ScRAE: Deterministic Regularized Autoencoders with Flexible Priors for Clustering Single-cell Gene Expression Data

TL;DR

This paper introduces scRAE, a deterministic autoencoder with a learnable prior, designed to improve clustering of high-dimensional, sparse single-cell gene expression data by better balancing bias and variance.

Contribution

The paper proposes a novel deterministic autoencoder framework with a flexible prior generator for enhanced clustering of scRNA-seq data, addressing bias-variance trade-offs in regularized autoencoders.

Findings

scRAE outperforms existing methods on real-world datasets

The learnable prior improves clustering accuracy

The approach effectively balances bias and variance

Abstract

Clustering single-cell RNA sequence (scRNA-seq) data poses statistical and computational challenges due to their high-dimensionality and data-sparsity, also known as `dropout' events. Recently, Regularized Auto-Encoder (RAE) based deep neural network models have achieved remarkable success in learning robust low-dimensional representations. The basic idea in RAEs is to learn a non-linear mapping from the high-dimensional data space to a low-dimensional latent space and vice-versa, simultaneously imposing a distributional prior on the latent space, which brings in a regularization effect. This paper argues that RAEs suffer from the infamous problem of bias-variance trade-off in their naive formulation. While a simple AE without a latent regularization results in data over-fitting, a very strong prior leads to under-representation and thus bad clustering. To address the above issues, we propose a modified RAE framework (called the scRAE) for effective clustering of the single-cell RNA sequencing data. scRAE consists of deterministic AE with a flexibly learnable prior generator network, which is jointly trained with the AE. This facilitates scRAE to trade-off better between the bias and variance in the latent space. We demonstrate the efficacy of the proposed method through extensive experimentation on several real-world single-cell Gene expression datasets.