Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks.

Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks.
复制标题

通过复发性神经网络生成聚焦的分子库来发现药物。

DOI:
10.1021/acscentsci.7b00512
复制
发表时间:
2018-01-24
影响因子:
18.2
通讯作者:
Waller MP
Waller MP
中科院分区:
化学1区
文献类型:
--
作者:
Segler MHS;Kogej T;Tyrchan C;Waller MP

文献摘要

参考文献

被引文献

相似文献

在从头药物设计中,使用计算策略来生成对所需生物靶标具有良好亲和力的新型分子。在这项工作中,我们证明循环神经网络可以被训练为分子结构的生成模型,类似于自然语言处理中的统计语言模型。我们证明,生成的分子的属性与用于训练模型的分子的属性非常相关。为了丰富具有针对给定生物靶标的活性分子的文库,我们建议使用已知对该靶标具有活性的小分子集来微调模型。针对金黄色葡萄球菌,该模型再现了药物化学家设计的 6051 个测试分子中的 14%,而针对恶性疟原虫(疟疾),该模型再现了 1240 个测试分子中的 28%。当与评分函数结合使用时,我们的模型可以执行完整的从头药物设计周期,以生成大量用于药物发现的新分子。使用人工神经网络,计算机可以学习生成具有所需目标特性的分子。这可以帮助药物设计的创造性过程。
In de novo drug design, computational strategies are used to generate novel molecules with good affinity to the desired biological target. In this work, we show that recurrent neural networks can be trained as generative models for molecular structures, similar to statistical language models in natural language processing. We demonstrate that the properties of the generated molecules correlate very well with the properties of the molecules used to train the model. In order to enrich libraries with molecules active toward a given biological target, we propose to fine-tune the model with small sets of molecules, which are known to be active against that target. Against Staphylococcus aureus, the model reproduced 14% of 6051 hold-out test molecules that medicinal chemists designed, whereas against Plasmodium falciparum (Malaria), it reproduced 28% of 1240 test molecules. When coupled with a scoring function, our model can perform the complete de novo drug design cycle to generate large sets of novel molecules for drug discovery. Using artificial neural networks, computers can learn to generate molecules with desired target properties. This can aid in the creative process of drug design.
DOI: 10.1109/72.963769
发表时间: 2001-11-01
影响因子: --
作者:
Gers, FA;Schtmidhuber, J
通讯作者: Schtmidhuber, J
DOI: 10.1103/physrevlett.98.146401
发表时间: 2007-04-06
影响因子: 8.6
作者:
Behler, Joerg;Parrinello, Michele
通讯作者: Parrinello, Michele
DOI: 10.1021/ci940128y
发表时间: 1997-07-01
期刊: JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES
影响因子: --
作者:
Baskin, II;Palyulin, VA;Zefirov, NS
通讯作者: Zefirov, NS
DOI: 10.1021/ci500361u
发表时间: 2014-10-01
影响因子: 5.6
作者:
Alvarsson, Jonathan;Eklund, Martin;Noeske, Tobias
通讯作者: Noeske, Tobias
DOI: 10.1021/jm9602928
发表时间: 1996-07-19
影响因子: 7.3
作者:
Bemis, GW;Murcko, MA
通讯作者: Murcko, MA