EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Predicting bacterial transcription factor binding sites through machine learning and structural characterization based on DNA duplex stability

André Borges Farias iD, Gustavo Sganzerla Martinez iD, Edgardo Galán-Vásquez iD, Marisa Fabiana Nicolás iD, Ernesto Pérez-Rueda iD

Briefings in Bioinformatics · 2024

DOI: 10.1093/bib/bbae581 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2024. Verfasst von André Borges Farias und 4 weiteren Autor:innen. Beteiligte Einrichtung: Laboratório Nacional de Computação Científica - LNCC, Avenida Getúlio Vargas, Petrópolis, Rio de Janeiro 25651075, Brazil. Hauptthemen laut MEDLINE: Machine Learning, Transcription Factors. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: PAPIIT-DGAPA UNAM, Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES/UNAM, COOPBRAS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Transcriptional factors (TFs) in bacteria play a crucial role in gene regulation by binding to specific DNA sequences, thereby assisting in the activation or repression of genes. Despite their central role, deciphering shape recognition of bacterial TFs-DNA interactions remains an intricate challenge. A deeper understanding of DNA secondary structures could greatly enhance our knowledge of how TFs recognize and interact with DNA, thereby elucidating their biological function. In this study, we employed machine learning algorithms to predict transcription factor binding sites (TFBS) and classify them as directed-repeat (DR) or inverted-repeat (IR). To accomplish this, we divided the set of TFBS nucleotide sequences by size, ranging from 8 to 20 base pairs, and converted them into thermodynamic data known as DNA duplex stability (DDS). Our results demonstrate that the Random Forest algorithm accurately predicts TFBS with an average accuracy of over 82% and effectively distinguishes between IR and DR with an accuracy of 89%. Interestingly, upon converting the base pairs of several TFBS-IR into DDS values, we observed a symmetric profile typical of the palindromic structure associated with these architectures. This study presents a novel TFBS prediction model based on a DDS characteristic that may indicate how respective proteins interact with base pairs, thus providing insights into molecular mechanisms underlying bacterial TFs-DNA interaction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningTranscription FactorsBinding SitesDNA, BacterialAlgorithmsDNANucleic Acid ConformationComputational BiologyBacterial ProteinsProtein BindingBacteria

Stichwörter der Autor:innen

DNA duplex stabilitymachine learningtranscription factor binding site

Substanzen

Transcription FactorsDNA, BacterialDNABacterial Proteins

Autor:innen und Institutionen

  • Laboratório Nacional de Computação Científica - LNCC, Avenida Getúlio Vargas, Petrópolis, Rio de Janeiro 25651075, Brazil.
  • Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas, Universidad Nacional Autónoma de México, Unidad Académica del Estado de Yucatán, Carretera Sierra Papacal, Mérida 97302, Yucatán, México.
  • Microbiology and Immunology, Dalhousie University, 5850 College Street, Halifax B3H 4H7, Nova Scotia, Canada.
  • Departamento de Ingeniería de Sistemas Computacionales y Automatización, Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas, Universidad Nacional Autónoma de México, Ciudad Universitaria, Circuito Escol…

ORCID-Profile: André Borges Farias, Gustavo Sganzerla Martinez, Edgardo Galán-Vásquez, Marisa Fabiana Nicolás, Ernesto Pérez-Rueda

Förderung

  • PAPIIT-DGAPA UNAM
  • Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES/UNAM
  • COOPBRAS
  • CNPq
  • FAPERJ-CNE

Zitieren

APA

Borges Farias, A., Sganzerla Martinez, G., Galán-Vásquez, E., Nicolás, M. F., & Pérez-Rueda, E. (2024). Predicting bacterial transcription factor binding sites through machine learning and structural characterization based on DNA duplex stability. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae581

Vancouver

Borges Farias A, Sganzerla Martinez G, Galán-Vásquez E, Nicolás MF, Pérez-Rueda E. Predicting bacterial transcription factor binding sites through machine learning and structural characterization based on DNA duplex stability. Briefings in Bioinformatics. 2024. doi:10.1093/bib/bbae581

BibTeX
@article{BorgesFarias2024,
  author = {Borges Farias, André and Sganzerla Martinez, Gustavo and Galán-Vásquez, Edgardo and Nicolás, Marisa Fabiana and Pérez-Rueda, Ernesto},
  title = {Predicting bacterial transcription factor binding sites through machine learning and structural characterization based on DNA duplex stability},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  doi = {10.1093/bib/bbae581}
}
Kostenlos starten →