Computational Science Laboratory , Universitat Pompeu Fabra , Barcelona Biomedical Research Park (PRBB), C Dr Aiguader 88 , 08003 Barcelona , Spain.
Acellera , Barcelona Biomedical Research Park (PRBB), C Dr. Aiguader 88 , 08003 Barcelona , Spain.
J Chem Inf Model. 2019 Mar 25;59(3):1205-1214. doi: 10.1021/acs.jcim.8b00706. Epub 2019 Feb 28.
In this work, we propose a machine learning approach to generate novel molecules starting from a seed compound, its three-dimensional (3D) shape, and its pharmacophoric features. The pipeline draws inspiration from generative models used in image analysis and represents a first example of the de novo design of lead-like molecules guided by shape-based features. A variational autoencoder is used to perturb the 3D representation of a compound, followed by a system of convolutional and recurrent neural networks that generate a sequence of SMILES tokens. The generative design of novel scaffolds and functional groups can cover unexplored regions of chemical space that still possess lead-like properties.
在这项工作中，我们提出了一种机器学习方法，从种子化合物、其三维 (3D) 形状和药效特征出发，生成新的分子。该流水线的灵感来自于图像分析中使用的生成模型，代表了首次使用基于形状的特征引导从头设计类先导化合物的例子。变分自动编码器用于扰动化合物的 3D 表示，然后是一个卷积和递归神经网络系统，生成 SMILES 标记序列。新颖支架和功能基团的生成设计可以覆盖仍然具有类先导性质的化学空间中未探索的区域。
