Directed Graph Attention Neural Network Utilizing 3D Coordinates for Molecular Property Prediction
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights
TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence
AdaptMol: Adaptive Fusion from Sequence String to Topological Structure for Few-shot Drug Discovery
BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models
Knowledge-aware contrastive heterogeneous molecular graph learning
FragmentNet: Adaptive Graph Fragmentation for Graph-to-Sequence Molecular Representation Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.