Pharmaceutical Artificial Intelligence Department, Insilico Medicine, Inc., Emerging Technology Centers, Johns Hopkins University at Eastern , Baltimore, Maryland 21218, United States.
Steklov Mathematical Institute at St. Petersburg , St. Petersburg 191023, Russia.
Mol Pharm. 2017 Sep 5;14(9):3098-3104. doi: 10.1021/acs.molpharmaceut.7b00346. Epub 2017 Aug 4.
Deep generative adversarial networks (GANs) are the emerging technology in drug discovery and biomarker development. In our recent work, we demonstrated a proof-of-concept of implementing deep generative adversarial autoencoder (AAE) to identify new molecular fingerprints with predefined anticancer properties. Another popular generative model is the variational autoencoder (VAE), which is based on deep neural architectures. In this work, we developed an advanced AAE model for molecular feature extraction problems, and demonstrated its advantages compared to VAE in terms of (a) adjustability in generating molecular fingerprints; (b) capacity of processing very large molecular data sets; and (c) efficiency in unsupervised pretraining for regression model. Our results suggest that the proposed AAE model significantly enhances the capacity and efficiency of development of the new molecules with specific anticancer properties using the deep generative models.
深度生成对抗网络（GAN）是药物发现和生物标志物开发中的新兴技术。在我们最近的工作中，我们证明了实现深度生成对抗自动编码器（AAE）的概念验证，以识别具有预定抗癌特性的新分子指纹。另一种流行的生成模型是变分自动编码器（VAE），它基于深度神经网络架构。在这项工作中，我们为分子特征提取问题开发了一个先进的 AAE 模型，并展示了与 VAE 相比，它在以下方面的优势：（a）在生成分子指纹方面的可调节性；（b）处理非常大数据集的能力；（c）回归模型的无监督预训练效率。我们的结果表明，所提出的 AAE 模型显著提高了使用深度生成模型开发具有特定抗癌特性的新分子的能力和效率。
