CROP: a feature-independent context-aware method for CRISPR-Cas9 frameshift prediction.
Open Access
- 1 July 2026
- journal article
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 42 (Supplement)
Abstract
The CRISPR-Cas9 complex has revolutionized genome-editing technologies. By designing a 20 nt-long guide RNA, a Cas9 nuclease can be guided to cleave almost any genomic target site (followed by NGG). The cleavage induces double-stranded DNA breaks, which are then repaired by cellular pathways. Accurate CRISPR-Cas9 repair-outcome prediction is essential for designing guide RNAs with desired genomic effects, such as gene knockout. A central challenge is quantifying the rate of frameshifts, i.e. repair-outcomes that lead to a change in the local length that is not a multiple of three. Previous methods for frameshift-rate prediction were trained on only a few experimental or cellular contexts, mostly relied on manually defined microhomology features, and were limited by sparse features and class labels. We developed CROP, a feature-independent context-aware repair-outcome prediction method. By aggregating specific repair outcomes as Δlength classes, CROP overcomes class sparsity. We designed CROP to work with variable input sequence lengths and output classes to utilize multiple datasets simultaneously. We benchmarked CROP against state-of-the-art repair-outcome prediction methods over 18 datasets, which we curated and standardized from various studies. Across all datasets, CROP outperformed all competing methods in frameshift-rate prediction. We performed cross-experiment and cross-cellular frameshift-rate predictions to investigate the generalizability of repair mechanisms. Finally, we show that CROP learned microhomology principles from raw sequences without explicit feature engineering, establishing an end-to-end architecture for CRISPR-Cas9 repair-outcome prediction that learns from multiple datasets. CROP is available at https://github.com/OrensteinLab/CROP.Keywords
Funding Information
- Israel Science Foundation (358/21)
This publication has 22 references indexed in Scilit:
- Advances in genome editing through control of DNA repair pathwaysNature Cell Biology, 2019
- Cas9 has no exonuclease activity resulting in staggered cleavage with overhangs and predictable di- and tri-nucleotide CRISPR insertions without template donorCell Discovery, 2019
- Large dataset enables prediction of repair after CRISPR–Cas9 editing in primary T cellsNature Biotechnology, 2019
- Massively parallel profiling and predictive modeling of the outcomes of CRISPR/Cas9-mediated double-strand break repairNucleic Acids Research, 2019
- Predictable and precise template-free CRISPR editing of pathogenic variantsNature, 2018
- Discovering epistatic feature interactions from neural network models of regulatory DNA sequencesBioinformatics, 2018
- Genome-Scale CRISPR-Cas9 Knockout Screening in Human CellsScience, 2014
- Nucleotide sequence of the iap gene, responsible for alkaline phosphatase isozyme conversion in Escherichia coli, and identification of the gene productJournal of Bacteriology, 1987
- Increased frequency of N-region insertion in a murine pre-B-cell line infected with a terminal deoxynucleotidyl transferase retroviral expression vector.Molecular and Cellular Biology, 1987
- Joining of immunoglobulin heavy chain gene segments: implications from a chromosome with evidence of three D-JH fusions.Proceedings of the National Academy of Sciences, 1982