Figure 4 - uploaded by Daniela Mayumi Ushizima
Content may be subject to copyright.
Histogram of testing error distribution comparing MR-3D-DenseNet and KRR for (a) 1 H, (b) 13 C, (c) 15 N and (d) 17 O
Source publication
We have developed a deep learning algorithm for chemical shift prediction for atoms in molecular crystals that utilizes an atom-centered Gaussian density model for the 3D data representation of a molecule. We define multiple channels that describe different spatial resolutions for each atom type that utilizes cropping, pooling, and concatenation to...
Contexts in source publication
Context 1
... importantly, the prediction time of MR-3D-DenseNet with a trained model does not scale with the number of training examples, whereas the testing time for KRR scales linearly because the similarity kernel has to be calculated using all of the training samples. In totality, the MR-3D-DenseNet architecture with data augmentation yields a much tighter prediction error across the unique data across all atom types relative to KRR as seen in Figure 4. We found that further increasing the data augmentation to 16-fold rotations or adding the effects of small vibrational smearing of atom positions had a neutral effect on the prediction performance. ...
Context 2
... totality, the MR-3D-DenseNet architecture with data augmentation yields a much tighter prediction error across the unique data across all atom types relative to KRR as seen in Figure 4. We found that further increasing the data augmentation to 16-fold rotations or adding the effects of small vibrational smearing of atom positions had a neutral effect on the prediction performance. Instead Figure 4 emphasizes that creating more unique data for the heavy atoms will certainly improve the MR-3D-DenseNet performance relative to ab initio models, as the number of heavy atom samples are limited compared to 1 H samples in the current dataset. The MR-3D-DenseNet model is interpretable by extracting the chemical bonding and hydrogen-bonding information that is clearly relevant for 1 H chemical shift prediction using principle component analysis (PCA). ...
Context 3
... importantly, the prediction time of MR-3D-DenseNet with a trained model does not scale with the number of training examples, whereas the testing time for KRR scales linearly because the similarity kernel has to be calculated using all of the training samples. In totality, the MR-3D-DenseNet architecture with data augmentation yields a much tighter prediction error across the unique data across all atom types relative to KRR as seen in Figure 4. We found that further increasing the data augmentation to 16-fold rotations or adding the effects of small vibrational smearing of atom positions had a neutral effect on the prediction performance. ...
Context 4
... totality, the MR-3D-DenseNet architecture with data augmentation yields a much tighter prediction error across the unique data across all atom types relative to KRR as seen in Figure 4. We found that further increasing the data augmentation to 16-fold rotations or adding the effects of small vibrational smearing of atom positions had a neutral effect on the prediction performance. Instead Figure 4 emphasizes that creating more unique data for the heavy atoms will certainly improve the MR-3D-DenseNet performance relative to ab initio models, as the number of heavy atom samples are limited compared to 1 H samples in the current dataset. The MR-3D-DenseNet model is interpretable by extracting the chemical bonding and hydrogen-bonding information that is clearly relevant for 1 H chemical shift prediction using principle component analysis (PCA). ...
