DeepTRIAGE: Interpretable and Individualised BiomarkerScores using Attention Mechanism for the Classification of Breast Cancer Sub-types

Abstract

MotivationBreast cancer is a collection of multiple tissue pathologies, each with a distinct molecular signature that correlates with patient prognosis and response to therapy. Accurately differentiating between breast cancer sub-types is an important part of clinical decision-making. Already, this problem has been addressed using machine learning methods that separate tissue samples into distinct groups. However, there remains unexplained heterogeneity within the established sub-types that cannot be resolved by the commonly used classification algorithms. In this paper, we propose a novel deep learning architecture, called DeepTRIAGE (Deep learning for the TRactable Individualised Analysis of Gene Expression), which not only classifies cancer sub-types with comparable accuracy, but simultaneously assigns each patient their own set of interpretable and individualised biomarker scores. These personalised scores describe how important each feature is in the classification of each patient, and can be analysed post-hoc to generate new hypotheses about intra-class heterogeneity. ResultsWe apply the DeepTRIAGE framework to classify the gene expression signatures of luminal A and luminal B breast cancer sub-types, and illustrate its use for genes and gene set (i.e., GO and KEGG) features. Using DeepTRIAGE, we find that the GINS1 gene and the kinetochore organisation GO term are the most important features for luminal sub-type classification. Through classification, DeepTRIAGE simultaneously reveals heterogeneity within the luminal A biomarker scores that significantly associate with tumour stage, placing all luminal samples along a continuum of severity. Availability and implementationThe proposed model is implemented in Python using Py-Torch framework. The analysis is done in Python and R. All Methods and models are freely available from https://github.com/adham/BiomarkerAttend.