---
_id: '14716'
abstract:
- lang: eng
  text: "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.\r\n\r\nResults: 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.\r\n\r\nConclusions:
    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."
acknowledgement: Open Access funding enabled and organized by Projekt DEAL. A.Y. and
  O.V.K. acknowledge financial support from the Klaus Faber Foundation. A.A.A. was
  funded by the Helmholtz AI project AMR-XAI. The work of O.O.B. is funded by Fonds
  zur Förderung der Wissenschaftlichen Forschung (FWF), Grant ESP 253-B.
article_number: '404'
article_processing_charge: Yes (via OA deal)
article_type: original
author:
- first_name: Alper
  full_name: Yurtseven, Alper
  last_name: Yurtseven
- first_name: Sofia
  full_name: Buyanova, Sofia
  id: 2F54A7BC-3902-11EA-AC87-BC9F3DDC885E
  last_name: Buyanova
- first_name: Amay Ajaykumar A.
  full_name: Agrawal, Amay Ajaykumar A.
  last_name: Agrawal
- first_name: Olga
  full_name: Bochkareva, Olga
  id: C4558D3C-6102-11E9-A62E-F418E6697425
  last_name: Bochkareva
  orcid: 0000-0003-1006-6639
- first_name: Olga V V.
  full_name: Kalinina, Olga V V.
  last_name: Kalinina
citation:
  ama: Yurtseven A, Buyanova S, Agrawal AAA, Bochkareva O, Kalinina OVV. Machine learning
    and phylogenetic analysis allow for predicting antibiotic resistance in M. tuberculosis.
    <i>BMC Microbiology</i>. 2023;23(1). doi:<a href="https://doi.org/10.1186/s12866-023-03147-7">10.1186/s12866-023-03147-7</a>
  apa: Yurtseven, A., Buyanova, S., Agrawal, A. A. A., Bochkareva, O., &#38; Kalinina,
    O. V. V. (2023). Machine learning and phylogenetic analysis allow for predicting
    antibiotic resistance in M. tuberculosis. <i>BMC Microbiology</i>. Springer Nature.
    <a href="https://doi.org/10.1186/s12866-023-03147-7">https://doi.org/10.1186/s12866-023-03147-7</a>
  chicago: Yurtseven, Alper, Sofia Buyanova, Amay Ajaykumar A. Agrawal, Olga Bochkareva,
    and Olga V V. Kalinina. “Machine Learning and Phylogenetic Analysis Allow for
    Predicting Antibiotic Resistance in M. Tuberculosis.” <i>BMC Microbiology</i>.
    Springer Nature, 2023. <a href="https://doi.org/10.1186/s12866-023-03147-7">https://doi.org/10.1186/s12866-023-03147-7</a>.
  ieee: A. Yurtseven, S. Buyanova, A. A. A. Agrawal, O. Bochkareva, and O. V. V. Kalinina,
    “Machine learning and phylogenetic analysis allow for predicting antibiotic resistance
    in M. tuberculosis,” <i>BMC Microbiology</i>, vol. 23, no. 1. Springer Nature,
    2023.
  ista: Yurtseven A, Buyanova S, Agrawal AAA, Bochkareva O, Kalinina OVV. 2023. Machine
    learning and phylogenetic analysis allow for predicting antibiotic resistance
    in M. tuberculosis. BMC Microbiology. 23(1), 404.
  mla: Yurtseven, Alper, et al. “Machine Learning and Phylogenetic Analysis Allow
    for Predicting Antibiotic Resistance in M. Tuberculosis.” <i>BMC Microbiology</i>,
    vol. 23, no. 1, 404, Springer Nature, 2023, doi:<a href="https://doi.org/10.1186/s12866-023-03147-7">10.1186/s12866-023-03147-7</a>.
  short: A. Yurtseven, S. Buyanova, A.A.A. Agrawal, O. Bochkareva, O.V.V. Kalinina,
    BMC Microbiology 23 (2023).
date_created: 2023-12-31T23:01:02Z
date_published: 2023-12-01T00:00:00Z
date_updated: 2024-01-02T09:20:57Z
day: '01'
ddc:
- '570'
department:
- _id: FyKo
doi: 10.1186/s12866-023-03147-7
external_id:
  pmid:
  - '38124060'
file:
- access_level: open_access
  checksum: 7ff5e95f3496ff663301eb4a13a316d5
  content_type: application/pdf
  creator: dernst
  date_created: 2024-01-02T09:09:32Z
  date_updated: 2024-01-02T09:09:32Z
  file_id: '14723'
  file_name: 2023_BMCMicrobiology_Yurtseven.pdf
  file_size: 1979922
  relation: main_file
  success: 1
file_date_updated: 2024-01-02T09:09:32Z
has_accepted_license: '1'
intvolume: '        23'
issue: '1'
language:
- iso: eng
license: https://creativecommons.org/licenses/by/4.0/
month: '12'
oa: 1
oa_version: Published Version
pmid: 1
publication: BMC Microbiology
publication_identifier:
  eissn:
  - 1471-2180
publication_status: published
publisher: Springer Nature
quality_controlled: '1'
scopus_import: '1'
status: public
title: Machine learning and phylogenetic analysis allow for predicting antibiotic
  resistance in M. tuberculosis
tmp:
  image: /images/cc_by.png
  legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
  name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
  short: CC BY (4.0)
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 23
year: '2023'
...