Consensus Label Propagation with Graph Convolutional Networks for Single-Cell RNA Sequencing Cell Type Annotation

Daniel Phillip Lewinsohn, Donald F Conrad, Cory Braker Scott

Keywords: GNN, Ensemble Models, scRNA-seq, Bioinformatics, Label Propagation

Abstract: Single-cell RNA sequencing (scRNA-seq) data, annotated by cell type, is useful in a variety of downstream biological applications, such as profiling gene expression at the single-cell level. However, manually assigning these annotations with known marker genes is both time-consuming and subjective. We present a Graph Convolutional Network (GCN) based approach to automate the annotation process. Our process builds upon existing labeling approaches, using state-of-the-art tools to find highly-confident cells through consensus and spreading these confident labels with a semi-supervised GCN. Using simulated data and two scRNA-seq data sets from different tissues, we show that our method improves accuracy over a simple consensus algorithm and the average of the underlying tools. We also demonstrate that our GCN method allows for feature interpretation, revealing important genes for cell type classification. We present our completed pipeline, written in Pytorch, as an end-to-end tool for automating and interpreting the classification of scRNA-seq data.

Type Of Submission: Extended abstract (max 4 main pages).

Agreement: Check this if you are okay with being contacted to participate in an anonymous survey.

TL;DR: We show that using a Graph Convolutional Network we can propagate confident labels to all cells in a data set of single-cell RNA sequencing data. Our model outperforms all underlying models in the ensemble as well as the consensus of those models.

Type Of Submission: Extended abstract.

Software: https://github.com/lewinsohndp/scSHARP