ReadSeeker: A DNABERT based de-novo read-level gene predictor
PLOS One · 2025
DOI: 10.1371/journal.pone.0335732 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Ben Wulf und 1 weiteren Autor:innen. Beteiligte Einrichtung: Center for Bio-Medical Image and Information Processing (CBMI), HTW University of Applied Sciences, Berlin, Berlin, Germany. Hauptthemen laut MEDLINE: Software, High-Throughput Nucleotide Sequencing, Sequence Analysis, DNA, Computational Biology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
ReadSeeker, a newly fine-tuned, DNABERT-based model, differentiates NGS short reads into protein-coding (CDS) and non-protein-coding (non-CDS) categories without requiring known reference sequences. For model training, extensive datasets encompassing viral, bacterial, and mammalian sequences where used. Training involved generating approximately 3 million synthetic reads from annotated genomic elements. Performance evaluation on real-world datasets, including human, viral, and bacterial samples, revealed ReadSeeker’s high accuracy, exceeding 94%, with ROC-AUC scores above 98% in most cases.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Center for Bio-Medical Image and Information Processing (CBMI), HTW University of Applied Sciences, Berlin, Berlin, Germany.
ORCID-Profile: Ben Wulf, Piotr Wojciech Dabrowski
Zitieren
APA
Wulf, B., & Dabrowski, P. W. (2025). ReadSeeker: A DNABERT based de-novo read-level gene predictor. PLOS One. https://doi.org/10.1371/journal.pone.0335732
Vancouver
Wulf B, Dabrowski PW. ReadSeeker: A DNABERT based de-novo read-level gene predictor. PLOS One. 2025. doi:10.1371/journal.pone.0335732
BibTeX
@article{Wulf2025,
author = {Wulf, Ben and Dabrowski, Piotr Wojciech},
title = {ReadSeeker: A DNABERT based de-novo read-level gene predictor},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0335732}
}
EUVIMED