We present a flexible deep convolutional neural network method for the analyse of arbitrary sized graph structures representing molecules. The method makes use of RDKit, an open-source cheminformatics software, allowing the incorporation of any global molecular (such as molecular charge) and local (such as atom type) information. We evaluate the method on the Side Effect Resource (SIDER) v4.1 dataset and show that it significantly outperforms another recently proposed method based on deep convolutional neural networks. We also reflect on how different types of information and input data affect the predictive power of our model. This reflection highlights several open problems that should be solved to further improve the use of deep learning within cheminformatics.
CITATION STYLE
Ståhl, N., Falkman, G., Karlsson, A., Mathiason, G., & Boström, J. (2019). Improving the use of deep convolutional neural networks for the prediction of molecular properties. In Advances in Intelligent Systems and Computing (Vol. 803, pp. 71–79). Springer Verlag. https://doi.org/10.1007/978-3-319-98702-6_9
Mendeley helps you to discover research relevant for your work.