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

被引：18

作者：

Wei, Jingyi ^{[1
,2
,3
]}

Lotfy, Peter ^{[4
]}

Faizi, Kian ^{[4
]}

Baungaard, Sara ^{[2
]}

Gibson, Emily ^{[3
]}

Wang, Eleanor ^{[4
,5
]}

Slabodkin, Hannah ^{[2
,3
]}

Kinnaman, Emily ^{[2
,3
]}

Chandrasekaran, Sita ^{[3
,5
,6
]}

Kitano, Hugo ^{[7
]}

Durrant, Matthew G. ^{[3
,5
,6
]}

Duffy, Connor, V ^{[3
,8
]}

Pawluk, April ^{[3
]}

Hsu, Patrick D. ^{[3
,5
]}

Konermann, Silvana ^{[2
,3
]}

机构：

[1] Stanford Univ, Dept Bioengn, Stanford, CA USA

[2] Stanford Univ, Dept Biochem, Stanford, CA 94305 USA

[3] Arc Inst, Palo Alto, CA 94304 USA

[4] Salk Inst Biol Studies, Lab Mol & Cell Biol, La Jolla, CA USA

[5] Univ Calif Berkeley, Dept Bioengn, Berkeley, CA 94720 USA

[6] Univ Calif Berkeley, Innovat Genom Inst, Berkeley, CA USA

[7] Stanford Univ, Dept Comp Sci, Stanford, CA USA

[8] Stanford Univ, Dept Genet, Stanford, CA USA

来源：

CELL SYSTEMS | 2023年 / 14卷 / 12期

关键词：

PREDICTION; GENOME;

D O I：

10.1016/j.cels.2023.11.006

中图分类号：

Q5 [生物化学]; Q7 [分子生物学];

学科分类号：

071010 ; 081704 ;

摘要：

Effective and precise mammalian transcriptome engineering technologies are needed to accelerate biolog-ical 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 tar-geting in human cells.

引用

页码：1087 / 1102.e13

页数：30