RT Journal Article
SR Electronic
T1 CASowary: CRISPR-Cas13 guide RNA predictor for transcript depletion
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2021.07.26.453663
DO 10.1101/2021.07.26.453663
A1 Alexander Krohannon
A1 Mansi Srivastava
A1 Simone Rauch
A1 Rajneesh Srivastava
A1 Bryan C. Dickinson
A1 Sarath Chandra Janga
YR 2021
UL http://biorxiv.org/content/early/2021/07/27/2021.07.26.453663.abstract
AB Recent discovery of the gene editing system -CRISPR (Clustered Regularly Interspersed Short Palindromic Repeats) associated proteins (Cas), has resulted in its widespread use for improved understanding of a variety of biological systems. Cas13, a lesser studied Cas protein, has been repurposed to allow for efficient and precise editing of RNA molecules. The Cas13 system utilizes base complementarity between a crRNA/sgRNA (crispr RNA or single guide RNA) and a target RNA transcript, to preferentially bind to only the target transcript. Unlike targeting the upstream regulatory regions of protein coding genes on the genome, the transcriptome is significantly more redundant, leading to many transcripts having wide stretches of identical nucleotide sequences. Transcripts also exhibit complex three-dimensional structures and interact with an array of RBPs (RNA Binding Proteins), both of which further limit the scope of effective target sequences. As a result, there currently exists no method to predict whether a specific sgRNA will effectively knockdown a transcript. Here we present a novel machine learning and computational tool, CASowary, to predict the efficacy of a sgRNA. We used publicly available RNA knockdown data from Cas13 characterization experiments for 555 sgRNAs targeting the transcriptome in HEK293 cells, in conjunction with transcriptome-wide protein occupancy information on RNA. Our model utilizes a Decision Tree architecture with a set of 112 sequence and target availability features, to classify sgRNA efficacy into one of four classes, based upon expected level of target transcript knockdown. After accounting for noise in the training data set, the noise-normalized accuracy exceeds 70%. Additionally, highly effective sgRNA predictions have been experimentally validated using an independent RNA targeting Cas system -CIRTS, confirming the robustness and reproducibility of our model’s sgRNA predictions. Utilizing transcriptome wide protein occupancy map generated using POP-seq in Hela cells against publicly available protein-RNA interaction map in Hek293 cells, we show that CASowary can predict high quality guides for numerous transcripts in a cell line specific manner. Application of CASowary to whole transcriptomes should enable rapid deployment of CRISPR/Cas13 systems, facilitating the development of therapeutic interventions linked with aberrations in RNA regulatory processes.Competing Interest StatementThe authors have declared no competing interest.AUCArea Under the CurveCasCRISPR associatedcDNAcomplementary DNACIRTSCRISPR-Cas-Inspired RNA Targeting SystemCRISPRClustered Regularly Interspersed Short Palindromic RepeatscrRNAcrispr RNADNADeoxyRibonucleic AcidGEOGene Expression OmnibusIDTIntegrated DNA TechnologiesIGVIntegrative Genomics ViewerlncRNAlong non-coding RNAncRNAnon-coding RNANIHNational Institute of HealthPAMProtospacer Adjacent MotifPOP-seqProtein Occupancy Profile sequencingRBPRNA Binding ProtienROCReceiver Operator CurvesgRNAsingle guide RNA