Drug resistance prediction and resistance genes identification in Mycobacterium tuberculosis based on a hierarchical attentive neural network utilizing genome-wide variants

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.

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.

Regulation of ferroptosis-related genes in CD8+ NKT cells and classical monocytes may affect the immunotherapy response after combined treatment in triple negative breast cancer

BACKGROUND

Drug resistance has led to the failure of immunotherapy in triple negative breast cancer patients. Here we aimed to explore the mechanisms of drug resistance in patients in order to enhance their response to immunotherapy.

METHODS

We downloaded publicly available single-cell RNA-sequencing data of peripheral blood mononuclear cells from patients after treatment to investigate the possible mechanisms of drug resistance. The publicly available TCGA transcriptomic data and somatic mutation data were used for further validation. In this study, a series of bioinformatics and machine learning methods were employed.

RESULTS

We identified the vital roles of CD8+ NKT cells and classical monocytes in the immunotherapy response of triple-negative breast cancer patients. The proportion of these cell types was significantly increased in group partial response. We also found that downregulation of ferroptosis-related genes regulates the immune pathway. The analysis of scRNA data and TCGA transcriptomic data presented that DUSP1 may play a crucial role in immunotherapy resistance.

CONCLUSION

Overall, the composition of the tumor microenvironment affects the immunotherapy response of patients, and DUSP1 may be a potential target for overcoming drug resistance.

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.

PatA Regulates Isoniazid Resistance by Mediating Mycolic Acid Synthesis and Controls Biofilm Formation by Affecting Lipid Synthesis in Mycobacteria

Lipids are prominent components of the mycobacterial cell wall, and they play critical roles not only in maintaining biofilm formation but also in resisting environmental stress, including drug resistance. However, information regarding the mechanism mediating mycobacterial lipid synthesis remains limited. PatA is a membrane-associated acyltransferase and synthesizes phosphatidyl-myo-inositol mannosides (PIMs) in mycobacteria. Here, we found that PatA could regulate the synthesis of lipids (except mycolic acids) to maintain biofilm formation and environmental stress resistance in Mycolicibacterium smegmatis. Interestingly, the deletion of patA significantly enhanced isoniazid (INH) resistance in M. smegmatis, although it reduced bacterial biofilm formation. This might be due to the fact that the patA deletion promoted the synthesis of mycolic acids through an unknown synthesis pathway other than the reported fatty acid synthase (FAS) pathway, which could effectively counteract the inhibition by INH of mycolic acid synthesis in mycobacteria. Furthermore, the amino acid sequences and physiological functions of PatA were highly conserved in mycobacteria. Therefore, we found a mycolic acid synthesis pathway regulated by PatA in mycobacteria. In addition, PatA also affected biofilm formation and environmental stress resistance by regulating the synthesis of lipids (except mycolic acids) in mycobacteria. IMPORTANCE Tuberculosis, caused by Mycobacterium tuberculosis, leads to a large number of human deaths every year. This is so serious, which is due mainly to the drug resistance of mycobacteria. INH kills M. tuberculosis by inhibiting the synthesis of mycolic acids, which are synthesized by the FAS pathway. However, whether there is another mycolic acid synthesis pathway is unknown. In this study, we found a PatA-mediated mycolic acid synthesis pathway that led to INH resistance of in patA-deleted mutant. In addition, we first report the regulatory effect of PatA on mycobacterial biofilm formation, which could affect the bacterial response to environmental stress. Our findings represent a new model for regulating biofilm formation by mycobacteria. More importantly, the discovery of the PatA-mediated mycolic acid synthesis pathway indicates that the study of mycobacterial lipids has entered a new stage, and the enzymes might be new targets of antituberculosis drugs.

The Application of Artificial Intelligence in the Diagnosis and Drug Resistance Prediction of Pulmonary Tuberculosis

With the increasing incidence and mortality of pulmonary tuberculosis, in addition to tough and controversial disease management, time-wasting and resource-limited conventional approaches to the diagnosis and differential diagnosis of tuberculosis are still awkward issues, especially in countries with high tuberculosis burden and backwardness. In the meantime, the climbing proportion of drug-resistant tuberculosis poses a significant hazard to public health. Thus, auxiliary diagnostic tools with higher efficiency and accuracy are urgently required. Artificial intelligence (AI), which is not new but has recently grown in popularity, provides researchers with opportunities and technical underpinnings to develop novel, precise, rapid, and automated implements for pulmonary tuberculosis care, including but not limited to tuberculosis detection. In this review, we aimed to introduce representative AI methods, focusing on deep learning and radiomics, followed by definite descriptions of the state-of-the-art AI models developed using medical images and genetic data to detect pulmonary tuberculosis, distinguish the infection from other pulmonary diseases, and identify drug resistance of tuberculosis, with the purpose of assisting physicians in deciding the appropriate therapeutic schedule in the early stage of the disease. We also enumerated the challenges in maximizing the impact of AI in this field such as generalization and clinical utility of the deep learning models.