Genome-wide functional screens enable the prediction of high activity CRISPR-Cas9 and -Cas12a guides in Yarrowia lipolytica

Genome-wide functional genetic screens have been successful in discovering genotype-phenotype relations and in engineering new phenotypes. While broadly applied in mammalian cell lines and in E. coli, use in non-conventional microorganisms has been limited, in part, due to the inability to accurately design high activity CRISPR guides in such species. Here, we develop an integrated experimental-computational approach to sgRNA design that is specific to an organism of choice, in this case applied to the oleaginous yeast Yarrowia lipolytica. Genome-wide single guide RNA (sgRNA) activity profiles were generated and used as input to a deep learning algorithm, DeepGuide, that is able to accurately predict guide activity for both SpCas9 and LbCas12a. DeepGuide first uses unsupervised learning to obtain a compressed representation of the genome, followed by supervised learning to map sgRNA sequence, genomic context, and epigenetic features with guide activity. Experimental validation, both genome-wide and with a subset of selected genes, confirms DeepGuide's ability to accurately predict high activity sgRNAs. DeepGuide provides an organism specific predictor of CRISPR guide activity that could be broadly applied to fungal species, prokaryotes, and other non-conventional organisms.