Double-Jeopardy: scRNA-seq Doublet/Multiplet Detection Using Multi-Omic Profiling

The computational detection and exclusion of cellular doublets/multiplets is a cornerstone for the identification the true biological signals from single-cell RNAseq (scRNA-seq) data. Current methods do not sensitively identify both heterotypic and homotypic doublets/multiplets. Here, we describe a novel machine learning approach for doublet/multiplet detection utilising VDJ-seq and/or CITE-seq information to predict their presence based on transcriptional features associated with identified hybrid droplets. Our method has high sensitivity and specificity, thus presenting a powerful, generalisable approach to ensuring high quality scRNA-seq data.