PT  - JOURNAL ARTICLE
AU  - Ayse Berceste Dincer
AU  - Safiye Celik
AU  - Naozumi Hiranuma
AU  - Su-In Lee
TI  - DeepProfile: Deep learning of cancer molecular profiles for precision medicine
AID  - 10.1101/278739
DP  - 2018 Jan 01
TA  - bioRxiv
PG  - 278739
4099  - http://biorxiv.org/content/early/2018/05/26/278739.short
4100  - http://biorxiv.org/content/early/2018/05/26/278739.full
AB  - We present the DeepProfile framework, which learns a variational autoencoder (VAE) network from thousands of publicly available gene expression samples and uses this network to encode a low-dimensional representation (LDR) to predict complex disease phenotypes. To our knowledge, DeepProfile is the first attempt to use deep learning to extract a feature representation from a vast quantity of unlabeled (i.e, lacking phenotype information) expression samples that are not incorporated into the prediction problem. We use Deep-Profile to predict acute myeloid leukemia patients’ in vitro responses to 160 chemotherapy drugs. We show that, when compared to the original features (i.e., expression levels) and LDRs from two commonly used dimensionality reduction methods, DeepProfile: (1) better predicts complex phenotypes, (2) better captures known functional gene groups, and (3) better reconstructs the input data. We show that DeepProfile is generalizable to other diseases and phenotypes by using it to predict ovarian cancer patients’ tumor invasion patterns and breast cancer patients’ disease subtypes.