EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access

Deep Learning Based Models for CRISPR/Cas Off‐Target Prediction

Mingming Cao, Alexander Brennan, Ciaran M Lee, So-Hyun Park, Gang Bao iD

Small Methods · 2025-07 · 9 (7)

DOI: 10.1002/smtd.202500122 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Small Methods, online erschienen am 04.06.2025. Verfasst von Mingming Cao und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bioengineering, Rice University, Houston, TX, 77030, USA. Hauptthemen laut MEDLINE: Deep Learning, CRISPR-Cas Systems, Gene Editing. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 123 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHLBI NIH HHS, Cancer Prevention and Research Institute of Texas, NHGRI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

CRISPR/Cas genome editing technologies enable effective and controlled genetic modifications; however, off‐target effects remain a significant concern, particularly in clinical applications. Experimental and in silico methods are developed to predict potential off‐target sites (OTS), including deep learning based methods, which can automatically and comprehensively learn sequence features, offer a promising tool for OTS prediction. Here, this work reviews the existing OTS prediction tools with an emphasis on deep learning methods, characterizes datasets used for deep learning training and testing, and evaluates six deep learning models —CRISPR‐Net, CRISPR‐IP, R‐CRISPR, CRISPR‐M, CrisprDNT, and Crispr‐SGRU —using six public datasets and validates OTS data from the CRISPRoffT database. Performance of these models is assessed using standardized metrics, such as Precision, Recall, F1 score, MCC, AUROC and PRAUC. This work finds that incorporating validated OTS datasets into model training enhanced overall model performance, and improved robustness of prediction, particularly with highly imbalanced datasets. While no model consistently outperforms other models across all scenarios, CRISPR‐Net, R‐CRISPR, and Crispr‐SGRU show strong overall performance. This analysis demonstrates the importance of integrating high‐quality validated OTS data with advanced deep learning architectures to improve CRISPR/Cas off‐target site predictions, ensuring safer genome editing applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningCRISPR-Cas SystemsGene EditingHumans

Stichwörter der Autor:innen

CRISPR/Casdeep learning modelgene editingoff‐target sites

Autor:innen und Institutionen

  • Department of Bioengineering, Rice University, Houston, TX, 77030, USA.
  • School of Biochemistry and Cell Biology, University College Cork, Cork, T12 K8AF, Ireland.

ORCID-Profile: Gang Bao

Förderung

  • NHLBI NIH HHS
  • Cancer Prevention and Research Institute of Texas
  • NHGRI NIH HHS
  • National Human Genome Research Institute
  • National Heart, Lung, and Blood Institute

Zitieren

APA

Cao, M., Brennan, A., Lee, C. M., Park, S. H., & Bao, G. (2025). Deep Learning Based Models for CRISPR/Cas Off‐Target Prediction. Small Methods, 9(7). https://doi.org/10.1002/smtd.202500122

Vancouver

Cao M, Brennan A, Lee CM, Park SH, Bao G. Deep Learning Based Models for CRISPR/Cas Off‐Target Prediction. Small Methods. 2025;9(7). doi:10.1002/smtd.202500122

BibTeX
@article{Cao2025,
  author = {Cao, Mingming and Brennan, Alexander and Lee, Ciaran M and Park, So-Hyun and Bao, Gang},
  title = {Deep Learning Based Models for CRISPR/Cas Off‐Target Prediction},
  journal = {Small Methods},
  year = {2025},
  volume = {9},
  number = {7},
  doi = {10.1002/smtd.202500122}
}
Kostenlos starten →