The message passing neural networks for chemical property prediction on SMILES

In this paper, we show that a simple coloring scheme can improve, both theoretically and empirically, the expressive power of Message Passing Neural Networks (MPNNs). More specifically, we introduce a graph neural network called Colored Local Iterative Procedure (CLIP) that uses colors to disambiguate identical node attributes, and show that this representation is a universal approximator of continuous functions on graphs with node attributes. Our method relies on separability, a key topological characteristic that allows to extend well-chosen neural networks into universal representations. Finally, we show experimentally that CLIP is capable of capturing structural characteristics that traditional MPNNs fail to distinguish, while being state-of-the-art on benchmark graph classification datasets.

Download Full-text

Generalizing Message Passing Neural Networks to Heterophily Using Position Information

10.1007/978-3-030-86365-4_19 ◽

2021 ◽

pp. 230-242

Author(s):

Wenzheng Zhang ◽

Jie Liu ◽

Liting Liu

Keyword(s):

Neural Networks ◽

Message Passing ◽

Position Information

Download Full-text

Building attention and edge message passing neural networks for bioactivity and physical–chemical property prediction

Journal of Cheminformatics ◽

10.1186/s13321-019-0407-y ◽

2020 ◽

Vol 12 (1) ◽

Cited By ~ 9

Author(s):

M. Withnall ◽

E. Lindelöf ◽

O. Engkvist ◽

H. Chen

Keyword(s):

Machine Learning ◽

Message Passing ◽

A Priori ◽

Molecular Graph ◽

Model Performance ◽

Learning Approaches ◽

Property Prediction ◽

Physical Chemical ◽

Chemical Descriptor ◽

Hyperparameter Selection

AbstractNeural Message Passing for graphs is a promising and relatively recent approach for applying Machine Learning to networked data. As molecules can be described intrinsically as a molecular graph, it makes sense to apply these techniques to improve molecular property prediction in the field of cheminformatics. We introduce Attention and Edge Memory schemes to the existing message passing neural network framework, 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.

Download Full-text