EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Feature Selection Strategies for Deep Learning-Based Classification in Ultra-High-Dimensional Genomic Data

Krzysztof Kotlarz iD, Dawid Słomian iD, Weronika Zawadzka iD, Joanna Szyda iD

International Journal of Molecular Sciences · 18.08.2025 · 26 (16) · 7961

DOI: 10.3390/ijms26167961 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Molecular Sciences, online erschienen am 18.08.2025. Verfasst von Krzysztof Kotlarz und 3 weiteren Autor:innen. Beteiligte Einrichtung: Biostatistics Group, Department of Genetics, Wroclaw University of Environmental and Life Sciences, 51-631 Wroclaw, Poland. Hauptthemen laut MEDLINE: Deep Learning, Genomics. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Centre.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The advancement of high-throughput sequencing has revolutionised genomic research by generating large amounts of data. However, Whole-Genome Sequencing is associated with a statistical challenge known as the p >> n problem. We classified 1825 individuals into five breeds based on 11,915,233 SNPs. First, three feature selection algorithms were applied: SNP-tagging and two approaches based on supervised rank aggregation, followed by either one-dimensional (1D-SRA) or multidimensional (MD-SRA) feature clustering. Individuals were then classified into breeds using a deep learning classifier composed of Convolutional Neural Networks. SNPs selected by SNP-tagging yielded the least satisfactory F1-score (86.87%); however, this approach offered rapid computing time. The 1D-SRA was less suitable for ultra-high-dimensional data due to computational, memory, and storage limitations. However, the SNP set selected by this algorithm provided the best classification quality (96.81%). MD-SRA provided a good balance between classification quality (95.12%) and computational efficiency (17x lower analysis time, 14x lower data storage). Unlike SNP-tagging, SRA-based approaches are universal and are not limited to genomic data. This study addressed the demand for efficient computational and statistical tools for feature selection in high-dimensional genomic data. The results demonstrate that the proposed MD-SRA is suitable for the classification of high-dimensional data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningGenomicsPolymorphism, Single NucleotideAlgorithmsAnimalsHigh-Throughput Nucleotide SequencingNeural Networks, ComputerComputational Biology

Stichwörter der Autor:innen

SNPdeep learningdimensionality reductionfeature selection algorithmsmixed linear modelmulti-class classificationwhole-genome sequencing

Autor:innen und Institutionen

  • Biostatistics Group, Department of Genetics, Wroclaw University of Environmental and Life Sciences, 51-631 Wroclaw, Poland.
  • National Research Institute of Animal Production, 32-083 Balice, Poland.

ORCID-Profile: Krzysztof Kotlarz, Dawid Słomian, Weronika Zawadzka, Joanna Szyda

Förderung

  • National Science Centre

Zitieren

APA

Kotlarz, K., Słomian, D., Zawadzka, W., & Szyda, J. (2025). Feature Selection Strategies for Deep Learning-Based Classification in Ultra-High-Dimensional Genomic Data. International Journal of Molecular Sciences, 26(16), 7961. https://doi.org/10.3390/ijms26167961

Vancouver

Kotlarz K, Słomian D, Zawadzka W, Szyda J. Feature Selection Strategies for Deep Learning-Based Classification in Ultra-High-Dimensional Genomic Data. International Journal of Molecular Sciences. 2025;26(16):7961. doi:10.3390/ijms26167961

BibTeX
@article{Kotlarz2025,
  author = {Kotlarz, Krzysztof and Słomian, Dawid and Zawadzka, Weronika and Szyda, Joanna},
  title = {Feature Selection Strategies for Deep Learning-Based Classification in Ultra-High-Dimensional Genomic Data},
  journal = {International Journal of Molecular Sciences},
  year = {2025},
  volume = {26},
  number = {16},
  pages = {7961},
  doi = {10.3390/ijms26167961}
}
Kostenlos starten →