Prediction of on-target and off-target activity of CRISPR–Cas13d guide RNAs using deep learning

• Published in: Nature biotechnology 2024-04, Vol.42 (4), p.628-637
• Main Authors: Wessels, Hans-Hermann, Stirn, Andrew, Méndez-Mancilla, Alejandro, Kim, Eric J., Hart, Sydney K., Knowles, David A., Sanjana, Neville E.
• Format: Article
• Language: English
• Subjects: 631/1647/1511; 631/1647/2163; 631/208/191; 631/208/505; 631/61/212/2019; Agriculture; Artificial neural networks; Bioinformatics; Biomedical and Life Sciences; Biomedical Engineering/Biotechnology; Biomedicine; Biotechnology; Context; CRISPR; Datasets; Deep learning; Gene dosage; Gene expression; gRNA; Life Sciences; Machine learning; Neural networks; Ribonucleic acid; RNA; Transcriptomes
• ISSN: 1087-0156; 1546-1696
• DOI: 10.1038/s41587-023-01830-8

Transcriptome engineering applications in living cells with RNA-targeting CRISPR effectors depend on accurate prediction of on-target activity and off-target avoidance. Here we design and test ~200,000 Rfx Cas13d guide RNAs targeting essential genes in human cells with systematically designed mismatches and insertions and deletions (indels). We find that mismatches and indels have a position- and context-dependent impact on Cas13d activity, and mismatches that result in G–U wobble pairings are better tolerated than other single-base mismatches. Using this large-scale dataset, we train a convolutional neural network that we term targeted inhibition of gene expression via gRNA design (TIGER) to predict efficacy from guide sequence and context. TIGER outperforms the existing models at predicting on-target and off-target activity on our dataset and published datasets. We show that TIGER scoring combined with specific mismatches yields the first general framework to modulate transcript expression, enabling the use of RNA-targeting CRISPRs to precisely control gene dosage. A machine learning model predicts on-target and off-target activity of Cas13d in human cells.