Analyzing the Accuracy of Critical Micelle Concentration Predictions Using Deep Learning.

Analyzing the Accuracy of Critical Micelle Concentration Predictions Using Deep Learning.
复制标题

使用深度学习分析临界胶束浓度预测的准确性。

DOI:
10.1021/acs.jctc.3c00868
复制
发表时间:
2023
影响因子:
5.5
通讯作者:
Moriarty A
Moriarty A
中科院分区:
化学1区
文献类型:
--
作者:
Moriarty A

文献摘要

参考文献

相似文献

提出了一种基于高斯过程的图型神经网络预测临界胶束浓度的新方法。所提出的模型使用分子的学习潜在空间表示来预测CMC并估计不确定性。将该模型在包含非离子、阳离子、阴离子和两性离子分子的数据集上的性能与使用扩展连接指纹(ECFP)的线性模型进行了比较。当有足够的良好平衡的训练数据时,基于GNN的模型的性能略好于线性ECFP模型,并且获得的预测精度可与已发表的在较小范围的表面活性剂化学成分上进行评估的模型相媲美。我们使用分子地图来显示潜在空间,这有助于识别预测可能是错误的分子,从而说明我们模型的适用范围。除了准确预测某些表面活性剂类别的CMC外,所提出的方法还可以为影响CMC的分子性质提供有价值的见解。
This paper presents a novel approach to predicting critical micelle concentrations (CMCs) by using graph neural networks (GNNs) augmented with Gaussian processes (GPs). The proposed model uses learned latent space representations of molecules to predict CMCs and estimate uncertainties. The performance of the model on a data set containing nonionic, cationic, anionic, and zwitterionic molecules is compared against a linear model that works with extended connectivity fingerprints (ECFPs). The GNN-based model performs slightly better than the linear ECFP model when there is enough well-balanced training data and achieves predictive accuracy that is comparable to published models that were evaluated on a smaller range of surfactant chemistries. We illustrate the applicability domain of our model using a molecular cartogram to visualize the latent space, which helps to identify molecules for which predictions are likely to be erroneous. In addition to accurately predicting CMCs for some surfactant classes, the proposed approach can provide valuable insights into the molecular properties that influence CMCs.
DOI: 10.2174/1573409911309020005
发表时间: 2013-06-01
影响因子: 1.7
作者:
Bolboaca, Sorana D.;Jaentschi, Lorentz;Diudea, Mircea V.
通讯作者: Diudea, Mircea V.
DOI: 10.1021/acs.jctc.9b00296
发表时间: 2019-09-01
影响因子: 5.5
作者:
Khedr, Abeer;Striolo, Alberto
通讯作者: Striolo, Alberto
QSPR 中的碎片方法
DOI: 10.1021/ci020010e
发表时间: 2002
期刊: Journal of chemical information and computer sciences
影响因子: --
作者:
N. Zefirov;V. Palyulin
通讯作者: V. Palyulin
DOI: 10.1016/j.fluid.2005.02.008
发表时间: 2005
影响因子: 2.6
作者:
Jaw;Yan
通讯作者: Yan
Gibbs-Tolman-Koenig-Buff Kelvin 缩合模型的提出以及使用环己烷吸附等温线评估二氧化硅纳米孔径
DOI: --
发表时间: 2010
期刊:
影响因子: --
作者:
Horikawa T;et al.;神田英輝
通讯作者: 神田英輝