DeepCC
Overview
DeepCC is a novel supervised deep framework for cancer molecular subtype classification, which leverages the power of deep learning based on an ANN for cancer classification. Especially, in DeepCC, we define a function which transforms gene expression profiles to transcriptional patterns with functional relevance using GSEA. Following the classification is performed by deep learning using a trainable multilayer ANN. By integrating biological knowledge, DeepCC can overcomes limitations of signature gene-based approach and leads to more robust performance. Besides, deep features learned by DeepCC captured biological characteristics associated with distinct molecular subtypes, enabling more compact within-subtype distribution and between-subtype separation of patient samples, and therefore greatly reduce the number of unclassifiable samples previously.
In summary, DeepCC provides a novel cancer classification framework that is platform independent, robust to missing data, and can be used for single sample prediction facilitating clinical implementation of cancer molecular subtyping.