Multimodal Modeling of CRISPR-Cas12 Activity Using Foundation Models and Chromatin Accessibility Data

TL;DR

This paper demonstrates that pre-trained biological foundation models combined with chromatin accessibility data significantly improve the prediction of guide RNA activity in CRISPR-Cas12 genome editing, addressing data scarcity and variability issues.

Contribution

It introduces a novel approach using embeddings from a pre-trained transcriptomic foundation model and chromatin accessibility data to enhance gRNA activity prediction.

Findings

Pre-trained foundation model embeddings improve prediction accuracy.

Chromatin accessibility data further enhances model performance.

Lightweight regressors with these inputs outperform traditional methods.

Abstract

Predicting guide RNA (gRNA) activity is critical for effective CRISPR-Cas12 genome editing but remains challenging due to limited data, variation across protospacer adjacent motifs (PAMs-short sequence requirements for Cas binding), and reliance on large-scale training. We investigate whether pre-trained biological foundation model originally trained on transcriptomic data can improve gRNA activity estimation even without domain-specific pre-training. Using embeddings from existing RNA foundation model as input to lightweight regressor, we show substantial gains over traditional baselines. We also integrate chromatin accessibility data to capture regulatory context, improving performance further. Our results highlight the effectiveness of pre-trained foundation models and chromatin accessibility data for gRNA activity prediction.