N-ACT: An Interpretable Deep Learning Model for Automatic Cell Type and Salient Gene Identification
This addresses the need for interpretable models in bioinformatics for researchers analyzing cellular composition, though it is incremental as it builds on existing deep learning frameworks by adding interpretability.
The paper tackled the problem of interpretability in automatic cell type identification from single-cell RNA sequencing data by introducing N-ACT, an interpretable deep learning model that uses neural-attention to detect salient genes, achieving comparable performance to state-of-the-art supervised methods on multiple datasets.
Single-cell RNA sequencing (scRNAseq) is rapidly advancing our understanding of cellular composition within complex tissues and organisms. A major limitation in most scRNAseq analysis pipelines is the reliance on manual annotations to determine cell identities, which are time consuming, subjective, and require expertise. Given the surge in cell sequencing, supervised methods-especially deep learning models-have been developed for automatic cell type identification (ACTI), which achieve high accuracy and scalability. However, all existing deep learning frameworks for ACTI lack interpretability and are used as "black-box" models. We present N-ACT (Neural-Attention for Cell Type identification): the first-of-its-kind interpretable deep neural network for ACTI utilizing neural-attention to detect salient genes for use in cell-type identification. We compare N-ACT to conventional annotation methods on two previously manually annotated data sets, demonstrating that N-ACT accurately identifies marker genes and cell types in an unsupervised manner, while performing comparably on multiple data sets to current state-of-the-art model in traditional supervised ACTI.