4.7 Article

AweGNN: Auto-parametrized weighted element-specific graph neural networks for molecules

Journal

COMPUTERS IN BIOLOGY AND MEDICINE
Volume 134, Issue -, Pages -

Publisher

PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.compbiomed.2021.104460

Keywords

Automated feature extraction; Deep neural network; Mathematical representation; Toxicity; Solvation

Funding

  1. NIH [GM126189]
  2. NSF [DMS-1721024, DMS-1761320, DMS-2052983, DMS-2053284, IIS1900473]
  3. NASA [80NSSC21M0023]
  4. Michigan Economic Development Corporation
  5. George Mason University award [PD45722]
  6. Bristol-Myers Squibb [BMS-65109]
  7. Pfizer
  8. University of Kentucky Start-up fund

Ask authors/readers for more resources

This study introduces a new neural network model, AweGNN, which can automatically extract features of complex biomolecular data, overcoming the obstacle of manual parametrization. By constructing multi-task and single-task models, AweGNN demonstrates state-of-the-art performance in molecular property predictions.
While automated feature extraction has had tremendous success in many deep learning algorithms for image analysis and natural language processing, it does not work well for data involving complex internal structures, such as molecules. Data representations via advanced mathematics, including algebraic topology, differential geometry, and graph theory, have demonstrated superiority in a variety of biomolecular applications, however, their performance is often dependent on manual parametrization. This work introduces the auto-parametrized weighted element-specific graph neural network, dubbed AweGNN, to overcome the obstacle of this tedious parametrization process while also being a suitable technique for automated feature extraction on these internally complex biomolecular data sets. The AweGNN is a neural network model based on geometric-graph features of element-pair interactions, with its graph parameters being updated throughout the training, which results in what we call a network-enabled automatic representation (NEAR). To enhance the predictions with small data sets, we construct multi-task (MT) AweGNN models in addition to single-task (ST) AweGNN models. The proposed methods are applied to various benchmark data sets, including four data sets for quantitative toxicity analysis and another data set for solvation prediction. Extensive numerical tests show that AweGNN models can achieve state-of-the-art performance in molecular property predictions.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available