# Risk Prediction of RNA Off-Targets of CRISPR Base Editors in Tissue-Specific Transcriptomes Using Language Models

## TL;DR

This study introduces a new pipeline and machine learning models to predict RNA off-target effects of CRISPR base editors in tissue-specific transcriptomes, improving safety assessments for genome editing.

## Contribution

A novel computational pipeline (PiCTURE) and machine learning models (STL and SNL) for detecting RNA off-targets of CRISPR base editors with higher accuracy than existing methods.

## Key findings

- PiCTURE identifies both canonical and non-canonical RNA off-targets, revealing a broader WCW motif.
- STL and SNL models outperformed motif-only approaches in accuracy, precision, recall, and F1 score.
- Tissue-specific analysis showed higher RNA off-target risk in colon and lungs compared to brain and ovaries.

## Abstract

Base-editing technologies, particularly cytosine base editors (CBEs), allow precise gene modification without introducing double-strand breaks; however, unintended RNA off-target effects remain a critical concern and are under studied. To address this gap, we developed the Pipeline for CRISPR-induced Transcriptome-wide Unintended RNA Editing (PiCTURE), a standardized computational pipeline for detecting and quantifying transcriptome-wide CBE-induced RNA off-target events. PiCTURE identifies both canonical ACW (W = A or T/U) motif-dependent and non-canonical RNA off-targets, revealing a broader WCW motif that underlies many unanticipated edits. Additionally, we developed two machine learning models based on the DNABERT-2 language model, termed STL and SNL, which outperformed motif-only approaches in terms of accuracy, precision, recall, and F1 score. To demonstrate the practical application of our predictive model for CBE-induced RNA off-target risk, we integrated PiCTURE outputs with the Predicting RNA Off-target compared with Tissue-specific Expression for Caring for Tissue and Organ (PROTECTiO) pipeline and estimated RNA off-target risk for each transcript showing tissue-specific expression. The analysis revealed differences among tissues: while the brain and ovaries exhibited relatively low off-target burden, the colon and lungs displayed relatively high risks. Our study provides a comprehensive framework for RNA off-target profiling, emphasizing the importance of advanced machine learning-based classifiers in CBE safety evaluations and offering valuable insights to inform the development of safer genome-editing therapies.