EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Normalized compression distance for DNA classification

Gavin Hearne, Mohammadsaleh S Refahi, Haozhe Neil Duan, James R Brown, Gail L Rosen

PeerJ · 2026

DOI: 10.7717/peerj.20677 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ, 2026. Verfasst von Gavin Hearne und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, Drexel University, Philadelphia, PA, United States of America. Hauptthemen laut MEDLINE: Sequence Analysis, DNA, Data Compression, DNA, Genomics. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Analyzing the origin and diversity of numerous genomic sequences, such as those sampled from the human microbiome, is an important first step in genomic analysis. The use of normalized compression distance (NCD) has demonstrated capabilities in the field of text classification as a low-resource alternative to deep neural networks (DNNs) by leveraging compression algorithms to approximate Kolmogorov information distance. In an effort to apply this technique toward genomics tasks akin to tools such as Many-against-Many sequence searching (MMseqs) and Kraken2, we have explored the use of a gzip -based NCD combination in both gene labeling of open reading frames (ORFs) and taxonomic classification of short reads. Our implementation achieved 0.89 accuracy and 0.88 macro-F1 on human gene classification, surpassing similar NCD-based approaches. In prokaryotic gene labeling tasks, NCD shows superior classification accuracy to traditional alignment or exact-match tools in out-of-distribution settings, while also outperforming comparable sequence-embedding methods in in-distribution classification. However, the computational complexity of O(MN) (in standard big-O notation, where M and N denote the sizes of the training and test databases, respectively) constrains scalability to very large datasets, though these findings nonetheless demonstrate that compression-based approaches provide an effective alternative for genomic sequence classification, particularly in low-data environments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Sequence Analysis, DNAData CompressionDNAGenomicsCompression AlgorithmsOpen Reading FramesGenes, BacterialGenes, Archaeal

Stichwörter der Autor:innen

Alignment-free methodsBioinformaticsCompression distanceGenomic classificationGenomic sequence analysisGzip compressionMetagenomics

Substanzen

DNA

Autor:innen und Institutionen

  • Department of Electrical Engineering, Drexel University, Philadelphia, PA, United States of America.

Förderung

  • National Science Foundation

Zitieren

APA

Hearne, G., S Refahi, M., Duan, H. N., Brown, J. R., & Rosen, G. L. (2026). Normalized compression distance for DNA classification. PeerJ. https://doi.org/10.7717/peerj.20677

Vancouver

Hearne G, S Refahi M, Duan HN, Brown JR, Rosen GL. Normalized compression distance for DNA classification. PeerJ. 2026. doi:10.7717/peerj.20677

BibTeX
@article{Hearne2026,
  author = {Hearne, Gavin and S Refahi, Mohammadsaleh and Duan, Haozhe Neil and Brown, James R and Rosen, Gail L},
  title = {Normalized compression distance for DNA classification},
  journal = {PeerJ},
  year = {2026},
  doi = {10.7717/peerj.20677}
}
Kostenlos starten →