Machine Learning Methods for Predicting Guide RNA Effects in CRISPR Epigenome Editing Experiments

Overview

Journal bioRxiv

Date 2024 Apr 25

PMID 38659894

Authors

Wancen Mu

Tianyou Luo

Alejandro Barrera

Lexi R Bounds

Tyler S Klann

Maria Ter Weele

Julien Bryois

Gregory E Crawford

Patrick F Sullivan

Charles A Gersbach

Michael I Love

Yun Li

Affiliations

Soon will be listed here.

Abstract

CRISPR epigenomic editing technologies enable functional interrogation of non-coding elements. However, current computational methods for guide RNA (gRNA) design do not effectively predict the power potential, molecular and cellular impact to optimize for efficient gRNAs, which are crucial for successful applications of these technologies. We present "launch-dCas9" (machine LeArning based UNified CompreHensive framework for CRISPR-dCas9) to predict gRNA impact from multiple perspectives, including cell fitness, wildtype abundance (gauging power potential), and gene expression in single cells. Our launchdCas9, built and evaluated using experiments involving >1 million gRNAs targeted across the human genome, demonstrates relatively high prediction accuracy (AUC up to 0.81) and generalizes across cell lines. Method-prioritized top gRNA(s) are 4.6-fold more likely to exert effects, compared to other gRNAs in the same cis-regulatory region. Furthermore, launchdCas9 identifies the most critical sequence-related features and functional annotations from >40 features considered. Our results establish launch-dCas9 as a promising approach to design gRNAs for CRISPR epigenomic experiments.

References

Kim H, Kim Y, Lee S, Min S, Bae J, Choi J . SpCas9 activity prediction by DeepSpCas9, a deep learning-based model with high generalization performance. Sci Adv. 2019; 5(11):eaax9249. PMC: 6834390. DOI: 10.1126/sciadv.aax9249. View

Xu H, Xiao T, Chen C, Li W, Meyer C, Wu Q . Sequence determinants of improved CRISPR sgRNA design. Genome Res. 2015; 25(8):1147-57. PMC: 4509999. DOI: 10.1101/gr.191452.115. View

Lundberg S, Erion G, Chen H, DeGrave A, Prutkin J, Nair B . From Local Explanations to Global Understanding with Explainable AI for Trees. Nat Mach Intell. 2020; 2(1):56-67. PMC: 7326367. DOI: 10.1038/s42256-019-0138-9. View

Rao S, Huntley M, Durand N, Stamenova E, Bochkov I, Robinson J . A 3D map of the human genome at kilobase resolution reveals principles of chromatin looping. Cell. 2014; 159(7):1665-80. PMC: 5635824. DOI: 10.1016/j.cell.2014.11.021. View

Hsu J, Fulco C, Cole M, Canver M, Pellin D, Sher F . CRISPR-SURF: discovering regulatory elements by deconvolution of CRISPR tiling screen data. Nat Methods. 2018; 15(12):992-993. PMC: 6620603. DOI: 10.1038/s41592-018-0225-6. View

Calo E, Wysocka J . Modification of enhancer chromatin: what, how, and why?. Mol Cell. 2013; 49(5):825-37. PMC: 3857148. DOI: 10.1016/j.molcel.2013.01.038. View

. A comparative genomics multitool for scientific discovery and conservation. Nature. 2020; 587(7833):240-245. PMC: 7759459. DOI: 10.1038/s41586-020-2876-6. View

Calviello A, Hirsekorn A, Wurmus R, Yusuf D, Ohler U . Reproducible inference of transcription factor footprints in ATAC-seq and DNase-seq datasets using protocol-specific bias modeling. Genome Biol. 2019; 20(1):42. PMC: 6385462. DOI: 10.1186/s13059-019-1654-y. View

Chuai G, Ma H, Yan J, Chen M, Hong N, Xue D . DeepCRISPR: optimized CRISPR guide RNA design by deep learning. Genome Biol. 2018; 19(1):80. PMC: 6020378. DOI: 10.1186/s13059-018-1459-4. View

10.

Lazzarotto C, Malinin N, Li Y, Zhang R, Yang Y, Lee G . CHANGE-seq reveals genetic and epigenetic effects on CRISPR-Cas9 genome-wide activity. Nat Biotechnol. 2020; 38(11):1317-1327. PMC: 7652380. DOI: 10.1038/s41587-020-0555-7. View

11.

Muhammad Rafid A, Toufikuzzaman M, Rahman M, Sohel Rahman M . CRISPRpred(SEQ): a sequence-based method for sgRNA on target activity prediction using traditional machine learning. BMC Bioinformatics. 2020; 21(1):223. PMC: 7268231. DOI: 10.1186/s12859-020-3531-9. View

12.

Liao Y, Smyth G, Shi W . The R package Rsubread is easier, faster, cheaper and better for alignment and quantification of RNA sequencing reads. Nucleic Acids Res. 2019; 47(8):e47. PMC: 6486549. DOI: 10.1093/nar/gkz114. View

13.

Yu G, Wang L, He Q . ChIPseeker: an R/Bioconductor package for ChIP peak annotation, comparison and visualization. Bioinformatics. 2015; 31(14):2382-3. DOI: 10.1093/bioinformatics/btv145. View

14.

Ghisletti S, Barozzi I, Mietton F, Polletti S, De Santa F, Venturini E . Identification and characterization of enhancers controlling the inflammatory gene expression program in macrophages. Immunity. 2010; 32(3):317-28. DOI: 10.1016/j.immuni.2010.02.008. View

15.

Sur I, Taipale J . The role of enhancers in cancer. Nat Rev Cancer. 2016; 16(8):483-93. DOI: 10.1038/nrc.2016.62. View

16.

Hiranniramol K, Chen Y, Liu W, Wang X . Generalizable sgRNA design for improved CRISPR/Cas9 editing efficiency. Bioinformatics. 2020; 36(9):2684-2689. PMC: 7203743. DOI: 10.1093/bioinformatics/btaa041. View

17.

DeWeirdt P, Sanson K, Sangree A, Hegde M, Hanna R, Feeley M . Optimization of AsCas12a for combinatorial genetic screens in human cells. Nat Biotechnol. 2020; 39(1):94-104. PMC: 7854777. DOI: 10.1038/s41587-020-0600-6. View

18.

Finak G, McDavid A, Yajima M, Deng J, Gersuk V, Shalek A . MAST: a flexible statistical framework for assessing transcriptional changes and characterizing heterogeneity in single-cell RNA sequencing data. Genome Biol. 2015; 16:278. PMC: 4676162. DOI: 10.1186/s13059-015-0844-5. View

19.

Creyghton M, Cheng A, Welstead G, Kooistra T, Carey B, Steine E . Histone H3K27ac separates active from poised enhancers and predicts developmental state. Proc Natl Acad Sci U S A. 2010; 107(50):21931-6. PMC: 3003124. DOI: 10.1073/pnas.1016071107. View

20.

Konstantakos V, Nentidis A, Krithara A, Paliouras G . CRISPR-Cas9 gRNA efficiency prediction: an overview of predictive tools and the role of deep learning. Nucleic Acids Res. 2022; 50(7):3616-3637. PMC: 9023298. DOI: 10.1093/nar/gkac192. View