Predicting rifampicin resistance mutations in bacterial RNA polymerase subunit beta based on majority consensus

Abstract

Background Mutations in an enzyme target are one of the most common mechanisms whereby antibiotic resistance arises. Identification of the resistance mutations in bacteria is essential for understanding the structural basis of antibiotic resistance and design of new drugs. However, the traditionally used experimental approaches to identify resistance mutations were usually labor-intensive and costly. Results We present a machine learning (ML)-based classifier for predicting rifampicin (Rif) resistance mutations in bacterial RNA Polymerase subunit β (RpoB). A total of 186 mutations were gathered from the literature for developing the classifier, using 80% of the data as the training set and the rest as the test set. The features of the mutated RpoB and their binding energies with Rif were calculated through computational methods, and used as the mutation attributes for modeling. Classifiers based on five ML algorithms, i.e. decision tree, k nearest neighbors, naïve Bayes, probabilistic neural network and support vector machine, were first built, and a majority consensus (MC) approach was then used to obtain a new classifier based on the classifications of the five individual ML algorithms. The MC classifier comprehensively improved the predictive performance, with accuracy, F-measure and AUC of 0.78, 0.83 and 0.81for training set whilst 0.84, 0.87 and 0.83 for test set, respectively. Conclusion The MC classifier provides an alternative methodology for rapid identification of resistance mutations in bacteria, which may help with early detection of antibiotic resistance and new drug discovery.

rpoB Mutations and Effects on Rifampin Resistance in Mycobacterium tuberculosis

“…RIF resistance is usually caused by mutations within RIF resistance-determining regions (RRDRs) of RpoB that are involved in the formation of the RIF-binding pocket. 35,36 Accordingly, all 11 mutated sites contributing to RIF-resistance in our study, including V170, Q429, L430, S431, Q432, D435, S441, H445, S450, L452 and I491, are located in the RRDRs of RpoB, 35 while four residues outside RRDRs, namely P45, T400, G759 and Q1056, are not involved in RIF binding. Though in this study, mutations P45S, T400I, G759S and Q1056K occurred in isolates belonging to high-level RIF resistant group, these mutations were accompanied by additional mutations associated with high-level RIF resistance, S450L or H445Y.…”

“…These contradictory results probably owe to using the different crystal structure models and different algorithms. 35,36 Only by combining the results of structural prediction with phenotypic data could we determine whether a mutation contributes to drug resistance. However, in this study, these five mutations occurred in RIF-resistant isolates, and these mutations were accompanied by an additional RIF resistance-associated mutation.…”

Reduction of the resistome risk from cow slurry and manure microbiomes to soil and vegetable microbiomes

“…Remarkably, although farmers did not report the use of rifamycin to treat common diseases, in fresh slurry, stored slurry, faeces and all the studied soils, ansamycin was the main resistance profile in terms of total annotated ARGs. As an example of the different mechanisms associated to ansamycin resistance, mutations in rpoB prevent rifamycin from binding to rpoB and then the bactericidal activity of rifamycin is lost [rifamycin is an ansamycin subclass antibiotic that binds to the β‐subunit of RNA polymerase (RNAP), rpoB , and blocks RNA synthesis) (Ning et al ., 2021). Module IV in our first network analysis was composed of only two ARGs, rpoB and rpoB2 .…”

Tackling the Antimicrobial Resistance “Pandemic” with Machine Learning Tools: A Summary of Available Evidence

“…In drug resistance profiling of tuberculosis, some models have achieved 99% accuracy [112]. Machine learning classifiers were used to predict resistance mutations related to rifampicin as an alternative rapid method [113].…”