Prediction of Acquired Antimicrobial Resistance for Multiple Bacterial Species Using Neural Networks

Overview

Journal mSystems

Publisher American Society for Microbiology

Specialty Microbiology

Date 2020 Jan 23

PMID 31964771

Citations 26

Authors

D Aytan-Aktug

P T L C Clausen

V Bortolaia

F M Aarestrup

O Lund

Affiliations

Soon will be listed here.

Abstract

Machine learning has proven to be a powerful method to predict antimicrobial resistance (AMR) without using prior knowledge for selected bacterial species-antimicrobial combinations. To date, only species-specific machine learning models have been developed, and to the best of our knowledge, the inclusion of information from multiple species has not been attempted. The aim of this study was to determine the feasibility of including information from multiple bacterial species to predict AMR for an individual species, since this may make it easier to train and update resistance predictions for multiple species and may lead to improved predictions. Whole-genome sequence data and susceptibility profiles from 3,528 , 1,694 , 658 , and 1,236 isolates were included. We developed machine learning models trained by the features of the PointFinder and ResFinder programs detected to predict binary (susceptible/resistant) AMR profiles. We tested four feature representation methods to determine the most efficient way for introducing features into the models. When training the model only on the isolates, high prediction performances were obtained for the six AMR profiles included. By adding information on ciprofloxacin from the additional 3,588 isolates, there was no reduction in performance for the other antimicrobials but an increased performance for ciprofloxacin AMR profile prediction for and In conclusion, the species-independent models can predict multi-AMR profiles for multiple species without losing any robustness. Machine learning is a proven method to predict AMR; however, the performance of any machine learning model depends on the quality of the input data. Therefore, we evaluated different methods of representing information about mutations as well as mobilizable genes, so that the information can serve as input for a robust model. We combined data from multiple bacterial species in order to develop species-independent machine learning models that can predict resistance profiles for multiple antimicrobials and species with high performance.

Citing Articles

The role of artificial intelligence and machine learning in predicting and combating antimicrobial resistance.

Bilal H, Khan M, Khan S, Shafiq M, Fang W, Khan R Comput Struct Biotechnol J. 2025; 27:423-439.

PMID: 39906157 PMC: 11791014. DOI: 10.1016/j.csbj.2025.01.006.

A comparison of various feature extraction and machine learning methods for antimicrobial resistance prediction in .

Kaya D, Ulgen E, Kocagoz A, Sezerman O Front Antibiot. 2025; 2():1126468.

PMID: 39816648 PMC: 11731958. DOI: 10.3389/frabi.2023.1126468.

Integrative genomics would strengthen AMR understanding through ONE health approach.

Liu C, Pandey R Heliyon. 2025; 10(14):e34719.

PMID: 39816336 PMC: 11734142. DOI: 10.1016/j.heliyon.2024.e34719.

Artificial intelligence in predicting pathogenic microorganisms' antimicrobial resistance: challenges, progress, and prospects.

Li Y, Cui X, Yang X, Liu G, Zhang J Front Cell Infect Microbiol. 2024; 14:1482186.

PMID: 39554812 PMC: 11564165. DOI: 10.3389/fcimb.2024.1482186.

Neural network-based predictions of antimicrobial resistance phenotypes in multidrug-resistant from whole genome sequencing and gene expression.

Jia H, Li X, Zhuang Y, Wu Y, Shi S, Sun Q Antimicrob Agents Chemother. 2024; 68(12):e0144624.

PMID: 39540735 PMC: 11619347. DOI: 10.1128/aac.01446-24.

References

Henikoff S, Henikoff J . Amino acid substitution matrices from protein blocks. Proc Natl Acad Sci U S A. 1992; 89(22):10915-9. PMC: 50453. DOI: 10.1073/pnas.89.22.10915. View

Hasman H, Saputra D, Sicheritz-Ponten T, Lund O, Svendsen C, Frimodt-Moller N . Rapid whole-genome sequencing for detection and characterization of microorganisms directly from clinical samples. J Clin Microbiol. 2013; 52(1):139-46. PMC: 3911411. DOI: 10.1128/JCM.02452-13. View

Dobrindt U, Hacker J . Whole genome plasticity in pathogenic bacteria. Curr Opin Microbiol. 2001; 4(5):550-7. DOI: 10.1016/s1369-5274(00)00250-2. View

McCULLOCH W, PITTS W . A logical calculus of the ideas immanent in nervous activity. 1943. Bull Math Biol. 1990; 52(1-2):99-115; discussion 73-97. View

Zankari E, Allesoe R, Joensen K, Cavaco L, Lund O, Aarestrup F . PointFinder: a novel web tool for WGS-based detection of antimicrobial resistance associated with chromosomal point mutations in bacterial pathogens. J Antimicrob Chemother. 2017; 72(10):2764-2768. PMC: 5890747. DOI: 10.1093/jac/dkx217. View

Ezewudo M, Borens A, Chiner-Oms A, Miotto P, Chindelevitch L, Starks A . Integrating standardized whole genome sequence analysis with a global Mycobacterium tuberculosis antibiotic resistance knowledgebase. Sci Rep. 2018; 8(1):15382. PMC: 6194142. DOI: 10.1038/s41598-018-33731-1. View

Zou Y, Xue W, Luo G, Deng Z, Qin P, Guo R . 1,520 reference genomes from cultivated human gut bacteria enable functional microbiome analyses. Nat Biotechnol. 2019; 37(2):179-185. PMC: 6784896. DOI: 10.1038/s41587-018-0008-8. View

Davis J, Boisvert S, Brettin T, Kenyon R, Mao C, Olson R . Antimicrobial Resistance Prediction in PATRIC and RAST. Sci Rep. 2016; 6:27930. PMC: 4906388. DOI: 10.1038/srep27930. View

Nguyen M, Brettin T, Long S, Musser J, Olsen R, Olson R . Developing an in silico minimum inhibitory concentration panel test for Klebsiella pneumoniae. Sci Rep. 2018; 8(1):421. PMC: 5765115. DOI: 10.1038/s41598-017-18972-w. View

10.

Clausen P, Aarestrup F, Lund O . Rapid and precise alignment of raw reads against redundant databases with KMA. BMC Bioinformatics. 2018; 19(1):307. PMC: 6116485. DOI: 10.1186/s12859-018-2336-6. View

11.

Llor C, Bjerrum L . Antimicrobial resistance: risk associated with antibiotic overuse and initiatives to reduce the problem. Ther Adv Drug Saf. 2014; 5(6):229-41. PMC: 4232501. DOI: 10.1177/2042098614554919. View

12.

Bradley P, Gordon N, Walker T, Dunn L, Heys S, Huang B . Rapid antibiotic-resistance predictions from genome sequence data for Staphylococcus aureus and Mycobacterium tuberculosis. Nat Commun. 2015; 6:10063. PMC: 4703848. DOI: 10.1038/ncomms10063. View

13.

Chen M, Doddi A, Royer J, Freschi L, Schito M, Ezewudo M . Beyond multidrug resistance: Leveraging rare variants with machine and statistical learning models in Mycobacterium tuberculosis resistance prediction. EBioMedicine. 2019; 43:356-369. PMC: 6557804. DOI: 10.1016/j.ebiom.2019.04.016. View

14.

Bagel S, Hullen V, Wiedemann B, Heisig P . Impact of gyrA and parC mutations on quinolone resistance, doubling time, and supercoiling degree of Escherichia coli. Antimicrob Agents Chemother. 1999; 43(4):868-75. PMC: 89219. DOI: 10.1128/AAC.43.4.868. View

15.

Wattam A, Abraham D, Dalay O, Disz T, Driscoll T, Gabbard J . PATRIC, the bacterial bioinformatics database and analysis resource. Nucleic Acids Res. 2013; 42(Database issue):D581-91. PMC: 3965095. DOI: 10.1093/nar/gkt1099. View

16.

Ahmad S, Mokaddas E, Al-Mutairi N, Eldeen H, Mohammadi S . Discordance across Phenotypic and Molecular Methods for Drug Susceptibility Testing of Drug-Resistant Mycobacterium tuberculosis Isolates in a Low TB Incidence Country. PLoS One. 2016; 11(4):e0153563. PMC: 4838278. DOI: 10.1371/journal.pone.0153563. View

17.

Matthews B . Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochim Biophys Acta. 1975; 405(2):442-51. DOI: 10.1016/0005-2795(75)90109-9. View

18.

Ellington M, Ekelund O, Aarestrup F, Canton R, Doumith M, Giske C . The role of whole genome sequencing in antimicrobial susceptibility testing of bacteria: report from the EUCAST Subcommittee. Clin Microbiol Infect. 2016; 23(1):2-22. DOI: 10.1016/j.cmi.2016.11.012. View

19.

Stoesser N, Batty E, Eyre D, Morgan M, Wyllie D, Del Ojo Elias C . Predicting antimicrobial susceptibilities for Escherichia coli and Klebsiella pneumoniae isolates using whole genomic sequence data. J Antimicrob Chemother. 2013; 68(10):2234-44. PMC: 3772739. DOI: 10.1093/jac/dkt180. View

20.

Zankari E, Hasman H, Cosentino S, Vestergaard M, Rasmussen S, Lund O . Identification of acquired antimicrobial resistance genes. J Antimicrob Chemother. 2012; 67(11):2640-4. PMC: 3468078. DOI: 10.1093/jac/dks261. View