Title |
Machine learning for the prediction of molecular dipole moments obtained by density functional theory
|
---|---|
Published in |
Journal of Cheminformatics, August 2018
|
DOI | 10.1186/s13321-018-0296-5 |
Pubmed ID | |
Authors |
Florbela Pereira, João Aires-de-Sousa |
Abstract |
Machine learning (ML) algorithms were explored for the fast estimation of molecular dipole moments calculated by density functional theory (DFT) by B3LYP/6-31G(d,p) on the basis of molecular descriptors generated from DFT-optimized geometries and partial atomic charges obtained by empirical or ML schemes. A database was used with 10,071 structures, new molecular descriptors were designed and the models were validated with external test sets. Several ML algorithms were screened. Random forest regression models predicted an external test set of 3368 compounds achieving mean absolute error up to 0.44 D. The results represent a significant improvement of the dipole moments calculated using empirical point charges located at the nucleus, even assuming the DFT-optimized geometry (root mean square error, RMSE, of 0.68 D vs. 1.53 D and R2 = 0.87 vs. 0.66). |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
Sweden | 1 | 9% |
Israel | 1 | 9% |
Switzerland | 1 | 9% |
United States | 1 | 9% |
Unknown | 7 | 64% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 7 | 64% |
Scientists | 3 | 27% |
Science communicators (journalists, bloggers, editors) | 1 | 9% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 85 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 22 | 26% |
Researcher | 15 | 18% |
Student > Bachelor | 9 | 11% |
Student > Doctoral Student | 6 | 7% |
Student > Master | 4 | 5% |
Other | 7 | 8% |
Unknown | 22 | 26% |
Readers by discipline | Count | As % |
---|---|---|
Chemistry | 32 | 38% |
Physics and Astronomy | 6 | 7% |
Materials Science | 6 | 7% |
Computer Science | 3 | 4% |
Engineering | 3 | 4% |
Other | 11 | 13% |
Unknown | 24 | 28% |