Dates: 2023
Principal Investigator: Dr. Van Dinh Tran
Funded by: SDAIA-KFUPM Joint Research Center for Artificial Intelligence                                                              Description: This project addresses the safety concerns of CRISPR-Cas genome editing, particularly the challenge of off-target effects where unintended sites are modified. While existing machine learning methods predict off-target sites with some success, they mainly focus on PAM-adjacent sequences of fixed length, ignoring broader sequence context and protein information. To overcome these limitations, the project proposes CrisprCPA, a novel transformer-based model that integrates sequence context, epigenetics, and protein information, and leverages transfer learning across CRISPR systems, cell types, and species. The model’s performance will be rigorously evaluated against state-of-the-art methods using diverse datasets, aiming to improve the accuracy and reliability of off-target prediction.