Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective

Lu, Chengqiang; Liu, Qi; Wang, Chao; Huang, Zhenya; Lin, Peize; He, Lixin

doi:10.1609/aaai.v33i01.33011052

Cited by 138 publications

(130 citation statements)

References 13 publications

Supporting

Mentioning

130

Contrasting

Order By: Relevance

“…Multilevel graph convolutional neural network (MGCN), 65 similar to MPNN, has advantages in terms of generalizability and transferability.…”

Section: Implementationsmentioning

confidence: 99%

Forecasting System of Computational Time of DFT/TDDFT Calculations under the Multiverse Ansatz via Machine Learning and Cheminformatics

Zhang

et al. 2021

ACS Omega

View full text Add to dashboard Cite

With the view of achieving a better performance in task assignment and load-balancing, a top-level designed forecasting system for predicting computational times of density-functional theory (DFT)/time-dependent DFT (TDDFT) calculations is presented. The computational time is assumed as the intrinsic property for the molecule. Based on this assumption, the forecasting system is established using the “reinforced concrete”, which combines the cheminformatics, several machine-learning (ML) models, and the framework of many-world interpretation (MWI) in multiverse ansatz. Herein, the cheminformatics is used to recognize the topological structure of molecules, the ML models are used to build the relationships between topology and computational cost, and the MWI framework is used to hold various combinations of DFT functionals and basis sets in DFT/TDDFT calculations. Calculated results of molecules from the DrugBank dataset show that (1) it can give quantitative predictions of computational costs, typical mean relative errors can be less than 0.2 for DFT/TDDFT calculations with derivations of ±25% using the exactly pretrained ML models and (2) it can also be employed to various combinations of DFT functional and basis set cases without exactly pretrained ML models, while only slightly enlarge predicting errors.

show abstract

“…Multilevel graph convolutional neural network (MGCN), 65 similar to MPNN, has advantages in terms of generalizability and transferability.…”

Section: Implementationsmentioning

confidence: 99%

Forecasting System of Computational Time of DFT/TDDFT Calculations under the Multiverse Ansatz via Machine Learning and Cheminformatics

Zhang

et al. 2021

ACS Omega

View full text Add to dashboard Cite

show abstract

“…However, deep learning 70 can directly learn from low-level molecular structure information (e.g., atom types and bond types), and then gradually extract high-level representation through deep multiple neural network layers to predict targets. 43,61,[71][72][73][74][75][76][77][78][79][80][81][82][83][84][85][86] Since we can generally achieve acceptable performance in deep learning by 'focusing' on our target tasks, the information of ACSFs could be excluded from the input, instead we set ACSFs as one of the targets in the present DeepMoleNet model. Such ACSFs information could come from the training signals of the related tasks in the multi-task learning (MTL), which has been successfully used in many fields ranging from natural language processing and speech recognition, computer vision, and drug discovery.…”

Section: Deepmolenet Architecturementioning

confidence: 99%

Transferable Multi-level Attention Neural Network for Accurate Prediction of Quantum Chemistry Properties via Multi-task Learning

Liu¹,

Lin²,

Jia³

et al. 2021

Preprint

View full text Add to dashboard Cite

The development of efficient models for predicting specific properties through machine learning is of great importance for the innovation of chemistry and material science. However, predicting global electronic structure properties like frontier molecular orbital HOMO and LUMO energy levels and their HOMO-LUMO gaps from the small-sized molecule data to larger molecules remains a challenge. Here we develop a multi-level attention neural network, named DeepMoleNet, to enable chemical interpretable insights being fused into multi-task learning through (1) weighting contributions from various atoms and (2) taking the atom-centered symmetry functions (ACSFs) as the teacher descriptor. The efficient prediction of 12 properties including dipole moment, HOMO, and Gibbs free energy within chemical accuracy is achieved by using multiple benchmarks, both at the equilibrium and non-equilibrium geometries, including up to 110,000 records of data in QM9, 400,000 records in MD17 and 280,000 records in ANI-1ccx for random split evaluation. The good transferability for predicting larger molecules outside the training set is demonstrated in both equilibrium QM9 and Alchemy datasets at density functional theory (DFT) level. Additional tests on non-equilibrium molecular conformations from DFT-based MD17 dataset and ANI-1ccx dataset with coupled cluster accuracy as well as the public test sets of singlet fission molecules, biomolecules, long oligomers, and protein with up to 140 atoms show reasonable predictions for thermodynamics and electronic structure properties. The proposed multi-level attention neural network is applicable to high-throughput screening of numerous chemical species in both <a></a><a>equilibrium</a> and <a></a><a></a><a>non-equilibrium</a> molecular spaces to accelerate rational designs of drug-like molecules, material candidates, and chemical reactions.

show abstract

“…Graph neural networks (GNNs) result in state-of-the-art predictions on quantum mechanical properties, physicochemical properties, biological activity and toxicity. [1][2][3][4][5][6][7][8][9][10][11] To fairly evaluate the quality of different methods, Wu et al introduced MoleculeNet as a large-scale benchmark for molecular property prediction. 12 It provides multiple public data sets, data splitting, as well as high-quality implementation of popular algorithms of molecular featurization and learning algorithms.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Marginalized Graph Kernel and Message Passing Neural Network

Xiang

Tang²,

Lin³

et al. 2021

Preprint

View full text Add to dashboard Cite

This work presents a state-of-the-art hybrid kernel for molecular property predictions. The hybrid kernel consists of a marginalized graph kernel that operates on molecular graphs and radial basis function kernels that operate on global molecular features. Direct message passing neural network (D-MPNN) with global molecular features is used as strong baselines. After using Bayesian optimization to find the optimal hyperparameters, we benchmark the models on 11 publicly available data sets. Our results show that the prediction of the graph kernel is correlated to the prediction of D-MPNN, which indicates that the molecular representation learned from D-MPNN is very close to the reproducing kernel Hilbert space generated by the hybrid kernel. These results may provide clues for research on the interpretability of graph neural networks. In addition, ensembling the graph kernel models with D-MPNN is the best. The advantage of D-MPNN lies in computational efficiency, and the advantage of the graph kernel model lies in the inherent uncertainty qualification of Gaussian process regression. All codes for graph kernel machines used in this work can be found at <a href="https://github.com/Xiangyan93/Chem-Graph-Kernel-Machine">https://github.com/Xiangyan93/Chem-Graph-Kernel-Machine</a>.

show abstract

Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective

Cited by 138 publications

References 13 publications

Forecasting System of Computational Time of DFT/TDDFT Calculations under the Multiverse Ansatz via Machine Learning and Cheminformatics

Forecasting System of Computational Time of DFT/TDDFT Calculations under the Multiverse Ansatz via Machine Learning and Cheminformatics

Transferable Multi-level Attention Neural Network for Accurate Prediction of Quantum Chemistry Properties via Multi-task Learning

A Comparative Study of Marginalized Graph Kernel and Message Passing Neural Network

Contact Info

Product

Resources

About