Bogdan Kirillov, Ekaterina Savitskaya (passed away in 2019), Maxim Panov and Konstantin Severinov from Skoltech co-authored a recent paper “Uncertainty-aware and interpretable evaluation of Cas9–gRNA and Cas12a–gRNA specificity for fully matched and partially mismatched targets with Deep Kernel Learning” that has been published in Nucleic Acids Research. The scientists developed method, a hybrid of Capsule Networks and Gaussian Processes that predicts the cleavage efficiency of a gRNA with a corresponding confidence interval, which allows the user to incorporate information regarding possible model errors into the experimental design. The researchers provide the first utilization of uncertainty estimation in computational gRNA design. They introduce a set of criteria for gRNA selection based on off-target cleavage efficiency and its variance and present a collection of pre-computed gRNAs for human chromosome 22. The authors show that the model rediscovers an established biological factor underlying cleavage efficiency, the importance of the seed region in gRNA. Full text of the paper is available here.