sequencing and gene expression. Antimicrobial Agents and Chemotherapy, 68(12), e01446-24.
9.Jin, C., Jia, C., Hu, W., Xu, H., Shen, Y., & Yue, M. (2024). Predicting antimicrobial resistance in E. coli with discriminative position fused deep learning classifier. Computational and Structural Biotechnology Journal, 23, 559-565.
10.Joddha, H. B., Mathakiya, R. A., Joshi, K. V., Khant, R. B., Golaviya, A. V., Hinsu, A. T., ... & Koringa, P. G. (2023). Profiling of antimicrobial resistance genes and integron from Escherichia coli isolates using whole genome sequencing. Genes, 14(6), 1212.
11.Kim, J. I., Maguire, F., Tsang, K. K., Gouliouris, T., Peacock, S. J., McAllister, T. A., ... & Beiko, R. G. (2022). Machine learning for antimicrobial resistance prediction: current practice, limitations, and clinical perspective. Clinical microbiology reviews, 35(3), e00179-21.
12.Kulkarni, V. (2025). Antimicrobial Resistance Dataset [Data set]. Kaggle. https://www.kaggle.com/datasets/vihaankulkarni/antimicrobial-resistance-dataset
13.Lau, H. J., Lim, C. H., Foo, S. C., & Tan, H. S. (2021). The role of artificial intelligence in the battle against antimicrobial-resistant bacteria. Current genetics, 67(3), 421-429.
14.Liu, Z., Deng, D., Lu, H., Sun, J., Lv, L., Li, S., ... & Wang, G. (2020). Evaluation of machine learning models for predicting antimicrobial resistance of Actinobacillus pleuropneumoniae from whole genome sequences. Frontiers in microbiology, 11, 48.
15.Maguire, F., Rehman, M. A., Carrillo, C., Diarra, M. S., & Beiko, R. G. (2019). Identification of primary antimicrobial resistance drivers in agricultural nontyphoidal Salmonella enterica serovars by using machine learning. Msystems, 4(4), 10-1128.
16.Moat, J., Zovoilis, A., Steinkey, R., Zaheer, R., McAllister, T., & Laing, C. (2025). Machine learning methods to identify markers and predict antimicrobial resistance in Escherichia coli. Canadian Journal of Microbiology, 71, 1-15.
17.Mohammad-Taheri, S., Navada, P. P., Hoyt, C. T., Zucker, J., Sachs, K., Gyori, B. M., & Vitek, O. (2024). Eliater: a Python package for estimating outcomes of perturbations in biomolecular networks. Bioinformatics, 40(9), btae527.
18.Nguyen, M., Long, S. W., McDermott, P. F., Olsen, R. J., Olson, R., Stevens, R. L., ... & Davis, J. J. (2018). Using machine learning to predict antimicrobial minimum inhibitory concentrations and associated genomic features for nontyphoidal Salmonella. BioRxiv, 380782.
19.Penven, M., Zouari, A., Nogues, S., Collet, A., Lecourt, M., Birer, A., ... & Cattoir, V. (2023). Web-based prediction of antimicrobial resistance in enterococcal clinical isolates by whole-genome sequencing. European Journal of Clinical Microbiology & Infectious Diseases, 42(1), 67-76.
20.Ren, Y., Chakraborty, T., Doijad, S., Falgenhauer, L., Falgenhauer, J., Goesmann, A., ... & Heider, D. (2022). Prediction of antimicrobial resistance based on whole-genome sequencing and machine learning. Bioinformatics, 38(2), 325-334.
21.Sakagianni, A., Koufopoulou, C., Feretzakis, G., Kalles, D., Verykios, V. S., & Myrianthefs, P. (2023). Using machine learning to predict antimicrobial resistance―a literature review. Antibiotics, 12(3), 452.
22.Salman Ibne Eunus. (2025). antibiotic_resistance-geissen-dataset: Predicting antibiotic resistance genes [Data set]. Kaggle. https://www.kaggle.com/datasets/salmaneunus/antibiotic-resistance-geissen-dataset
23.Van Camp, P. J., Haslam, D. B., & Porollo, A. (2020). Prediction of antimicrobial resistance in Gram-negative bacteria from whole-genome sequencing data. Frontiers in microbiology, 11, 1013.
24.Vanalli, C., Mari, L., Righetto, L., Casagrandi, R., Gatto, M., & Cattadori, I. M. (2020). Within-host mechanisms of immune regulation explain the contrasting dynamics of two helminth species in both single and dual infections. PLoS computational biology, 16(11), e1008438.
25.Waddington, C., Carey, M. E., Boinett, C. J., Higginson, E., Veeraraghavan, B., & Baker, S. (2022). Exploiting genomics to mitigate the public health impact of antimicrobial resistance. Genome medicine, 14(1), 15.
Copyright (c) 2026 IJRDO - JOURNAL OF BIOLOGICAL SCIENCE
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Author(s) and co-author(s) jointly and severally represent and warrant that the Article is original with the author(s) and does not infringe any copyright or violate any other right of any third parties, and that the Article has not been published elsewhere. Author(s) agree to the terms that the IJRDO Journal will have the full right to remove the published article on any misconduct found in the published article.
