Feature representation for explainable CRISPR off-target prediction and base editing efficiency
Frontiers in Bioinformatics · 20.04.2026 · 6
DOI: 10.3389/fbinf.2026.1800237 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Bioinformatics, online erschienen am 20.04.2026. Verfasst von Faiza Hasin und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Bari Aldo Moro, Bari, Italy. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
The interaction between guide RNAs (gRNAs) and target DNA sequences is a critical factor in the effectiveness of CRISPR/Cas9 (Clustered Regularly Interspaced Short Palindromic Repeats/CRISPR-associated protein 9) gene editing. Predicting these interactions accurately necessitates models that offer biological knowledge in addition to high accuracy. This study analyzes the impact of feature representation on accuracy and interpretability in off-target prediction.
Methods
We address two CRISPR applications: gene knockout (KO) and base editing (BE) using distinct benchmark datasets. For the KO problem, we utilized CHANGE-seq and GUIDE-seq to evaluate paired sequence representations, while the Hanna screening dataset has been used for BE. We approached the prediction problem both as a classification and regression task using XGBoost models.
Results
In the case of KO, there is not a single universally optimal encoding. For both classification and regression, One-Hot and its variants (OH, OH5C) achieve the best results on GUIDE-seq (AUPR = 0.661, Pearson = 0.756), while the Bulges representation performs best on CHANGE-seq (AUPR = 0.612, Pearson = 0.602). In the case of BE, One-hot encoding consistently outperforms K-mer representation for predictive accuracy both as regression and classification (AUPR = 0.723, Pearson = 0.746).
Discussion
Our analysis demonstrates comparable predictive performance across both gene knockout and base editing tasks, confirming the robustness of the framework in distinct editing domains. Interpretability analysis using SHapley Additive exPlanations (SHAP) reveals that despite different mechanisms, the Protospacer Adjacent Motif (PAM)-proximal region remains a critical feature for prediction for both editing mechanisms.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, University of Bari Aldo Moro, Bari, Italy.
- Institute for Biomedical Technologies (Bari Unit), National Research Council (CNR), Bari, Italy.
- Institute for Biomedical Technologies (Milan Unit), National Research Council (CNR), Milan, Italy.
Zitieren
APA
Hasin, F., Minervini, M., Mencar, C., Ventrella, G., Consiglio, A., Orro, A., & Selmi, T. (2026). Feature representation for explainable CRISPR off-target prediction and base editing efficiency. Frontiers in Bioinformatics, 6. https://doi.org/10.3389/fbinf.2026.1800237
Vancouver
Hasin F, Minervini M, Mencar C, Ventrella G, Consiglio A, Orro A, et al. Feature representation for explainable CRISPR off-target prediction and base editing efficiency. Frontiers in Bioinformatics. 2026;6. doi:10.3389/fbinf.2026.1800237
BibTeX
@article{Hasin2026,
author = {Hasin, Faiza and Minervini, Michele and Mencar, Corrado and Ventrella, Giuseppe and Consiglio, Arianna and Orro, Alessandro and Selmi, Tommaso},
title = {Feature representation for explainable CRISPR off-target prediction and base editing efficiency},
journal = {Frontiers in Bioinformatics},
year = {2026},
volume = {6},
doi = {10.3389/fbinf.2026.1800237}
}
EUVIMED