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.
翻译:我们展示了两种基于变式自动编码的深层基因模型,以提高药物反应预测的准确性。我们的模型,即周期变式自动编码器及其半监督扩展,即药物反应变式自动编码器(Dr.VAE),在药物应用前后了解基本基因状态的潜在代表性,这取决于:(一) 每种基因的药物引起的生物变化和(二) 总体治疗反应结果。我们的VAE模型在3%至11%的AUROC和2%至30%的AUPR之间比目前公布的实地基准高出。此外,我们发现,更好的重建精确度并不一定导致分类准确性提高,联合培训的模式比独立将重建错误降到最低的模型效果更好。