Determinants of Base Editing Outcomes from Target Library Analysis and Machine Learning

• Published in: Cell Vol. 182; no. 2; pp. 463 - 480.e30
• Main Authors: Arbab, Mandana, Shen, Max W., Mok, Beverly, Wilson, Christopher, Matuszek, Żaneta, Cassa, Christopher A., Liu, David R.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 23.07.2020
• Subjects: adenine; alleles; Animals; artificial intelligence; base editing; cytosine; disease correction; Gene Editing - methods; Gene Library; Humans; Machine Learning; mammals; Mice; Mouse Embryonic Stem Cells - cytology; Mouse Embryonic Stem Cells - metabolism; nucleotides; Point Mutation; precision genome editing; RNA, Guide, CRISPR-Cas Systems; transversion base editing; transversion base editing; machine learning; base editing; disease correction; precision genome editing
• ISSN: 0092-8674; 1097-4172; 1097-4172
• DOI: 10.1016/j.cell.2020.05.037

Although base editors are widely used to install targeted point mutations, the factors that determine base editing outcomes are not well understood. We characterized sequence-activity relationships of 11 cytosine and adenine base editors (CBEs and ABEs) on 38,538 genomically integrated targets in mammalian cells and used the resulting outcomes to train BE-Hive, a machine learning model that accurately predicts base editing genotypic outcomes (R ≈ 0.9) and efficiency (R ≈ 0.7). We corrected 3,388 disease-associated SNVs with ≥90% precision, including 675 alleles with bystander nucleotides that BE-Hive correctly predicted would not be edited. We discovered determinants of previously unpredictable C-to-G, or C-to-A editing and used these discoveries to correct coding sequences of 174 pathogenic transversion SNVs with ≥90% precision. Finally, we used insights from BE-Hive to engineer novel CBE variants that modulate editing outcomes. These discoveries illuminate base editing, enable editing at previously intractable targets, and provide new base editors with improved editing capabilities. [Display omitted] •Base editing outcome precision and efficiency are frequently unintuitive•Machine learning model (BE-Hive) accurately predicts base editing efficiency and editing patterns•Base editor engineering can increase and reduce aberrant transversion editing•We precisely correct 3,388 pathogenic SNVs, many previously considered intractable A comprehensive look at CRISPR base editing efficiencies and outcomes across target sequences, cell lines, and base editing effectors yields machine learning models and a web-based tool for users to predict the editing efficiency, bystander edits, and the best base editor to use for a sequence of interest.