CRISCross: Integration of Epigenetic Information for Deep-Learning-Based Prediction of CRISPR-Cas9 Off-Targets Across Cell Types
- 1Bioinformatics Group, Department of Computer Science, University of Freiburg
Abstract
CRISPR-Cas9 enables precise genome editing but remains limited by off-target effects, raising safety concerns and necessitating accurate prediction. Although epigenetic features influence Cas9 binding and cleavage, their predictive signals are often weak, highlyvariable, and context-dependent, limiting the effectiveness of existing machine learning approaches. Cross-cell-type settings are especially challenging: epigenetic landscapes differ substantially, and models trained on one cell type frequently fail to generalize. Here, we systematically investigate the role of epigenetic context in off-target prediction and demonstrate that its utility depends on modeling interactions with sequence features rather than treating it as an independent signal. Tabular and deep learning experiments demonstrate that epigenetic features provide a consistent but modestly complementary signal, and that late-stage fusion strategies are insufficient to effectively exploit this information. To address this, we introduce CRISCross, a cross-attention-based architecture that captures sequence-epigenetic interactions at the nucleotide level, alongside CRISPRAT, a synthetic pretraining strategy that learns transferable representations from genome-derived sgRNA-off-target pairs without relying on dataset-specific pretraining. CRISCross, incorporating AlphaGenome-derived chromatin accessibility signals, shows better predictive performance than sequence-only baselines across three independent test datasets spanning two cell types, demonstrating improved generalization across guide RNAs, datasets, and cellular contexts. This is particularly relevant for therapeutic applications involving cell types or patient-derived contexts that lack dedicated experimental datasets. In such settings, predicted chromatin accessibility may provide scalable contextual information when direct epigenomic profiling is unavailable or impractical. Together, these results show that accurate CRISPR off-target prediction benefits from interaction-aware integration of epigenetic context alongside generalizable pretraining strategies.
Related
- PredIDR3: A new output-encoding scheme and abundant negative source provide more information for deep learning-based protein intrinsic disorder prediction
- Machine learning prediction of 1-year thrombosis risk in membranous nephropathy: integration of renal pathology and early longitudinal trajectories
- DNA methylation-based prediction of differentiation state at cell-type resolution reveals an age-associated epigenetic mesenchymal drift
- Cell-level integration of gene expression and B cell receptor data captures complementary B cell information
- Selection vs. integration task demands shape the similarity of information neural coding
BibTeX
@misc{pargeter2026criscross,
title = {{CRISCross: Integration of Epigenetic Information for Deep-Learning-Based Prediction of CRISPR-Cas9 Off-Targets Across Cell Types}},
author = {W. Jobson Pargeter and D. Rabsch and M. M. Kaufmann and M. Uhl and A. Mitrofanov and T. Brox and T. Cathomen and V. D. Tran and R. Backofen},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.09.757843},
url = {https://www.biorxiv.org/content/10.64898/2026.10.09.757843v1},
note = {CC BY-ND},
}
RIS
TY - UNPB
TI - CRISCross: Integration of Epigenetic Information for Deep-Learning-Based Prediction of CRISPR-Cas9 Off-Targets Across Cell Types
AU - W. Jobson Pargeter
AU - D. Rabsch
AU - M. M. Kaufmann
AU - M. Uhl
AU - A. Mitrofanov
AU - T. Brox
AU - T. Cathomen
AU - V. D. Tran
AU - R. Backofen
PY - 2026
DA - 2026/10/09
PB - bioRxiv
DO - 10.64898/2026.10.09.757843
UR - https://www.biorxiv.org/content/10.64898/2026.10.09.757843v1
AB - CRISPR-Cas9 enables precise genome editing but remains limited by off-target effects, raising safety concerns and necessitating accurate prediction. Although epigenetic features influence Cas9 binding and cleavage, their predictive signals are often weak, highlyvariable, and context-dependent, limiting the effectiveness of existing machine learning approaches. Cross-cell-type settings are especially challenging: epigenetic landscapes differ substantially, and models trained on one cell type frequently fail to generalize. Here, we systematically investigate the role of epigenetic context in off-target prediction and demonstrate that its utility depends on modeling interactions with sequence features rather than treating it as an independent signal. Tabular and deep learning experiments demonstrate that epigenetic features provide a consistent but modestly complementary signal, and that late-stage fusion strategies are insufficient to effectively exploit this information. To address this, we introduce CRISCross, a cross-attention-based architecture that captures sequence-epigenetic interactions at the nucleotide level, alongside CRISPRAT, a synthetic pretraining strategy that learns transferable representations from genome-derived sgRNA-off-target pairs without relying on dataset-specific pretraining. CRISCross, incorporating AlphaGenome-derived chromatin accessibility signals, shows better predictive performance than sequence-only baselines across three independent test datasets spanning two cell types, demonstrating improved generalization across guide RNAs, datasets, and cellular contexts. This is particularly relevant for therapeutic applications involving cell types or patient-derived contexts that lack dedicated experimental datasets. In such settings, predicted chromatin accessibility may provide scalable contextual information when direct epigenomic profiling is unavailable or impractical. Together, these results show that accurate CRISPR off-target prediction benefits from interaction-aware integration of epigenetic context alongside generalizable pretraining strategies.
ER -