Modeling the off-target effects of CRISPR-Cas9 experiments for the treatment of Duchenne Muscular Dystrophy

Duchenne Muscular Dystrophy (DMD) is a neuromuscular disorder caused by the absence of the dystrophin protein. If left untreated, it causes movement problems at the age of 10-12 years, and death occurs in the 20-30 years due to heart failure. There is currently no cure for this disease, only symptomatic treatment. Genome editing approaches like the CRISPR-Cas9 technology can provide new opportunities to ameliorate the disease by eliminating DMD mutations and restoring dystrophin expression. While it is true that on-target activity can be influenced by the guide specificity, the proposed approach focuses on the devastating results that off-target cleavage can cause (e.g., unexpected mutations). This is why reducing off-target effects is the first priority in guide design. The rapid growth of the Artificial Intelligence field has helped researchers employ artificial feature extraction and Machine Learning approaches to evaluate the potential off-target scores. This work presents our approach in evaluating off-targets of CRISPR-Cas9 gene editing specifically for the DMD disorder, using Machine Learning. We offer a comparison between four regression methods that predict the insertions-deletions (indels) produced based on a pair guide RNA and the equivalent off-target and evaluate the results using the Spearman correlation metric. We propose the most suitable method, a Decision Tree Regressor, for this problem and a comparison of the results with some state-of-art tools. The performance of our tool with Cross Validation is better than the independent performance of the other tools except from Elevation which performed about as good as ours.