A generalizable Cas9/sgRNA prediction model using machine transfer learning with small high-quality datasets

• Published in: Nature communications Vol. 14; no. 1; p. 5514
• Main Authors: Ham, Dalton T., Browne, Tyler S., Banglorewala, Pooja N., Wilson, Tyler L., Michael, Richard K., Gloor, Gregory B., Edgell, David R.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 07.09.2023; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/2397; 631/326/4041/3196; Accuracy; Antimicrobial agents; Bacteria; Cleavage; CRISPR; Datasets; Genome editing; Genomes; Humanities and Social Sciences; Learning algorithms; Machine learning; multidisciplinary; Nuclease; Nucleotide sequence; Positive selection; Prediction models; Science; Science (multidisciplinary); Toxicity; Transfer learning
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-023-41143-7

The CRISPR/Cas9 nuclease from Streptococcus pyogenes (SpCas9) can be used with single guide RNAs (sgRNAs) as a sequence-specific antimicrobial agent and as a genome-engineering tool. However, current bacterial sgRNA activity models struggle with accurate predictions and do not generalize well, possibly because the underlying datasets used to train the models do not accurately measure SpCas9/sgRNA activity and cannot distinguish on-target cleavage from toxicity. Here, we solve this problem by using a two-plasmid positive selection system to generate high-quality data that more accurately reports on SpCas9/sgRNA cleavage and that separates activity from toxicity. We develop a machine learning architecture (crisprHAL) that can be trained on existing datasets, that shows marked improvements in sgRNA activity prediction accuracy when transfer learning is used with small amounts of high-quality data, and that can generalize predictions to different bacteria. The crisprHAL model recapitulates known SpCas9/sgRNA-target DNA interactions and provides a pathway to a generalizable sgRNA bacterial activity prediction tool that will enable accurate antimicrobial and genome engineering applications. Current bacterial sgRNA activity models struggle with accurate predictions and generalizations. Here the authors report crisprHAL, a machine learning architecture that can be trained on existing datasets, and shows good sgRNA activity prediction accuracy can generalize predictions to different bacteria.