Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules.

Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules.
复制标题

DOI:
10.1021/acscentsci.7b00572
复制
发表时间:
2018-02-28
影响因子:
18.2
通讯作者:
Aspuru-Guzik A
Aspuru-Guzik A
中科院分区:
化学1区
文献类型:
--
作者:
Gómez-Bombarelli R;Wei JN;Duvenaud D;Hernández-Lobato JM;Sánchez-Lengeling B;Sheberla D;Aguilera-Iparraguirre J;Hirzel TD;Adams RP;Aspuru-Guzik A

文献摘要

参考文献

被引文献

相似文献

我们报告了一种将分子的离散表示转换为多维连续表示或从多维连续表示转换的方法。这个模型允许我们产生新的分子,通过化合物的开放空间进行有效的探索和优化。一个深度神经网络被训练在数十万个现有的化学结构上,以构建三个耦合功能:编码器、解码器和预报器。编码器将分子的离散表示转换为实值的连续向量,而解码器将这些连续向量转换回离散的分子表示。预报器根据分子的潜在连续向量表示来估计化学性质。分子的连续表示允许我们通过在潜在空间中执行简单的操作来自动生成新的化学结构,例如解码随机向量、扰动已知的化学结构或在分子之间进行内插。连续表示法还允许使用强大的基于梯度的优化来有效地指导对优化功能化合物的搜索。我们在类药物分子领域和一组重原子少于9个的分子中展示了我们的方法。为了解决化学中的逆向设计挑战,我们使用神经网络将分子转换为连续的矢量表示。我们演示了基于梯度的分子性质优化。
We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient exploration and optimization through open-ended spaces of chemical compounds. A deep neural network was trained on hundreds of thousands of existing chemical structures to construct three coupled functions: an encoder, a decoder, and a predictor. The encoder converts the discrete representation of a molecule into a real-valued continuous vector, and the decoder converts these continuous vectors back to discrete molecular representations. The predictor estimates chemical properties from the latent continuous vector representation of the molecule. Continuous representations of molecules allow us to automatically generate novel chemical structures by performing simple operations in the latent space, such as decoding random vectors, perturbing known chemical structures, or interpolating between molecules. Continuous representations also allow the use of powerful gradient-based optimization to efficiently guide the search for optimized functional compounds. We demonstrate our method in the domain of drug-like molecules and also in a set of molecules with fewer that nine heavy atoms. To solve the inverse design challenge in chemistry, we convert molecules into continuous vector representations using neural networks. We demonstrate gradient-based property optimization of molecules.
DOI: 10.1038/nchem.1243
发表时间: 2012-01-24
期刊: Nature chemistry
影响因子: 21.8
作者:
通讯作者: --
DOI: 10.1093/nar/gkv951
发表时间: 2016-01-04
影响因子: 14.9
作者:
Kim S;Thiessen PA;Bolton EE;Chen J;Fu G;Gindulyte A;Han L;He J;He S;Shoemaker BA;Wang J;Yu B;Zhang J;Bryant SH
通讯作者: Bryant SH
DOI: 10.1021/jz200866s
发表时间: 2011-09-01
影响因子: 5.7
作者:
Hachmann, Johannes;Olivares-Amaya, Roberto;Aspuru-Guzik, Alan
通讯作者: Aspuru-Guzik, Alan
DOI: 10.1063/1.2987711
发表时间: 2008-11-07
影响因子: 4.4
作者:
Balamurugan, D.;Yang, Weitao;Beratan, David N.
通讯作者: Beratan, David N.
DOI: 10.1186/1758-2946-1-8
发表时间: 2009-06-10
影响因子: 8.6
作者:
Ertl P;Schuffenhauer A
通讯作者: Schuffenhauer A