ABSTRACT
Correct and timely detection of Mycobacterium tuberculosis (MTB) resistance against existing tuberculosis (TB) drugs is essential for the limit of TB amplification. The objectives of the projects are (1) to develop classification models that help isoniazid-resistant TB diagnosis, (2) to find the best performed classification algorithm, and (3) to rank the gene mutations according to feature importance. The python sklearn and matplotlib packages were frequently utilized throughout the research for data curation, classification model development, and feature importance ranking. Additionally, area under the curve (AUC), precision, sensitivity, specificity, F1 score, and correct classification rate measured for model performances, and Gini importance calculated feature importance. Gradient boosting found to overperform other classification models with the highest accuracy mean 0f 0.852, and its overfitting error exposed the need for dimensionality reduction prior to model training. Gene 625 and 331 were the most significant features in this project, and this suggested the potential of machine learning (ML) to find new resistance makers. The results confirmed the application of ML in clinical settings for quicker and better prediction of drug resistance based on large genome sequencing data. With future studies focusing on less studied and second-line TB drugs, classification models could decrease mortality and prevent the amplification of existing antibiotic resistance by allowing early diagnosis and treatment.
CCS CONCEPTS • Computing methodologies∼Machine learning∼Learning paradigms∼Supervised learning∼Supervised learning by classification
- World Health Organization, “Global Tuberculosis Report 2020”, Oct. 2021Google Scholar
- Centers for Disease Control and Prevention CDC, “Drug-Resistant TB,” Jan. 2017, https://www.cdc.gov/tb/topic/drtb/default.htmGoogle Scholar
- Y. L. Xie , “Evaluation of a Rapid Molecular Drug-Susceptibility Test for Tuberculosis,” New England Journal of Medicine, vol. 377, no. 11, pp. 1043–1054, Sep. 2017, doi:10.1056/nejmoa1614915.Google ScholarCross Ref
- A. Sharma, E. Machado, K. V. B. Lima, P. N. Suffys, and E. C. Conceic, “Tuberculosis drug resistance profiling based on machine learning: A literature review”, The Brazilian Journal of Infectious Diseases, v. 26, n. 1, Jan. 2022, 102332 doi: 10.1016/j.bjid.2022.102332Google ScholarCross Ref
- D. V. Volokhov, V. E. Chizhikov, S. Denkin, and Y. Zhang, “Molecular detection of drug-resistant Mycobacterium tuberculosis with a scanning-frame oligonucleotide microarray,” Methods in Molecular Biology (Clifton, N.J.), vol. 465, pp. 395–417, June 2010, doi: 10.1007/978-1-59745-207-6_26.Google ScholarCross Ref
- W. Deelder, , “Machine Learning Predicts Accurately Mycobacterium tuberculosis Drug Resistance From Whole Genome Sequencing Data,” frontiers in Genetic, Sep.2019, https://doi.org/10.3389/fgene.2019.00922Google ScholarCross Ref
- Y. Yang, , “Machine learning for classifying tuberculosis drug-resistance from DNA sequencing data”, Bioinformatics, v. 34, n. 10, pp. 1666–1671, May 2018, doi: 10.1093/bioinformatics/btx801Google ScholarCross Ref
- M. L. Chen , “Deep learning predicts tuberculosis drug resistance status from genome sequencing data,” Mar. 2018, doi: 10.1101/275628. *Google ScholarCross Ref
- M. R. Farhat , “Genetic Determinants of Drug Resistance inMycobacterium tuberculosis and Their Diagnostic Value,” American Journal of Respiratory and Critical Care Medicine, vol. 194, no. 5, pp. 621–630, Sep. 2016, doi: 10.1164/rccm.201510-2091oc.Google ScholarCross Ref
- S.Kouchaki, , “Application of machine learning techniques to tuberculosis drug resistance analysis, ” Oxford, Nov. 2018, pp. 2276-2282, doi: 10.1093/bioinformatics/bty949Google Scholar
- S. Kouchaki , “Multi-Label Random Forest Model for Tuberculosis Drug Resistance Classification and Mutation Ranking,” Frontiers in Microbiology, vol. 11, Apr. 2020, doi: 10.3389/fmicb.2020.00667.Google Scholar
Recommendations
An Evolutionary Conservation & Rigidity Analysis Machine Learning Approach for Detecting Critical Protein Residues
BCB'13: Proceedings of the International Conference on Bioinformatics, Computational Biology and Biomedical InformaticsIn proteins, certain amino acids may play a critical role in determining their structure and function. Examples include flexible regions which allow domain motions, and highly conserved residues on functional interfaces which play a role in binding and ...
Efficient Machine Learning-Based Prediction of CYP450 Inhibition
Database and Expert Systems ApplicationsAbstractCytochrome P450 (CYP450) enzymes are crucial in drug metabolism and development. They are mainly involved in drug efficacy and toxicity, which are significant concerns while exploring potential pharmaceutical compounds. Machine learning-based ...
Machine-learning repurposing of DrugBank compounds for opioid use disorder
AbstractOpioid use disorder (OUD) is a chronic and relapsing condition that involves the continued and compulsive use of opioids despite harmful consequences. The development of medications with improved efficacy and safety profiles for OUD treatment is ...
Highlights- Drug repurposing is a promising option for finding medications to treat opioid use disorder.
- Advanced machine learning models were used to virtually screen the DrugBank database for possible drug candidates.
- Natural language ...
Comments