scMAGeCK links genotypes with multiple phenotypes in single-cell CRISPR screens

Abstract

We present scMAGeCK, a computational framework to identify genomic elements associated with multiple expression-based phenotypes in CRISPR/Cas9 functional screening that uses single-cell RNA-seq as readout. scMAGeCK outperforms existing methods, identifies genes and enhancers with known and novel functions in cell proliferation, and enables an unbiased construction of genotype-phenotype network. Single-cell CRISPR screening on mouse embryonic stem cells identifies key genes associated with different pluripotency states. Applying scMAGeCK on multiple datasets, we identify key factors that improve the power of single-cell CRISPR screening. Collectively, scMAGeCK is a novel tool to study genotype-phenotype relationships at a single-cell level.

Machine learning for single cell genomics data analysis

“…Several ML approaches have been developed for that purpose, for instance by characterizing cells across measurements, projecting multiple measurements into a common latent space or learning the missing modalities. Transcriptomics is typically one of the modalities that is integrated, together with chromatin accessibility [69, 52, 70], DNA [71], DNA methylation [72, 52], proteomic data [73, 74, 69, 75, 76] or CRISPR perturbations [77 • , 78].…”

“…Among models that do not require co-assay data, some use weak supervision such as SCIM [72], an adversarial AE model that assumes that the cell types are known for a fraction of the cells and Seurat v3 [52], a canonical correlation analysis (CCA)-based model that relies on building anchor cells using mutual nearest neighbours. Applied to single-cell CRISPR screenings, scMAGeCK [78] relies on statistical analyses and MUSIC [77 • ] on topic modeling in order to link gene perturbations to cell phenotype. Finally, it is worth mentioning that some models require features to have a one-to-one correspondence between views [71, 52, 75, 77 • , 78], which may not be the case systematically.…”

“…Applied to single-cell CRISPR screenings, scMAGeCK [78] relies on statistical analyses and MUSIC [77 • ] on topic modeling in order to link gene perturbations to cell phenotype. Finally, it is worth mentioning that some models require features to have a one-to-one correspondence between views [71, 52, 75, 77 • , 78], which may not be the case systematically.…”

Conditional resampling improves calibration and sensitivity in single-cell CRISPR screen analysis

“…We also simulated negative control gRNA data using a logistic regression model with the same covariates as the gene expression model. We assessed the calibration of three methods across the four simulated datasets: SCEPTRE, improved negative binomial regression, and scMAGeCK-LR 12 , a recently-proposed, permutation-based nonparametric method. To assess the impact of model misspecification on SCEPTRE and the improved negative binomial method (on which SCEPTRE relies), we fixed the dispersion of the negative binomial method to 1 across all four simulated datasets.…”

In silico Method in CRISPR/Cas System: An Expedite and Powerful Booster

“…MAGeCK-RRA ( 147 ) based on the negative binomial model and robust rank aggregation (RRA) is the first tool customized for prioritizing gRNAs, performing gene-level ranking and identifying the enriched pathways. To extend the functions, MAGeCK-RRA ( 147 ) was further updated to scMAGeCK ( 148 ) for single-cell CRISPR screening (a novel technique combining pooled CRISPR screening with single-cell RNA-seq, which enables the identification of gRNAs at single-cell resolution from sequencing by modifying the lentiviral vector) and MAGeCKFlute ( 137 ) with optional ranking algorithm (maximum likelihood estimation) ( 149 ), gRNA outlier removal by network essentiality scoring tool ( 150 ), and various accessory functions including upstream quality control and downstream visualization. For some novices without programming expertise, command-line programs are hard to tame and the graphical workflow, ENCoRE ( 141 ), seems more user-friendly, whereas the rough processing of gene ranking may induce unreliable results.…”