Directed Graph Attention Neural Network Utilizing 3D Coordinates for Molecular Property Prediction

12/01/2020
by   Chen Qian, et al.
0

The prosperity of computer vision (CV) and natural language procession (NLP) in recent years has spurred the development of deep learning in many other domains. The advancement in machine learning provides us with an alternative option besides the computationally expensive density functional theories (DFT). Kernel method and graph neural networks have been widely studied as two mainstream methods for property prediction. The promising graph neural networks have achieved comparable accuracy to the DFT method for specific objects in the recent study. However, most of the graph neural networks with high precision so far require fully connected graphs with pairwise distance distribution as edge information. In this work, we shed light on the Directed Graph Attention Neural Network (DGANN), which only takes chemical bonds as edges and operates on bonds and atoms of molecules. DGANN distinguishes from previous models with those features: (1) It learns the local chemical environment encoding by graph attention mechanism on chemical bonds. Every initial edge message only flows into every message passing trajectory once. (2) The transformer blocks aggregate the global molecular representation from the local atomic encoding. (3) The position vectors and coordinates are used as inputs instead of distances. Our model has matched or outperformed most baseline graph neural networks on QM9 datasets even without thorough hyper-parameters searching. Moreover, this work suggests that models directly utilizing 3D coordinates can still reach high accuracies for molecule representation even without rotational and translational invariance incorporated.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/19/2021

Learning Attributed Graph Representations with Communicative Message Passing Transformer

Constructing appropriate representations of molecules lies at the core o...
02/21/2022

Ligandformer: A Graph Neural Network for Predicting Compound Property with Robust Interpretation

Robust and efficient interpretation of QSAR methods is quite useful to v...
11/08/2021

Directional Message Passing on Molecular Graphs via Synthetic Coordinates

Graph neural networks that leverage coordinates via directional message ...
03/30/2022

Automatic Identification of Chemical Moieties

In recent years, the prediction of quantum mechanical observables with m...
09/20/2021

Edge-similarity-aware Graph Neural Networks

Graph are a ubiquitous data representation, as they represent a flexible...
03/03/2021

Chemistry-informed Macromolecule Graph Representation for Similarity Computation and Supervised Learning

Macromolecules are large, complex molecules composed of covalently bonde...
10/04/2021

3D-Transformer: Molecular Representation with Transformer in 3D Space

Spatial structures in the 3D space are important to determine molecular ...