DropLasso: A robust variant of Lasso for single cell RNA-seq data
This addresses the challenge of classifying individual cells in scRNA-seq data, which is incremental as it adapts existing regularization techniques to a specific noisy data type.
The paper tackles the problem of learning molecular signatures from noisy single-cell RNA-seq data with dropout events, proposing DropLasso as a robust variant of Lasso that extends dropout regularization to sparse linear models, showing promising results on simulated and real data.
Single-cell RNA sequencing (scRNA-seq) is a fast growing approach to measure the genome-wide transcriptome of many individual cells in parallel, but results in noisy data with many dropout events. Existing methods to learn molecular signatures from bulk transcriptomic data may therefore not be adapted to scRNA-seq data, in order to automatically classify individual cells into predefined classes. We propose a new method called DropLasso to learn a molecular signature from scRNA-seq data. DropLasso extends the dropout regularisation technique, popular in neural network training, to esti- mate sparse linear models. It is well adapted to data corrupted by dropout noise, such as scRNA-seq data, and we clarify how it relates to elastic net regularisation. We provide promising results on simulated and real scRNA-seq data, suggesting that DropLasso may be better adapted than standard regularisa- tions to infer molecular signatures from scRNA-seq data.