Multimodal Modeling of CRISPR-Cas12 Activity Using Foundation Models and Chromatin Accessibility Data
By: Azim Dehghani Amirabad , Yanfei Zhang , Artem Moskalev and more
Potential Business Impact:
Helps gene editing tools work better and faster.
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.
Similar Papers
Artificial Intelligence for CRISPR Guide RNA Design: Explainable Models and Off-Target Safety
Quantitative Methods
AI helps gene editing tools work better and safer.
ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibility Data
Genomics
Finds hidden gene links to understand diseases.
Integrating Single-Cell Foundation Models with Graph Neural Networks for Drug Response Prediction
Machine Learning (CS)
Helps pick the best medicine for sick cells.