crispr2vec: Machine Learning Model Predicts Off-Target Cuts of CRISPR systems

Abstract

1Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR)/CRISPR-Cas systems have revolutionized gene editing, with applications in therapeutics, diagnostics, agriculture, and developing disease models. However, CRISPR-Cas suffers from off-target effects -- unintended genetic modifications in the genome that arise from its use. In this work, we present crispr2vec: a deep metric learning approach for embedding CRISPR single guide RNA (sgRNA) sequences and predicting off-target cuts. Given a fixed target sequence, we show that our learned embedding yields a faithful representation of potential off-targets. We present a new triplet sampling strategy specifically for CRISPR sequences that improves the quality of our embedding. We show the resulting embedding generalizes across different off-target cut detection assays. Finally, we demonstrate the superiority of our deep metric learning method in its ability to predict off-target cuts compared to previous literature in cross fold validation across different datasets for both seen and unseen sgRNAs.