Unsupervised feature construction and knowledge extraction from genome-wide assays of breast cancer with denoising autoencoders

Abstract

Big data bring new opportunities for methods that efficiently summarize and automatically extract knowledge from such compendia. While both supervised learning algorithms and unsupervised clustering algorithms have been successfully applied to biological data, they are either dependent on known biology or limited to discerning the most significant signals in the data. Here we present denoising autoencoders (DAs), which employ a data-defined learning objective independent of known biology, as a method to identify and extract complex patterns from genomic data. We evaluate the performance of DAs by applying them to a large collection of breast cancer gene expression data. Results show that DAs successfully construct features that contain both clinical and molecular information. There are features that represent tumor or normal samples, estrogen receptor (ER) status, and molecular subtypes. Features constructed by the autoencoder generalize to an independent dataset collected using a distinct experimental platform. By integrating data from ENCODE for feature interpretation, we discover a feature representing ER status through association with key transcription factors in breast cancer. We also identify a feature highly predictive of patient survival and it is enriched by FOXM1 signaling pathway. The features constructed by DAs are often bimodally distributed with one peak near zero and another near one, which facilitates discretization. In summary, we demonstrate that DAs effectively extract key biological principles from gene expression data and summarize them into constructed features with convenient properties.

Fig. 1

A) The network structure of denoising autoencoders. B) The distribution of one node's weight vector. C) The distribution of activity values for a node are bimodally distributed. Here we use Node5 as an example.

Fig. 2

Kaplan-Meier plots of disease-specific survival for Node5 (A), ER status (B), Luminal A subtype (C), and Tumor Grade (D) demonstrate that the constructed feature outperforms the other predictors.