EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY-NC 4.0

EnhancerMatcher: comparing cell-type-specific enhancer activity of DNA sequences using deep convolutional neural networks and explainable AI

Luis M Solis, William L Melendez, Shantanu H Fuke, Sayantan Paul, Anthony B Garza, Rolando Garcia, Marc S Halfon iD, Hani Z Girgis iD

NAR Genomics and Bioinformatics · 2025

DOI: 10.1093/nargab/lqaf151 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift NAR Genomics and Bioinformatics, 2025. Verfasst von Luis M Solis und 7 weiteren Autor:innen. Beteiligte Einrichtung: The Bioinformatics Toolsmith Laboratory, Department of Electrical Engineering and Computer Science, Texas A&M University-Kingsville, Kingsville, TX 7…. Hauptthemen laut MEDLINE: Enhancer Elements, Genetic, Neural Networks, Computer, Software, Sequence Analysis, DNA. Die Arbeit nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NHGRI NIH HHS, National Human Genome Research Institute, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Transcriptional enhancers—unlike promoters—are challenging to identify computationally due to their variable distance and orientation relative to target genes. The scarcity of experimentally confirmed enhancers often limits the training of robust machine-learning models for enhancer prediction. We present EnhancerMatcher, a convolutional neural network-based tool that identifies cell-type-specific enhancers using only two confirmed enhancers as references. Trained on putative enhancers from the CATlas Project and control sequences from the human genome, EnhancerMatcher classifies sequences in triplets: two known enhancers from a common cell type and a third sequence evaluated for enhancer activity. Unlike existing methods, EnhancerMatcher enables classification across all cell types while preserving specificity through two reference enhancers. It achieved 90% accuracy, 92% recall, and 87% specificity on human test data. Furthermore, EnhancerMatcher demonstrated strong cross-species generalization, effectively recognizing mouse enhancers using its human-trained model, and exhibited consistent performance across diverse cell types regardless of their data representation size. EnhancerMatcher extracts features directly from raw sequences and provides interpretability through class activation maps, making it a powerful, versatile, and generalizable tool for enhancer discovery and regulatory sequence analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Enhancer Elements, GeneticNeural Networks, ComputerSoftwareSequence Analysis, DNAHumansAnimalsMiceDeep LearningMachine LearningConvolutional Neural Networks

Autor:innen und Institutionen

  • The Bioinformatics Toolsmith Laboratory, Department of Electrical Engineering and Computer Science, Texas A&M University-Kingsville, Kingsville, TX 78363, United States.
  • Department of Biochemistry, University at Buffalo-State University of New York, Buffalo, NY 14203, United States.

ORCID-Profile: Marc S Halfon, Hani Z Girgis

Förderung

  • NHGRI NIH HHS
  • National Human Genome Research Institute
  • National Institutes of Health

Zitieren

APA

Solis, L. M., Melendez, W. L., Fuke, S. H., Paul, S., Garza, A. B., Garcia, R., Halfon, M. S., & Girgis, H. Z. (2025). EnhancerMatcher: comparing cell-type-specific enhancer activity of DNA sequences using deep convolutional neural networks and explainable AI. NAR Genomics and Bioinformatics. https://doi.org/10.1093/nargab/lqaf151

Vancouver

Solis LM, Melendez WL, Fuke SH, Paul S, Garza AB, Garcia R, et al. EnhancerMatcher: comparing cell-type-specific enhancer activity of DNA sequences using deep convolutional neural networks and explainable AI. NAR Genomics and Bioinformatics. 2025. doi:10.1093/nargab/lqaf151

BibTeX
@article{Solis2025,
  author = {Solis, Luis M and Melendez, William L and Fuke, Shantanu H and Paul, Sayantan and Garza, Anthony B and Garcia, Rolando and Halfon, Marc S and Girgis, Hani Z},
  title = {EnhancerMatcher: comparing cell-type-specific enhancer activity of DNA sequences using deep convolutional neural networks and explainable AI},
  journal = {NAR Genomics and Bioinformatics},
  year = {2025},
  doi = {10.1093/nargab/lqaf151}
}
Kostenlos starten →