Dr.VAE: Drug Response Variational Autoencoder
arXiv:1706.08203
Abstract
We present two deep generative models based on Variational Autoencoders to improve the accuracy of drug response prediction. Our models, Perturbation Variational Autoencoder and its semi-supervised extension, Drug Response Variational Autoencoder (Dr.VAE), learn latent representation of the underlying gene states before and after drug application that depend on: (i) drug-induced biological change of each gene and (ii) overall treatment response outcome. Our VAE-based models outperform the current published benchmarks in the field by anywhere from 3 to 11% AUROC and 2 to 30% AUPR. In addition, we found that better reconstruction accuracy does not necessarily lead to improvement in classification accuracy and that jointly trained models perform better than models that minimize reconstruction error independently.
submitted to NIPS 2017
Cited by in corpus (5)
- Evaluating deep variational autoencoders trained on pan-cancer gene expression
- Accelerated Discovery of Sustainable Building Materials
- Deep learning in bioinformatics: introduction, application, and perspective in big data era
- retina-VAE: Variationally Decoding the Spectrum of Macular Disease
- Learning a Generative Model of Cancer Metastasis