Deep learning and CRISPR-Cas13d ortholog discovery for optimized RNA targeting

Jingyi Wei; Peter Lotfy; Kian Faizi; Sara Baungaard; Emily Gibson; Eleanor Wang; Hannah Slabodkin; Emily Kinnaman; Sita Chandrasekaran; Hugo Kitano; Matthew G Durrant; Connor V Duffy; April Pawluk; Patrick D Hsu; Silvana Konermann

doi:10.1016/j.cels.2023.11.006

Deep learning and CRISPR-Cas13d ortholog discovery for optimized RNA targeting

Cell Syst. 2023 Dec 20;14(12):1087-1102.e13. doi: 10.1016/j.cels.2023.11.006. Epub 2023 Dec 12.

Authors

Affiliations

¹ Department of Bioengineering, Stanford University, Stanford, CA, USA; Department of Biochemistry, Stanford University, Stanford, CA, USA; Arc Institute, Palo Alto, CA, USA.
² Laboratory of Molecular and Cell Biology, Salk Institute for Biological Studies, La Jolla, CA, USA.
³ Arc Institute, Palo Alto, CA, USA.
⁴ Laboratory of Molecular and Cell Biology, Salk Institute for Biological Studies, La Jolla, CA, USA; Department of Bioengineering, University of California, Berkeley, Berkeley, CA, USA; Innovative Genomics Institute, University of California, Berkeley, Berkeley, CA, USA.
⁵ Department of Biochemistry, Stanford University, Stanford, CA, USA; Arc Institute, Palo Alto, CA, USA.
⁶ Arc Institute, Palo Alto, CA, USA; Department of Bioengineering, University of California, Berkeley, Berkeley, CA, USA; Innovative Genomics Institute, University of California, Berkeley, Berkeley, CA, USA.
⁷ Department of Computer Science, Stanford University, Stanford, CA, USA.
⁸ Arc Institute, Palo Alto, CA, USA; Department of Genetics, Stanford University, Stanford, CA, USA.
⁹ Arc Institute, Palo Alto, CA, USA; Department of Bioengineering, University of California, Berkeley, Berkeley, CA, USA; Innovative Genomics Institute, University of California, Berkeley, Berkeley, CA, USA. Electronic address: patrick@arcinstitute.org.
¹⁰ Department of Biochemistry, Stanford University, Stanford, CA, USA; Arc Institute, Palo Alto, CA, USA. Electronic address: silvana@arcinstitute.org.

PMID: 38091991
DOI: 10.1016/j.cels.2023.11.006

Abstract

Effective and precise mammalian transcriptome engineering technologies are needed to accelerate biological discovery and RNA therapeutics. Despite the promise of programmable CRISPR-Cas13 ribonucleases, their utility has been hampered by an incomplete understanding of guide RNA design rules and cellular toxicity resulting from off-target or collateral RNA cleavage. Here, we quantified the performance of over 127,000 RfxCas13d (CasRx) guide RNAs and systematically evaluated seven machine learning models to build a guide efficiency prediction algorithm orthogonally validated across multiple human cell types. Deep learning model interpretation revealed preferred sequence motifs and secondary features for highly efficient guides. We next identified and screened 46 novel Cas13d orthologs, finding that DjCas13d achieves low cellular toxicity and high specificity-even when targeting abundant transcripts in sensitive cell types, including stem cells and neurons. Our Cas13d guide efficiency model was successfully generalized to DjCas13d, illustrating the power of combining machine learning with ortholog discovery to advance RNA targeting in human cells.

Publication types

Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't

MeSH terms

CRISPR-Cas Systems* / genetics
Deep Learning*
Humans
RNA* / genetics
RNA, Guide, CRISPR-Cas Systems
Transcriptome

Substances

RNA
RNA, Guide, CRISPR-Cas Systems

Abstract

Publication types

MeSH terms

Substances

Grants and funding