Dr.VAE: Drug Response Variational Autoencoder

2017/06/26 by Ladislav Rampášek, Rampasek, Ladislav, Daniel Hidru +7 · 4 citations
Materials Science · Computer Science · Biochemistry, Genetics and Molecular Biology · #Machine Learning in Materials Science #Computational Drug Discovery Methods #Protein Structure and Dynamics

paper · pdf · doi:10.48550/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.

Cited by

• Learning a Generative Model of Cancer Metastasis
• Evaluating deep variational autoencoders trained on pan-cancer gene expression
• Variational Autoencoder for Anti-Cancer Drug Response Prediction
• Segment-Based Credit Scoring Using Latent Clusters in the Variational\n Autoencoder

Related

• Variational Autoencoder for Anti-Cancer Drug Response Prediction
• GPO-VAE: Modeling Explainable Gene Perturbation Responses utilizing GRN-Aligned Parameter Optimization
• Variational and Explanatory Neural Networks for Encoding Cancer Profiles and Predicting Drug Responses
• Predicting gene essentiality and drug response from perturbation screens in preclinical cancer models with LEAP: Layered Ensemble of Autoencoders and Predictors
• A Matrix Variational Auto-Encoder for Variant Effect Prediction in Pharmacogenes