دورية أكاديمية
First-line drug resistance profiling of Mycobacterium tuberculosis : a machine learning approach.
| العنوان: | First-line drug resistance profiling of Mycobacterium tuberculosis : a machine learning approach. |
|---|---|
| المؤلفون: | Müller SJ; IBM Research Africa, Johannesburg, South Africa., Meraba RL; IBM Research Africa, Johannesburg, South Africa., Dlamini GS; IBM Research Africa, Johannesburg, South Africa., Mapiye DS; IBM Research Africa, Johannesburg, South Africa. |
| المصدر: | AMIA ... Annual Symposium proceedings. AMIA Symposium [AMIA Annu Symp Proc] 2022 Feb 21; Vol. 2021, pp. 891-899. Date of Electronic Publication: 2022 Feb 21 (Print Publication: 2021). |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: American Medical Informatics Association Country of Publication: United States NLM ID: 101209213 Publication Model: eCollection Cited Medium: Internet ISSN: 1942-597X (Electronic) Linking ISSN: 15594076 NLM ISO Abbreviation: AMIA Annu Symp Proc Subsets: MEDLINE |
| أسماء مطبوعة: | Original Publication: Bethesda, MD : American Medical Informatics Association, c2003- |
| مواضيع طبية MeSH: | Antitubercular Agents*/pharmacology , Antitubercular Agents*/therapeutic use , Drug Resistance, Multiple, Bacterial*/genetics , Machine Learning* , Mycobacterium tuberculosis*/drug effects , Mycobacterium tuberculosis*/genetics , Tuberculosis*/drug therapy, Humans |
| مستخلص: | The persistence and emergence of new multi-drug resistant Mycobacterium tuberculosis (M. tb) strains continues to advance the devastating tuberculosis (TB) epidemic. Robust systems are needed to accurately and rapidly perform drug-resistance profiling, and machine learning (ML) methods combined with genomic sequence data may provide novel insights into drug-resistance mechanisms. Using 372 M. tb isolates, the combined utility of ML and bioinformatics to perform drug-resistance profiling is demonstrated. SNPs, InDels, and dinucleotide frequencies are explored as input features for three ML models, namely Decision Trees, Random Forest, and the eXtreme Gradient Boosted model. Using SNPs and InDels, all three models performed equally well yielding a 99% accuracy, 97% recall, and 99% F1-score. Using dinucleotide frequencies, the XGBoost algorithm was superior with a 97% accuracy, 94% recall and 97% F1-score. This study validates the use of variants and presents dinucleotide features as another effective feature encoding method for ML-based phenotype classification. (©2021 AMIA - All rights reserved.) |
| References: | Bioinformatics. 2009 Jul 15;25(14):1754-60. (PMID: 19451168) Bioinformatics. 2019 Jul 1;35(13):2276-2282. (PMID: 30462147) Int J Clin Exp Pathol. 2018 Aug 01;11(8):3903-3914. (PMID: 31949778) Bioinformatics. 2018 May 15;34(10):1666-1671. (PMID: 29240876) J Clin Microbiol. 2012 Dec;50(12):3831-7. (PMID: 22972833) Tuberculosis (Edinb). 2011 Jan;91(1):8-13. (PMID: 20980200) Int J Tuberc Lung Dis. 2009 Feb;13(2):260-5. (PMID: 19146757) IEEE Access. 2020 Oct 15;8:195263-195273. (PMID: 34976561) Nucleic Acids Res. 2020 Jan 8;48(D1):D606-D612. (PMID: 31667520) J Med Syst. 2002 Oct;26(5):445-63. (PMID: 12182209) Bioinformatics. 2011 Nov 1;27(21):2987-93. (PMID: 21903627) Fly (Austin). 2012 Apr-Jun;6(2):80-92. (PMID: 22728672) J Mol Biol. 1990 Oct 5;215(3):403-10. (PMID: 2231712) Int J Tuberc Lung Dis. 2015 Aug;19(8):954-959. (PMID: 26162362) Front Genet. 2012 Mar 15;3:35. (PMID: 22435069) Genome Biol Evol. 2020 Feb 1;12(2):3890-3905. (PMID: 31971587) Lancet Infect Dis. 2015 Oct;15(10):1193-1202. (PMID: 26116186) J Glob Antimicrob Resist. 2020 Mar;20:11-15. (PMID: 31121336) Antimicrob Agents Chemother. 2018 Sep 24;62(10):. (PMID: 30082293) BMC Genomics. 2018 May 16;19(1):365. (PMID: 29769016) J Comput Biol. 2012 May;19(5):455-77. (PMID: 22506599) Clin Exp Immunol. 2003 Jul;133(1):30-7. (PMID: 12823275) Eur Respir J. 2013 Jul;42(1):252-71. (PMID: 23180585) |
| المشرفين على المادة: | 0 (Antitubercular Agents) |
| تواريخ الأحداث: | Date Created: 20220321 Date Completed: 20220411 Latest Revision: 20220531 |
| رمز التحديث: | 20221213 |
| مُعرف محوري في PubMed: | PMC8861754 |
| PMID: | 35309001 |
| قاعدة البيانات: | MEDLINE |
| تدمد: | 1942-597X |
|---|