Molecular structure prediction based on graph convolutional networks
- URL: http://arxiv.org/abs/2107.01035v1
- Date: Thu, 1 Jul 2021 08:34:51 GMT
- Title: Molecular structure prediction based on graph convolutional networks
- Authors: Xiaohui Lin, Yongquan Jiang, Yan Yang
- Abstract summary: A new Model Structure based on Graph Convolutional Neural network (MSGCN) is proposed.
It can determine the molecular structure by predicting the distance between two atoms.
- Score: 3.4618015083384255
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Due to the important application of molecular structure in many fields,
calculation by experimental means or traditional density functional theory is
often time consuming. In view of this, a new Model Structure based on Graph
Convolutional Neural network (MSGCN) is proposed, which can determine the
molecular structure by predicting the distance between two atoms. In order to
verify the effect of MSGCN model, the model is compared with the method of
calculating molecular three-dimensional conformation in RDKit, and the result
is better than it. In addition, the distance predicted by the MSGCN model and
the distance calculated by the QM9 dataset were used to predict the molecular
properties, thus proving the effectiveness of the distance predicted by the
MSGCN model.
Related papers
- Knowledge-aware contrastive heterogeneous molecular graph learning [77.94721384862699]
We propose a paradigm shift by encoding molecular graphs into Heterogeneous Molecular Graph Learning (KCHML)
KCHML conceptualizes molecules through three distinct graph views-molecular, elemental, and pharmacological-enhanced by heterogeneous molecular graphs and a dual message-passing mechanism.
This design offers a comprehensive representation for property prediction, as well as for downstream tasks such as drug-drug interaction (DDI) prediction.
arXiv Detail & Related papers (2025-02-17T11:53:58Z) - REBIND: Enhancing ground-state molecular conformation via force-based graph rewiring [38.77055275481021]
We propose REBIND, a novel framework that rewires molecular graphs by adding edges based on the Lennard-Jones potential to capture non-bonded interactions for low-degree atoms.
Experimental results demonstrate that REBIND significantly outperforms state-of-the-art methods across various molecular sizes.
arXiv Detail & Related papers (2024-10-04T16:02:33Z) - Molecular Graph Representation Learning via Structural Similarity Information [11.38130169319915]
We introduce the textbf Structural Similarity Motif GNN (MSSM-GNN), a novel molecular graph representation learning method.
In particular, we propose a specially designed graph that leverages graph kernel algorithms to represent the similarity between molecules quantitatively.
We employ GNNs to learn feature representations from molecular graphs, aiming to enhance the accuracy of property prediction by incorporating additional molecular representation information.
arXiv Detail & Related papers (2024-09-13T06:59:10Z) - Pre-training of Molecular GNNs via Conditional Boltzmann Generator [0.0]
We propose a pre-training method for molecular GNNs using an existing dataset of molecular conformations.
We show that our model has a better prediction performance for molecular properties than existing pre-training methods.
arXiv Detail & Related papers (2023-12-20T15:30:15Z) - ViSNet: an equivariant geometry-enhanced graph neural network with
vector-scalar interactive message passing for molecules [69.05950120497221]
We propose an equivariant geometry-enhanced graph neural network called ViSNet, which elegantly extracts geometric features and efficiently models molecular structures.
Our proposed ViSNet outperforms state-of-the-art approaches on multiple MD benchmarks, including MD17, revised MD17 and MD22, and achieves excellent chemical property prediction on QM9 and Molecule3D datasets.
arXiv Detail & Related papers (2022-10-29T07:12:46Z) - Multi-Task Mixture Density Graph Neural Networks for Predicting Cu-based
Single-Atom Alloy Catalysts for CO2 Reduction Reaction [61.9212585617803]
Graph neural networks (GNNs) have drawn more and more attention from material scientists.
We develop a multi-task (MT) architecture based on DimeNet++ and mixture density networks to improve the performance of such task.
arXiv Detail & Related papers (2022-09-15T13:52:15Z) - Graph neural networks for the prediction of molecular structure-property
relationships [59.11160990637615]
Graph neural networks (GNNs) are a novel machine learning method that directly work on the molecular graph.
GNNs allow to learn properties in an end-to-end fashion, thereby avoiding the need for informative descriptors.
We describe the fundamentals of GNNs and demonstrate the application of GNNs via two examples for molecular property prediction.
arXiv Detail & Related papers (2022-07-25T11:30:44Z) - Edge Direction-invariant Graph Neural Networks for Molecular Dipole
Moments Prediction [0.0]
We develop new embeddings for representation of the dipole moment in molecules.
We show that the developed model works reasonably even for molecules with extended geometries.
We significantly improve the prediction results with accuracy comparable to ab-initio calculations.
arXiv Detail & Related papers (2022-06-26T12:52:17Z) - Learning Neural Generative Dynamics for Molecular Conformation
Generation [89.03173504444415]
We study how to generate molecule conformations (textiti.e., 3D structures) from a molecular graph.
We propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph.
arXiv Detail & Related papers (2021-02-20T03:17:58Z) - Equivariant message passing for the prediction of tensorial properties
and molecular spectra [1.7188280334580197]
We propose the polarizable atom interaction neural network (PaiNN) and improve on common molecule benchmarks over previous networks.
We apply this to the simulation of molecular spectra, achieving speedups of 4-5 orders of magnitude compared to the electronic structure reference.
arXiv Detail & Related papers (2021-02-05T13:00:12Z) - Multi-View Graph Neural Networks for Molecular Property Prediction [67.54644592806876]
We present Multi-View Graph Neural Network (MV-GNN), a multi-view message passing architecture.
In MV-GNN, we introduce a shared self-attentive readout component and disagreement loss to stabilize the training process.
We further boost the expressive power of MV-GNN by proposing a cross-dependent message passing scheme.
arXiv Detail & Related papers (2020-05-17T04:46:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.