A modified decision tree approach to improve the prediction and mutation discovery for drug resistance in Mycobacterium tuberculosis

Exploring diagnostic methods for drug-resistant tuberculosis: A comprehensive overview

Despite available global efforts and funding, Tuberculosis (TB) continues to affect a considerable number of patients worldwide. Policy makers and stakeholders set clear goals to reduce TB incidence and mortality, but the emergence of multidrug-resistant TB (MDR-TB) and extensively drug-resistant TB (XDR-TB) complicate the reach of these goals. Drug-resistance TB needs to be diagnosed rapidly and accurately to effectively treat patients, prevent the transmission of MDR-TB, minimise mortality, reduce treatment costs and avoid unnecessary hospitalisations. In this narrative review, we provide a comprehensive overview of laboratory methods for detecting drug resistance in MTB, focusing on phenotypic, molecular and other drug susceptibility testing (DST) techniques. We found a large variety of methods used, with the BACTEC MGIT 960 being the most common phenotypic DST and the Xpert MTB/RIF being the most common molecular DST. We emphasise the importance of integrating phenotypic and molecular DST to address issues like resistance to new drugs, heteroresistance, mixed infections and low-level resistance mutations. Notably, most of the analysed studies adhered to the outdated definition of XDR-TB and did not consider the pre-XDR definition, thus posing challenges in aligning diagnostic methods with the current landscape of TB resistance.

Whole-Genome Sequencing Predicting Phenotypic Antitubercular Drug Resistance: Meta-analysis

BACKGROUND

For simultaneous prediction of phenotypic drug susceptibility test (pDST) for multiple antituberculosis drugs, the whole genome sequencing (WGS) data can be analyzed using either a catalog-based approach, wherein 1 causative mutation suggests resistance, (eg, World Health Organization catalog) or noncatalog-based approach using complicated algorithm (eg, TB-profiler, machine learning). The aim was to estimate the predictive ability of WGS-based tests with pDST as the reference, and to compare the 2 approaches.

METHODS

Following a systematic literature search, the diagnostic test accuracies for 14 drugs were pooled using a random-effect bivariate model.

RESULTS

Of 779 articles, 44 with 16 821 specimens for meta-analysis and 13 not for meta-analysis were included. The areas under summary receiver operating characteristic curve suggested test accuracy was excellent (0.97-1.00) for 2 drugs (isoniazid 0.975, rifampicin 0.975), very good (0.93-0.97) for 8 drugs (pyrazinamide 0.946, streptomycin 0.952, amikacin 0.968, kanamycin 0.963, capreomycin 0.965, para-aminosalicylic acid 0.959, levofloxacin 0.960, ofloxacin 0.958), and good (0.75-0.93) for 4 drugs (ethambutol 0.926, moxifloxacin 0.896, ethionamide 0.878, prothionamide 0.908). The noncatalog-based and catalog-based approaches had similar ability for all drugs.

CONCLUSIONS

WGS accurately identifies isoniazid and rifampicin resistance. For most drugs, positive WGS results reliably predict pDST positive. The 2 approaches had similar ability.

CLINICAL TRIALS REGISTRATION

UMIN-ID UMIN000049276.

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

Antimicrobial resistance is recognised as one of the top threats healthcare is bound to face in the future. There have been various attempts to preserve the efficacy of existing antimicrobials, develop new and efficient antimicrobials, manage infections with multi-drug resistant strains, and improve patient outcomes, resulting in a growing mass of routinely available data, including electronic health records and microbiological information that can be employed to develop individualised antimicrobial stewardship. Machine learning methods have been developed to predict antimicrobial resistance from whole-genome sequencing data, forecast medication susceptibility, recognise epidemic patterns for surveillance purposes, or propose new antibacterial treatments and accelerate scientific discovery. Unfortunately, there is an evident gap between the number of machine learning applications in science and the effective implementation of these systems. This narrative review highlights some of the outstanding opportunities that machine learning offers when applied in research related to antimicrobial resistance. In the future, machine learning tools may prove to be superbugs' kryptonite. This review aims to provide an overview of available publications to aid researchers that are looking to expand their work with new approaches and to acquaint them with the current application of machine learning techniques in this field.

TB-DROP: deep learning-based drug resistance prediction of Mycobacterium tuberculosis utilizing whole genome mutations

The most widely practiced strategy for constructing the deep learning (DL) prediction model for drug resistance of Mycobacterium tuberculosis (MTB) involves the adoption of ready-made and state-of-the-art architectures usually proposed for non-biological problems. However, the ultimate goal is to construct a customized model for predicting the drug resistance of MTB and eventually for the biological phenotypes based on genotypes. Here, we constructed a DL training framework to standardize and modularize each step during the training process using the latest tensorflow 2 API. A systematic and comprehensive evaluation of each module in the three currently representative models, including Convolutional Neural Network, Denoising Autoencoder, and Wide & Deep, which were adopted by CNNGWP, DeepAMR, and WDNN, respectively, was performed in this framework regarding module contributions in order to assemble a novel model with proper dedicated modules. Based on the whole-genome level mutations, a de novo learning method was developed to overcome the intrinsic limitations of previous models that rely on known drug resistance-associated loci. A customized DL model with the multilayer perceptron architecture was constructed and achieved a competitive performance (the mean sensitivity and specificity were 0.90 and 0.87, respectively) compared to previous ones. The new model developed was applied in an end-to-end user-friendly graphical tool named TB-DROP (TuBerculosis Drug Resistance Optimal Prediction: https://github.com/nottwy/TB-DROP ), in which users only provide sequencing data and TB-DROP will complete analysis within several minutes for one sample. Our study contributes to both a new strategy of model construction and clinical application of deep learning-based drug-resistance prediction methods.

Machine learning and phylogenetic analysis allow for predicting antibiotic resistance in M. tuberculosis

BACKGROUND

Antimicrobial resistance (AMR) poses a significant global health threat, and an accurate prediction of bacterial resistance patterns is critical for effective treatment and control strategies. In recent years, machine learning (ML) approaches have emerged as powerful tools for analyzing large-scale bacterial AMR data. However, ML methods often ignore evolutionary relationships among bacterial strains, which can greatly impact performance of the ML methods, especially if resistance-associated features are attempted to be detected. Genome-wide association studies (GWAS) methods like linear mixed models accounts for the evolutionary relationships in bacteria, but they uncover only highly significant variants which have already been reported in literature.

RESULTS

In this work, we introduce a novel phylogeny-related parallelism score (PRPS), which measures whether a certain feature is correlated with the population structure of a set of samples. We demonstrate that PRPS can be used, in combination with SVM- and random forest-based models, to reduce the number of features in the analysis, while simultaneously increasing models' performance. We applied our pipeline to publicly available AMR data from PATRIC database for Mycobacterium tuberculosis against six common antibiotics.

CONCLUSIONS

Using our pipeline, we re-discovered known resistance-associated mutations as well as new candidate mutations which can be related to resistance and not previously reported in the literature. We demonstrated that taking into account phylogenetic relationships not only improves the model performance, but also yields more biologically relevant predicted most contributing resistance markers.

Association between mutations in a thyX-hsdS.1 region and para-aminosalicylic acid resistance in Mycobacterium tuberculosis clinical isolates

Although para-aminosalicylic acid (PAS) has been used to treat tuberculosis agent for decades, its mechanisms of resistance are still not thoroughly understood. Previously, sporadic studies showed that certain mutations in the thyX-hsdS.1 region caused PAS resistance in M. tuberculosis, but a comprehensive analysis is lacking. Recently, we found a G-10A mutation in thyX-hsdS.1 in a PAS-resistant clinical isolate, but it did not cause PAS resistance. SNPs in thyX-hsdS.1 in 6550 clinical isolates were analyzed, and 153 SNPs were identified. C-16 T was the most common SNP identified (54.25%, 83/153), followed by C-4T (7.19%, 11/153) and G-9A (6.54%, 10/153). Subsequently, the effects of those SNPs on the promoter activity of thyX were tested, and the results showed that mutations C-1T, G-3A, C-4T, C-4G, G-7A, G-9A, C-16T, G-18C, and C-19G led to increased promoter activity compared with the wild-type sequence, but other mutations did not. Then, thyX and wild-type thyX-hsdS.1, or thyX-hsdS.1 containing specific SNPs, were overexpressed in M. tuberculosis H37Ra. The results showed that mutations resulting in increased promoter activity also caused PAS resistance. Moreover, the results of an electrophoretic mobility shift assay showed that thyX-hsdS.1 containing the C-16T mutation had a higher binding capacity to RNA polymerase than did the wild-type sequence. Taken together, our data demonstrated that among the SNPs identified in thyX-hsdS.1 of M. tuberculosis clinical isolates, only those able to increase the promoter activity of thyX caused PAS resistance and therefore can be considered as molecular markers for PAS resistance.

EDST: a decision stump based ensemble algorithm for synergistic drug combination prediction

INTRODUCTION

There are countless possibilities for drug combinations, which makes it expensive and time-consuming to rely solely on clinical trials to determine the effects of each possible drug combination. In order to screen out the most effective drug combinations more quickly, scholars began to apply machine learning to drug combination prediction. However, most of them are of low interpretability. Consequently, even though they can sometimes produce high prediction accuracy, experts in the medical and biological fields can still not fully rely on their judgments because of the lack of knowledge about the decision-making process.

RELATED WORK

Decision trees and their ensemble algorithms are considered to be suitable methods for pharmaceutical applications due to their excellent performance and good interpretability. We review existing decision trees or decision tree ensemble algorithms in the medical field and point out their shortcomings.

METHOD

This study proposes a decision stump (DS)-based solution to extract interpretable knowledge from data sets. In this method, a set of DSs is first generated to selectively form a decision tree (DST). Different from the traditional decision tree, our algorithm not only enables a partial exchange of information between base classifiers by introducing a stump exchange method but also uses a modified Gini index to evaluate stump performance so that the generation of each node is evaluated by a global view to maintain high generalization ability. Furthermore, these trees are combined to construct an ensemble of DST (EDST).

EXPERIMENT

The two-drug combination data sets are collected from two cell lines with three classes (additive, antagonistic and synergistic effects) to test our method. Experimental results show that both our DST and EDST perform better than other methods. Besides, the rules generated by our methods are more compact and more accurate than other rule-based algorithms. Finally, we also analyze the extracted knowledge by the model in the field of bioinformatics.

CONCLUSION

The novel decision tree ensemble model can effectively predict the effect of drug combination datasets and easily obtain the decision-making process.

Machine Learning of the Whole Genome Sequence of Mycobacterium tuberculosis: A Scoping PRISMA-Based Review

Tuberculosis (TB) remains one of the most significant global health problems, posing a significant challenge to public health systems worldwide. However, diagnosing drug-resistant tuberculosis (DR-TB) has become increasingly challenging due to the rising number of multidrug-resistant (MDR-TB) cases, despite the development of new TB diagnostic tools. Even the World Health Organization-recommended methods such as Xpert MTB/XDR or Truenat are unable to detect all the Mycobacterium tuberculosis genome mutations associated with drug resistance. While Whole Genome Sequencing offers a more precise DR profile, the lack of user-friendly bioinformatics analysis applications hinders its widespread use. This review focuses on exploring various artificial intelligence models for predicting DR-TB profiles, analyzing relevant English-language articles using the PRISMA methodology through the Covidence platform. Our findings indicate that an Artificial Neural Network is the most commonly employed method, with non-statistical dimensionality reduction techniques preferred over traditional statistical approaches such as Principal Component Analysis or t-distributed Stochastic Neighbor Embedding.