PT  - JOURNAL ARTICLE
AU  - Florian Störtz
AU  - Jeffrey Mak
AU  - Peter Minary
TI  - piCRISPR: Physically Informed Deep Learning Models for CRISPR/Cas9 Off-Target Cleavage Prediction
AID  - 10.1101/2021.11.16.468799
DP  - 2022 Jan 01
TA  - bioRxiv
PG  - 2021.11.16.468799
4099  - http://biorxiv.org/content/early/2022/06/07/2021.11.16.468799.short
4100  - http://biorxiv.org/content/early/2022/06/07/2021.11.16.468799.full
AB  - CRISPR/Cas programmable nuclease systems have become ubiquitous in the field of gene editing. With progressing development, applications in in vivo therapeutic gene editing are increasingly within reach, yet limited by possible adverse side effects from unwanted edits. Recent years have thus seen continuous development of off-target prediction algorithms trained on in vitro cleavage assay data gained from immortalised cell lines. Here, we implement novel deep learning algorithms and feature encodings for off-target prediction and systematically sample the resulting model space in order to find optimal models and inform future modelling efforts. We lay emphasis on physically informed features which capture the biological environment of the cleavage site, hence terming our approach piCRISPR, which we gain on the large, diverse crisprSQL off-target cleavage dataset. We find that our best-performing model highlights the importance of sequence context and chromatin accessibility for cleavage prediction and compares favourably with state-of-the-art prediction performance. We further show that our novel, environmentally sensitive features are crucial to accurate prediction on sequence-identical locus pairs, making them highly relevant for clinical guide design. The source code and trained models can be found ready to use at github.com/florianst/picrispr.Competing Interest StatementThe authors have declared no competing interest.