DNAi: an open-source AI tool for unbiased DNA fiber analysis
Nucleic Acids Research · 13.04.2026 · 54 (7)
DOI: 10.1093/nar/gkag335 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nucleic Acids Research, online erschienen am 17.04.2026. Verfasst von Clément Playout und 5 weiteren Autor:innen. Beteiligte Einrichtung: Research Center, Maisonneuve-Rosemont Hospital, 5415, boulevard de l'Assomption Montréal, H1T 2M4 Québec, Canada. Hauptthemen laut MEDLINE: DNA, Software, Image Processing, Computer-Assisted. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Université de Montréal-Etudes, WOCO foundation, Line Chevrette foundation.
Abstract (Originalsprache)
DNA fiber assays are powerful tools for investigating replication dynamics at the single-molecule level. However, their application and widespread adoption has been hampered by the labor-intensive and tedious nature of manual analysis of large numbers of images. Quantification of labeled DNA fibers typically depends on subjective examination, selection, and annotation of individual fibers from fluorescence microscopy images reducing inter-user consistency, reproducibility, and experimental throughput. To address these issues, we developed DNAi, a computer vision tool based on deep learning allowing automated detection and quantification of labeled DNA fiber length. DNAi was trained on a large and diverse dataset of manually annotated images of DNA fibers and matches human performance and accuracy in segmentation and length measurement across a wide range of experimental conditions. The open-source tool includes a user-friendly interface, which permits visual validation and manual selection of segmented fibers. Overall, DNAi enables robust, rapid, and reproducible DNA fiber analysis, and is freely available.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Research Center, Maisonneuve-Rosemont Hospital, 5415, boulevard de l'Assomption Montréal, H1T 2M4 Québec, Canada.
- Department of Ophthalmology, Université de Montréal, 2900 Edouard-Montpetit, H3T 1J4 Québec, Canada.
- Molecular Biology Program, Université de Montréal, 2900 Edouard-Montpetit, H3T 1J4 Québec, Canada.
- Department of Medicine, Université de Montréal, 2900 Edouard-Montpetit, H3T 1J4 Québec, Canada.
ORCID-Profile: Clément Playout, Yosra Mehrjoo, Renaud Duval, Marie Carole Boucher, Santiago Costantino, Hugo Wurtele
Förderung
- Université de Montréal-Etudes
- WOCO foundation
- Line Chevrette foundation
- Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
Playout, C., Mehrjoo, Y., Duval, R., Boucher, M. C., Costantino, S., & Wurtele, H. (2026). DNAi: an open-source AI tool for unbiased DNA fiber analysis. Nucleic Acids Research, 54(7). https://doi.org/10.1093/nar/gkag335
Vancouver
Playout C, Mehrjoo Y, Duval R, Boucher MC, Costantino S, Wurtele H. DNAi: an open-source AI tool for unbiased DNA fiber analysis. Nucleic Acids Research. 2026;54(7). doi:10.1093/nar/gkag335
BibTeX
@article{Playout2026,
author = {Playout, Clément and Mehrjoo, Yosra and Duval, Renaud and Boucher, Marie Carole and Costantino, Santiago and Wurtele, Hugo},
title = {DNAi: an open-source AI tool for unbiased DNA fiber analysis},
journal = {Nucleic Acids Research},
year = {2026},
volume = {54},
number = {7},
doi = {10.1093/nar/gkag335}
}
EUVIMED