EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Machine learning for small-molecule antibiotics – discovery to pre-clinical optimization

Denise B Catacutan, Fabio Borgonovo, Isin Y Comba, Francesco Petri, Elie F Berbari, Jonathan M Stokes

Clinical Microbiology and Infection · 2026-11

DOI: 10.1016/j.cmi.2026.11.006 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Clinical Microbiology and Infection, 2026-11. Verfasst von Denise B Catacutan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biochemistry and Biomedical Sciences, McMaster University, Hamilton, Ontario, Canada; Michael G. DeGroote Institute for Infectious Dise…. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Canada Foundation for Innovation, Government of Ontario, Brain Tumour Foundation of Canada.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: The rapid rise of antimicrobial resistance (AMR) poses a critical global health crisis, with 4.71 million associated deaths and 1.14 million attributable deaths in 2021. By 2050, these tolls are forecasted to rise to 8.22 million associated deaths and 1.91 million attributable deaths annually. Despite this growing burden, the antibacterial pipeline is alarmingly lean, with few candidates exhibiting truly novel mechanisms of action (MOA). This innovation gap is worsened by the lack of economic incentives for large pharmaceutical companies to develop new antibiotics, placing increasing pressure on academic laboratories and small biotechnology companies. Machine learning (ML) has emerged as a promising, albeit unproven, toolset to accelerate and reduce the cost of antibiotic discovery and development. OBJECTIVES: To review a cross-section of ML methods and their applications across the preclinical antibiotic discovery and development pipeline. SOURCES: Google Scholar and PubMed were searched through June 2026, combining terms for machine learning, deep learning, and artificial intelligence with antibiotic discovery and development, virtual screening, generative molecular design, and ADMET prediction. Primary research articles were prioritized, with preprints from arXiv and bioRxiv included where no peer-reviewed version was available. Reference lists of retrieved articles and WHO antibacterial pipeline reports were also screened. CONTENT: ML approaches enable more efficient exploration of vast chemical spaces in silico, facilitating the discovery of structurally novel antibacterial compounds in phenotype- and target-based applications. Both discriminative and generative models have demonstrated success in discovering new scaffolds and in multi-property optimization tasks. In target-based discovery, ML-guided docking strategies have improved scalability relative to more computationally demanding physics-based methods. IMPLICATIONS: ML-guided methods can improve the efficiency, scalability, and success rate of antibiotic discovery and development programs. However, the implementation of these models will require high-quality training data and rigorous experimental validation prior to end-to-end integration.

Schlagwörter

Stichwörter der Autor:innen

antibioticsartificial intelligencemachine learning

Autor:innen und Institutionen

  • Department of Biochemistry and Biomedical Sciences, McMaster University, Hamilton, Ontario, Canada; Michael G. DeGroote Institute for Infectious Disease Research, McMaster University, Hamilton, Ontario, Canada; David Br…
  • Division of Public Health, Infectious Diseases and Occupational Medicine, Department of Medicine, Mayo Clinic College of Medicine and Science, Mayo Clinic, Rochester, 55905 MN, USA; Department of Infectious Diseases, Lu…
  • Division of Public Health, Infectious Diseases and Occupational Medicine, Department of Medicine, Mayo Clinic College of Medicine and Science, Mayo Clinic, Rochester, 55905 MN, USA.

Förderung

  • Canada Foundation for Innovation
  • Government of Ontario
  • Brain Tumour Foundation of Canada
  • Canadian Institutes of Health Research
  • Weston Family Foundation
  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Catacutan, D. B., Borgonovo, F., Comba, I. Y., Petri, F., Berbari, E. F., & Stokes, J. M. (2026). Machine learning for small-molecule antibiotics – discovery to pre-clinical optimization. Clinical Microbiology and Infection. https://doi.org/10.1016/j.cmi.2026.11.006

Vancouver

Catacutan DB, Borgonovo F, Comba IY, Petri F, Berbari EF, Stokes JM. Machine learning for small-molecule antibiotics – discovery to pre-clinical optimization. Clinical Microbiology and Infection. 2026. doi:10.1016/j.cmi.2026.11.006

BibTeX
@article{Catacutan2026,
  author = {Catacutan, Denise B and Borgonovo, Fabio and Comba, Isin Y and Petri, Francesco and Berbari, Elie F and Stokes, Jonathan M},
  title = {Machine learning for small-molecule antibiotics – discovery to pre-clinical optimization},
  journal = {Clinical Microbiology and Infection},
  year = {2026},
  doi = {10.1016/j.cmi.2026.11.006}
}
Kostenlos starten →