EUVIMEDEUVIMED entdecken
Crossref

Short human eccDNAs are predictable from sequences

Kai-Li Chang, Jia-Hong Chen, Tzu-Chieh Lin, Jun-Yi Leu, Cheng-Fu Kao, Jin Yung Wong, Huai-Kuang Tsai

Briefings in Bioinformatics · 2023

DOI: 10.1093/bib/bbad147 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2023. Verfasst von Kai-Li Chang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Information Science, Academia Sinica, Taipei, 115, Taiwan. Hauptthemen laut MEDLINE: DNA, Circular, DNA. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Science and Technology Council, Academia Sinica Grand Challenge Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Ubiquitous presence of short extrachromosomal circular DNAs (eccDNAs) in eukaryotic cells has perplexed generations of biologists. Their widespread origins in the genome lacking apparent specificity led some studies to conclude their formation as random or near-random. Despite this, the search for specific formation of short eccDNA continues with a recent surge of interest in biomarker development.

Results

To shed new light on the conflicting views on short eccDNAs’ randomness, here we present DeepCircle, a bioinformatics framework incorporating convolution- and attention-based neural networks to assess their predictability. Short human eccDNAs from different datasets indeed have low similarity in genomic locations, but DeepCircle successfully learned shared DNA sequence features to make accurate cross-datasets predictions (accuracy: convolution-based models: 79.65 ± 4.7%, attention-based models: 83.31 ± 4.18%).

Conclusions

The excellent performance of our models shows that the intrinsic predictability of eccDNAs is encoded in the sequences across tissue origins. Our work demonstrates how the perceived lack of specificity in genomics data can be re-assessed by deep learning models to uncover unexpected similarity.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DNA, CircularDNAHumansGenomeEukaryotic CellsBiomarkers

Stichwörter der Autor:innen

bidirectional encoder representations from transformersconvolutional neural networkdeep learningextrachromosomal circular DNA

Substanzen

DNA, CircularDNABiomarkers

Autor:innen und Institutionen

  • Institute of Information Science, Academia Sinica, Taipei, 115, Taiwan.
  • Department of Electrical Engineering, National Taiwan University, Taipei, 106, Taiwan.
  • Institute of Molecular Biology, Academia Sinica, Taipei 115, Taiwan.
  • Institute of Cellular and Organismic Biology, Academia Sinica, Taipei 115, Taiwan.

Förderung

  • National Science and Technology Council
  • Academia Sinica Grand Challenge Program

Zitieren

APA

Chang, K. L., Chen, J. H., Lin, T. C., Leu, J. Y., Kao, C. F., Wong, J. Y., & Tsai, H. K. (2023). Short human eccDNAs are predictable from sequences. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbad147

Vancouver

Chang KL, Chen JH, Lin TC, Leu JY, Kao CF, Wong JY, et al. Short human eccDNAs are predictable from sequences. Briefings in Bioinformatics. 2023. doi:10.1093/bib/bbad147

BibTeX
@article{Chang2023,
  author = {Chang, Kai-Li and Chen, Jia-Hong and Lin, Tzu-Chieh and Leu, Jun-Yi and Kao, Cheng-Fu and Wong, Jin Yung and Tsai, Huai-Kuang},
  title = {Short human eccDNAs are predictable from sequences},
  journal = {Briefings in Bioinformatics},
  year = {2023},
  doi = {10.1093/bib/bbad147}
}
Kostenlos starten →