An unsupervised explainable AI reveals oligonucleotide-usage zones matching 2,000 chromosome bands
Life Science Alliance · 2027-01 · 10 (1) · e202603782
DOI: 10.26508/lsa.202603782 ↗Kurz gefasst
Fachartikel in der Zeitschrift Life Science Alliance, online erschienen am 05.11.2026. Verfasst von Toshimichi Ikemura und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Bioscience, Nagahama Institute of Bio-Science and Technology, Nagahama, Japan t_ikemura@nagahama-i-bio.ac.jp. Hauptthemen laut MEDLINE: Oligonucleotides, Chromosomes, Human, Artificial Intelligence. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MEXT | Japan Science and Technology Agency, Nagahama Institute of Bio-Science and Technology.
Abstract (Originalsprache)
Unsupervised and explainable AI can uncover genomic features beyond human expectations. Oligonucleotides such as penta- and hexanucleotides often function as core binding motifs for regulatory proteins, and their usage provides powerful tools in functional genomics. We applied an unsupervised, explainable AI to their odds-ratio profiles of all 1-Mb euchromatic fragments in the human genome. Clustering using penta- or hexanucleotide odds ratios (1,024 or 4,096 variables) unexpectedly revealed nearly 2,000 distinct zones. CG-containing penta- and hexanucleotides (244 and 1,185 variables) produced comparable ∼2,000 zones, indicating fundamental genomic segmental structures. Human chromosomes exhibit Giemsa-banding patterns comprising 850 bands at prometaphase and ∼2,000 at prophase. Using single-nucleotide coordinates available for the 850 bands, we identified diagnostic oligonucleotides distinguishing Giemsa-negative and Giemsa-positive regions. Computational pseudo-band reconstruction based on these oligonucleotides generated genome segmentations that more closely paralleled the AI-derived ∼2,000 zones than the 850 bands. These findings indicate that AI captures characteristic sequence features of chromosomal bands and can predict high-resolution banding from genome sequences alone, thereby bridging classical cytogenetics and modern AI-based genomics.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Faculty of Bioscience, Nagahama Institute of Bio-Science and Technology, Nagahama, Japan t_ikemura@nagahama-i-bio.ac.jp.
- Association for Propagation of the Knowledge of Genetics, Shizuoka, Japan.
- Faculty of Bioscience, Nagahama Institute of Bio-Science and Technology, Nagahama, Japan.
- Graduate School of Science and Technology Electrical and Information Engineering, Niigata University, Niigata, Japan.
ORCID-Profile: Toshimichi Ikemura
Förderung
- MEXT | Japan Science and Technology Agency
- Nagahama Institute of Bio-Science and Technology
Zitieren
APA
Ikemura, T., Iwasaki, Y., Wada, K., Wada, Y., & Abe, T. (2027). An unsupervised explainable AI reveals oligonucleotide-usage zones matching 2,000 chromosome bands. Life Science Alliance, 10(1), e202603782. https://doi.org/10.26508/lsa.202603782
Vancouver
Ikemura T, Iwasaki Y, Wada K, Wada Y, Abe T. An unsupervised explainable AI reveals oligonucleotide-usage zones matching 2,000 chromosome bands. Life Science Alliance. 2027;10(1):e202603782. doi:10.26508/lsa.202603782
BibTeX
@article{Ikemura2027,
author = {Ikemura, Toshimichi and Iwasaki, Yuki and Wada, Kennosuke and Wada, Yoshiko and Abe, Takashi},
title = {An unsupervised explainable AI reveals oligonucleotide-usage zones matching 2,000 chromosome bands},
journal = {Life Science Alliance},
year = {2027},
volume = {10},
number = {1},
pages = {e202603782},
doi = {10.26508/lsa.202603782}
}
EUVIMED