EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Scalable de novo classification of antibiotic resistance of Mycobacterium tuberculosis

Mohammadali Serajian iD, Simone Marini iD, Jarno N Alanko iD, Noelle R Noyes iD, Mattia Prosperi iD, Christina Boucher iD

Bioinformatics · 28.06.2024 · 40 (Supplement_1) · i39-i47

DOI: 10.1093/bioinformatics/btae243 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 28.06.2024. Verfasst von Mohammadali Serajian und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer and Information Science and Engineering, University of Florida, 1889 Museum Road, Gainesville, Florida 32611, United States. Hauptthemen laut MEDLINE: Mycobacterium tuberculosis, Machine Learning. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIAID NIH HHS, NIH, NSF.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation World Health Organization estimates that there were over 10 million cases of tuberculosis (TB) worldwide in 2019, resulting in over 1.4 million deaths, with a worrisome increasing trend yearly. The disease is caused by Mycobacterium tuberculosis (MTB) through airborne transmission. Treatment of TB is estimated to be 85% successful, however, this drops to 57% if MTB exhibits multiple antimicrobial resistance (AMR), for which fewer treatment options are available. Results We develop a robust machine-learning classifier using both linear and nonlinear models (i.e. LASSO logistic regression (LR) and random forests (RF)) to predict the phenotypic resistance of Mycobacterium tuberculosis (MTB) for a broad range of antibiotic drugs. We use data from the CRyPTIC consortium to train our classifier, which consists of whole genome sequencing and antibiotic susceptibility testing (AST) phenotypic data for 13 different antibiotics. To train our model, we assemble the sequence data into genomic contigs, identify all unique 31-mers in the set of contigs, and build a feature matrix M, where M[i, j] is equal to the number of times the ith 31-mer occurs in the jth genome. Due to the size of this feature matrix (over 350 million unique 31-mers), we build and use a sparse matrix representation. Our method, which we refer to as MTB++, leverages compact data structures and iterative methods to allow for the screening of all the 31-mers in the development of both LASSO LR and RF. MTB++ is able to achieve high discrimination (F-1 >80%) for the first-line antibiotics. Moreover, MTB++ had the highest F-1 score in all but three classes and was the most comprehensive since it had an F-1 score >75% in all but four (rare) antibiotic drugs. We use our feature selection to contextualize the 31-mers that are used for the prediction of phenotypic resistance, leading to some insights about sequence similarity to genes in MEGARes. Lastly, we give an estimate of the amount of data that is needed in order to provide accurate predictions. Availability The models and source code are publicly available on Github at https://github.com/M-Serajian/MTB-Pipeline.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Mycobacterium tuberculosisMachine LearningDrug Resistance, BacterialMicrobial Sensitivity TestsAnti-Bacterial AgentsWhole Genome SequencingGenome, BacterialHumans

Substanzen

Anti-Bacterial Agents

Autor:innen und Institutionen

  • Department of Computer and Information Science and Engineering, University of Florida, 1889 Museum Road, Gainesville, Florida 32611, United States.
  • Department of Epidemiology, University of Florida, PO Box 100231, Gainesville, Florida 32601, United States.
  • Department of Computer Science, University of Helsinki, P.O. Box 4, Helsinki 00014, Finland.
  • Department of Veterinary Population Medicine, University of Minnesota, 1365 Gortner Avenue, St. Paul, Minnesota 55108, United States.

ORCID-Profile: Mohammadali Serajian, Simone Marini, Jarno N Alanko, Noelle R Noyes, Mattia Prosperi, Christina Boucher

Förderung

  • NIAID NIH HHS
  • NIH
  • NSF
  • NIAID

Zitieren

APA

Serajian, M., Marini, S., Alanko, J. N., Noyes, N. R., Prosperi, M., & Boucher, C. (2024). Scalable de novo classification of antibiotic resistance of Mycobacterium tuberculosis. Bioinformatics, 40(Supplement_1), i39-i47. https://doi.org/10.1093/bioinformatics/btae243

Vancouver

Serajian M, Marini S, Alanko JN, Noyes NR, Prosperi M, Boucher C. Scalable de novo classification of antibiotic resistance of Mycobacterium tuberculosis. Bioinformatics. 2024;40(Supplement_1):i39-i47. doi:10.1093/bioinformatics/btae243

BibTeX
@article{Serajian2024,
  author = {Serajian, Mohammadali and Marini, Simone and Alanko, Jarno N and Noyes, Noelle R and Prosperi, Mattia and Boucher, Christina},
  title = {Scalable de novo classification of antibiotic resistance of Mycobacterium tuberculosis},
  journal = {Bioinformatics},
  year = {2024},
  volume = {40},
  number = {Supplement_1},
  pages = {i39--i47},
  doi = {10.1093/bioinformatics/btae243}
}
Kostenlos starten →