ChemRxiv
These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
1/1
2 files
0/0

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

preprint
submitted on 18.09.2019 and posted on 23.09.2019 by Michael Withnall, Edvard Lindelöf, Ola Engkvist, Hongming Chen
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.

Funding

Big Data in Chemistry

European Commission

Find out more...

History

Email Address of Submitting Author

followup@withnall.org.uk

Institution

AstraZeneca R&D

Country

Sweden

ORCID For Submitting Author

0000-0002-9706-8698

Declaration of Conflict of Interest

The authors declare no conflict of interest.

Version Notes

Updated author contributions.

Exports