Distinguishing between Normal and Cancer Cells Using Autoencoder Node Saliency

TL;DR

This paper introduces an autoencoder-based approach with a novel node saliency measure to distinguish normal from cancer cells using gene expression data, demonstrating effective feature extraction and classification.

Contribution

It presents a scalable deep learning autoencoder trained on large cancer datasets and introduces autoencoder node saliency for cell type differentiation.

Findings

Autoencoder captures nonlinear gene expression relationships.

Autoencoder node saliency identifies key differentiating nodes.

Method outperforms PCA and t-SNE in feature extraction.

Abstract

Gene expression profiles have been widely used to characterize patterns of cellular responses to diseases. As data becomes available, scalable learning toolkits become essential to processing large datasets using deep learning models to model complex biological processes. We present an autoencoder to capture nonlinear relationships recovered from gene expression profiles. The autoencoder is a nonlinear dimension reduction technique using an artificial neural network, which learns hidden representations of unlabeled data. We train the autoencoder on a large collection of tumor samples from the National Cancer Institute Genomic Data Commons, and obtain a generalized and unsupervised latent representation. We leverage a HPC-focused deep learning toolkit, Livermore Big Artificial Neural Network (LBANN) to efficiently parallelize the training algorithm, reducing computation times from several hours to a few minutes. With the trained autoencoder, we generate latent representations of a small dataset, containing pairs of normal and cancer cells of various tumor types. A novel measure called autoencoder node saliency (ANS) is introduced to identify the hidden nodes that best differentiate various pairs of cells. We compare our findings of the best classifying nodes with principal component analysis and the visualization of t-distributed stochastic neighbor embedding. We demonstrate that the autoencoder effectively extracts distinct gene features for multiple learning tasks in the dataset.