Theoretical and Computational Chemistry

Building Attention and Edge Convolution Neural Networks for Bioactivity and Physical-Chemical Property Prediction



We introduce Attention and Edge Memory schemes to the existing Message Passing Neural Network framework for graph convolution, and benchmark our approaches against eight different physical-chemical and bioactivity datasets from the literature. We remove the need to introduce a priori knowledge of the task and chemical descriptor calculation by using only fundamental graph-derived properties. Our results consistently perform on-par with other state-of-the-art machine learning approaches, and set a new standard on sparse multi-task virtual screening targets. We also investigate model performance as a function of dataset preprocessing, and make some suggestions regarding hyperparameter selection.

Version notes

Updated author contributions.


Thumbnail image of Attention_Edge_Convolution_Bioactivity_Prediction_v12.pdf

Supplementary material

Thumbnail image of Supplemental Information.pdf
Supplemental Information
Thumbnail image of Attention_Edge_Convolution_Bioactivity_Prediction_v12.docx
Attention Edge Convolution Bioactivity Prediction v12