EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Negative dataset selection impacts machine learning-based predictors for multiple bacterial species promoters

Marcelo González iD, Roberto E Durán iD, Michael Seeger iD, Mauricio Araya iD, Nicolás Jara iD

Bioinformatics · 2025

DOI: 10.1093/bioinformatics/btaf135 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2025. Verfasst von Marcelo González und 4 weiteren Autor:innen. Beteiligte Einrichtung: Departamento de Electrónica, Universidad Técnica Federico Santa María, Avenida España 1680, Valparaíso 2390123, Chile. Hauptthemen laut MEDLINE: Machine Learning, Promoter Regions, Genetic, Bacteria. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Millennium Nucleus Bioproducts, Genomics and Environmental Microbiology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Advances in bacterial promoter predictors based on machine learning have greatly improved identification metrics. However, existing models overlooked the impact of negative datasets, previously identified in GC-content discrepancies between positive and negative datasets in single-species models. This study aims to investigate whether multiple-species models for promoter classification are inherently biased due to the selection criteria of negative datasets. We further explore whether the generation of synthetic random sequences (SRS) that mimic GC-content distribution of promoters can partly reduce this bias. Results Multiple-species predictors exhibited GC-content bias when using CDS as a negative dataset, suggested by specificity and sensibility metrics in a species-specific manner, and investigated by dimensionality reduction. We demonstrated a reduction in this bias by using the SRS dataset, with less detection of background noise in real genomic data. In both scenarios DNABERT showed the best metrics. These findings suggest that GC-balanced datasets can enhance the generalizability of promoter predictors across Bacteria. Availability and implementation The source code of the experiments is freely available at https://github.com/maigonzalezh/MultispeciesPromoterClassifier.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningPromoter Regions, GeneticBacteriaBase CompositionGenome, BacterialComputational Biology

Autor:innen und Institutionen

  • Departamento de Electrónica, Universidad Técnica Federico Santa María, Avenida España 1680, Valparaíso 2390123, Chile.
  • Laboratorio de Microbiología Molecular y Biotecnología Ambiental, Department of Chemistry & Center of Biotechnology Daniel Alkalay Lowitt, Universidad Técnica Federico Santa María, Avenida España 1680, Valparaíso 239012…
  • Millennium Nucleus Bioproducts, Genomics and Environmental Microbiology (BioGEM), Avenida España 1680, Valparaíso 2390123, Chile.

ORCID-Profile: Marcelo González, Roberto E Durán, Michael Seeger, Mauricio Araya, Nicolás Jara

Förderung

  • Millennium Nucleus Bioproducts, Genomics and Environmental Microbiology

Zitieren

APA

González, M., Durán, R. E., Seeger, M., Araya, M., & Jara, N. (2025). Negative dataset selection impacts machine learning-based predictors for multiple bacterial species promoters. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf135

Vancouver

González M, Durán RE, Seeger M, Araya M, Jara N. Negative dataset selection impacts machine learning-based predictors for multiple bacterial species promoters. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf135

BibTeX
@article{Gonzlez2025,
  author = {González, Marcelo and Durán, Roberto E and Seeger, Michael and Araya, Mauricio and Jara, Nicolás},
  title = {Negative dataset selection impacts machine learning-based predictors for multiple bacterial species promoters},
  journal = {Bioinformatics},
  year = {2025},
  doi = {10.1093/bioinformatics/btaf135}
}
Kostenlos starten →