Directed graph attention neural network utilizing 3D coordinates for molecular property prediction

نویسندگان

چکیده

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

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Attention-based Graph Neural Network for Semi-supervised Learning

Recently popularized graph neural networks achieve the state-of-the-art accuracy on a number of standard benchmark datasets for graph-based semi-supervised learning, improving significantly over existing approaches. These architectures alternate between a propagation layer that aggregates the hidden states of the local neighborhood and a fully-connected layer. Perhaps surprisingly, we show that...

متن کامل

Adaptive H∞ consensus control of euler-lagrange systems on directed network graph by utilizing neural network approximators

A design method of adaptive consensus control of multi-agent systems composed of fully actuated mobile robots which are described as a class of Euler-Lagrange systems on directed network graphs, is presented in this paper based on the notion of inverse optimal H∞ control criterion. The proposed control scheme is deduced as a solution of certain H∞ control problem, where estimation errors of tun...

متن کامل

Syntax-Directed Attention for Neural Machine Translation

Attention mechanism, including global attention and local attention, plays a key role in neural machine translation (NMT). Global attention attends to all source words for word prediction. In comparison, local attention selectively looks at fixed-window source words. However, alignment weights for the current target word often decrease to the left and right by linear distance centering on the a...

متن کامل

Utilizing a new feed-back fuzzy neural network for solving a system of fuzzy equations

This paper intends to offer a new iterative method based on articial neural networks for finding solution of a fuzzy equations system. Our proposed fuzzied neural network is a ve-layer feedback neural network that corresponding connection weights to output layer are fuzzy numbers. This architecture of articial neural networks, can get a real input vector and calculates its corresponding fuzzy o...

متن کامل

Chemi-net: a graph convolutional network for accurate drug property prediction

Absorption, distribution, metabolism, and excretion (ADME) studies are critical for drug discovery. Conventionally, these tasks, together with other chemical property predictions, rely on domain-specific feature descriptors, or fingerprints. Following the recent success of neural networks, we developed Chemi-Net, a completely data-driven, domain knowledge-free, deep learning method for ADME pro...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Computational Materials Science

سال: 2021

ISSN: ['1879-0801', '0927-0256']

DOI: https://doi.org/10.1016/j.commatsci.2021.110761