Machine learning with physicochemical relationships: solubility prediction in organic solvents and water.

Machine learning with physicochemical relationships: solubility prediction in organic solvents and water.
复制标题

DOI:
10.1038/s41467-020-19594-z
复制
发表时间:
2020-11-13
影响因子:
16.6
通讯作者:
Nguyen BN
Nguyen BN
中科院分区:
综合性期刊1区
文献类型:
--
作者:
Boobier S;Hose DRJ;Blacker AJ;Nguyen BN

文献摘要

参考文献

被引文献

相似文献

溶解度预测在药物开发、合成路线和化学工艺设计、提取和结晶中仍然是一个关键的挑战。在这里,我们报告了一个成功的方法,在有机溶剂和水的溶解度预测使用机器学习(ANN,SVM,RF,ExtraTrees,Bagging和GP)和计算化学的组合。将溶出过程合理解释为数值问题导致了一小组选定的描述符和随后的预测,这些描述符和预测独立于所应用的机器学习方法。与基准开放获取和商业工具相比,这些模型的预测准确度明显更高,准确度接近训练数据中的预期噪声水平(LogS ± 0.7)。最后,他们再现了不同溶剂中溶解度与分子性质之间的物理化学关系,从而导致合理的方法来提高每个模型的准确性。由于所涉及的现象的复杂性,准确预测溶解度对传统的计算方法提出了挑战。在这里,作者报告了一种成功的方法,使用机器学习和计算化学相结合的方法来预测有机溶剂和水中的溶解度。
Solubility prediction remains a critical challenge in drug development, synthetic route and chemical process design, extraction and crystallisation. Here we report a successful approach to solubility prediction in organic solvents and water using a combination of machine learning (ANN, SVM, RF, ExtraTrees, Bagging and GP) and computational chemistry. Rational interpretation of dissolution process into a numerical problem led to a small set of selected descriptors and subsequent predictions which are independent of the applied machine learning method. These models gave significantly more accurate predictions compared to benchmarked open-access and commercial tools, achieving accuracy close to the expected level of noise in training data (LogS ± 0.7). Finally, they reproduced physicochemical relationship between solubility and molecular properties in different solvents, which led to rational approaches to improve the accuracy of each models. Accurate prediction of solubility represents a challenge for traditional computational approaches due to the complex nature of phenomena involved. Here the authors report a successful approach to solubility prediction in organic solvents and water using combination of machine learning and computational chemistry.
DOI: 10.1021/ci9901338
发表时间: 2000-05-01
期刊: JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES
影响因子: --
作者:
Huuskonen, J
通讯作者: Huuskonen, J
DOI: 10.1093/bioinformatics/bty166
发表时间: 2018-08-01
期刊: BIOINFORMATICS
影响因子: 5.8
作者:
Khurana, Sameer;Rawi, Reda;Mall, Raghvendra
通讯作者: Mall, Raghvendra
DOI: 10.1039/p29930000799
发表时间: 1993-05-01
期刊: JOURNAL OF THE CHEMICAL SOCIETY-PERKIN TRANSACTIONS 2
影响因子: --
作者:
KLAMT, A;SCHUURMANN, G
通讯作者: SCHUURMANN, G
DOI: 10.3762/bjoc.9.265
发表时间: 2013-10-30
影响因子: 2.7
作者:
Baumann M;Baxendale IR
通讯作者: Baxendale IR
DOI: 10.1021/acs.oprd.6b00015
发表时间: 2016-04-01
影响因子: 3.4
作者:
Diorazio, Louis J.;Hose, David R. J.;Adlington, Neil K.
通讯作者: Adlington, Neil K.