期刊
MOLECULES
卷 26, 期 4, 页码 -出版社
MDPI
DOI: 10.3390/molecules26041048
关键词
pKa prediction; ab initio; bond length; carbon acid
资金
- EPSRC Established Career Fellowship [EP/K005472]
- BBSRC iCASE PhD studentship [BB/L016788/1]
- BBSRC iCASE PhD studentship (Syngenta Ltd.)
- Impact Acceleration funding (Lhasa Ltd.) [IAA_105]
Predicting the aqueous pK(a) of carbon acids is challenging due to insufficient experimental data, but using atom-type feature vectors can help reduce prediction errors. Incorporating knowledge from multiple models into a general model has shown to improve predictions compared to using literature experimental data alone.
The prediction of the aqueous pK(a) of carbon acids by Quantitative Structure Property Relationship or cheminformatics-based methods is a rather arduous problem. Primarily, there are insufficient high-quality experimental data points measured in homogeneous conditions to allow for a good global model to be generated. In our computationally efficient pK(a) prediction method, we generate an atom-type feature vector, called a distance spectrum, from the assigned ionisation atom, and learn coefficients for those atom-types that show the impact each atom-type has on the pK(a) of the ionisable centre. In the current work, we augment our dataset with pK(a) values from a series of high performing local models derived from the Ab Initio Bond Lengths method (AIBL). We find that, in distilling the knowledge available from multiple models into one general model, the prediction error for an external test set is reduced compared to that using literature experimental data alone.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据