4.7 Article

Accurate Prediction of Aqueous Free Solvation Energies Using 3D Atomic Feature-Based Graph Neural Network with Transfer Learning

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Engineering, Environmental

Transfer learning for solvation free energies: From quantum chemistry to experiments

Florence H. Vermeire et al.

Summary: In this work, a transfer learning approach combining quantum calculations and experimental measurements is proposed for the prediction of solvation free energies, showing significant advantages for new data, small datasets and out-of-sample predictions. The pre-trained models based on quantum calculations demonstrate improved out-of-sample performance, with a mean absolute error of 0.21 kcal/mol achieved on random test splits.

CHEMICAL ENGINEERING JOURNAL (2021)

Article Chemistry, Medicinal

Transferable Multilevel Attention Neural Network for Accurate Prediction of Quantum Chemistry Properties via Multitask Learning

Ziteng Liu et al.

Summary: DeepMoleNet is a multilevel attention neural network that efficiently predicts 12 properties, including dipole moment, HOMO, and Gibbs free energy, demonstrating good transferability for high-throughput screening of chemical species in both equilibrium and nonequilibrium molecular spaces.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2021)

Article Chemistry, Medicinal

Dataset Construction to Explore Chemical Space with 3D Geometry and Deep Learning

Jianing Lu et al.

Summary: A dataset is crucial for the development of deep learning models, and the new Frag20 dataset with optimized 3D geometries and calculated molecular properties contributes to the development of robust molecular energy prediction models that achieve near chemical accuracy.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2021)

Article Chemistry, Multidisciplinary

Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models

Dejun Jiang et al.

Summary: This study compared the predictive capacity and computational efficiency of descriptor-based models and graph-based models for molecular property prediction. The results showed that descriptor-based models generally outperform graph-based models in terms of prediction accuracy and computational efficiency. SVM performs the best for regression tasks, while RF and XGBoost are reliable for classification tasks.

JOURNAL OF CHEMINFORMATICS (2021)

Article Chemistry, Physical

Machine learning of free energies in chemical compound space using ensemble representations: Reaching experimental uncertainty for solvation

Jan Weinreich et al.

Summary: The Free energy Machine Learning (FML) model accurately predicts hydration free energies for chemical compounds, with prediction errors decreasing systematically with training set size and reaching experimental uncertainty levels after training on 80% of the FreeSolv database. FML's accuracy is comparable to state-of-the-art physics-based approaches, and it requires molecular dynamics runs to generate input representations for new query compounds. The model showcases usefulness in analyzing solvation free energies and identifying structure-property relationships for a large number of organic molecules.

JOURNAL OF CHEMICAL PHYSICS (2021)

Article Multidisciplinary Sciences

Improved prediction of solvation free energies by machine-learning polarizable continuum solvation model

Amin Alibakhshi et al.

Summary: Accurate theoretical evaluation of solvation free energy is challenging. Here the authors introduce a machine-learning based polarizable continuum solvation approach to improve the accuracy of widely accepted continuum solvation models by almost one order of magnitude without additional computational costs.

NATURE COMMUNICATIONS (2021)

Article Multidisciplinary Sciences

Algebraic graph-assisted bidirectional transformers for molecular property prediction

Dong Chen et al.

Summary: Researchers proposed an algebraic graph-assisted bidirectional transformer framework, which can integrate massive unlabeled molecular data into molecular representations via a self-supervised learning strategy and incorporate 3D stereochemical information from graphs, showing state-of-the-art performance in molecular property prediction.

NATURE COMMUNICATIONS (2021)

Article Biochemistry & Molecular Biology

Binding affinity and mechanisms of SARS-CoV-2 variants

Yanqiang Han et al.

Summary: This study investigated the effects of residue mutations in the S glycoprotein of SARS-CoV-2 on binding affinity using molecular dynamics simulations and sequence analysis. The findings demonstrated varying degrees of enhancements in binding affinity for different variants, providing a basis for further research on virus mutations.

COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL (2021)

Article Computer Science, Artificial Intelligence

Out-of-the-box deep learning prediction of pharmaceutical properties by broadly learned knowledge-based molecular representations

Wan Xiang Shen et al.

Summary: The study demonstrates that combining human knowledge-based molecular representations with convolutional neural networks can enhance deep learning of pharmaceutical properties. By extensively learning molecular descriptors and fingerprint features, the MolMap method was developed and MolMapNet models were constructed, which outperformed other models on various benchmark datasets and a novel dataset.

NATURE MACHINE INTELLIGENCE (2021)

Article Computer Science, Interdisciplinary Applications

DScribe: Library of descriptors for machine learning in materials science

Lauri Himanen et al.

COMPUTER PHYSICS COMMUNICATIONS (2020)

Article Chemistry, Medicinal

Pushing the Boundaries of Molecular Representation for Drug Discovery with the Graph Attention Mechanism

Zhaoping Xiong et al.

JOURNAL OF MEDICINAL CHEMISTRY (2020)

Article Chemistry, Multidisciplinary

Inductive transfer learning for molecular activity prediction: Next-Gen QSAR Models with MolPMoFiT

Xinhao Li et al.

JOURNAL OF CHEMINFORMATICS (2020)

Article Chemistry, Medicinal

Transfer Learning for Drug Discovery

Chenjing Cai et al.

JOURNAL OF MEDICINAL CHEMISTRY (2020)

Review Chemistry, Medicinal

Deep Learning in Chemistry

Adam C. Mater et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2019)

Article Chemistry, Medicinal

Analyzing Learned Molecular Representations for Property Prediction

Kevin Yang et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2019)

Article Chemistry, Physical

SchNetPack: A Deep Learning Toolbox For Atomistic Systems

K. T. Schutt et al.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2019)

Review Thermodynamics

Approaches for Calculating Solvation Free Energies and Enthalpies Demonstrated with an Update of the FreeSolv Database

Guilherme Duarte Ramos Matos et al.

JOURNAL OF CHEMICAL AND ENGINEERING DATA (2017)

Review Chemistry, Medicinal

Role of Solvation in Drug Design as Revealed by the Statistical Mechanics Integral Equation Theory of Liquids

Norio Yoshida

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2017)

Article Chemistry, Medicinal

In Silico Prediction of Physicochemical Properties of Environmental Chemicals Using Molecular Fingerprints and Machine Learning

Qingda Zang et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2017)

Article Chemistry, Medicinal

Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction

Connor W. Coley et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2017)

Article Chemistry, Physical

Comparison of Implicit and Explicit Solvent Models for the Calculation of Solvation Free Energy in Organic Solvents

Jin Zhang et al.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2017)

Article Multidisciplinary Sciences

Quantum-chemical insights from deep tensor neural networks

Kristof T. Schuett et al.

NATURE COMMUNICATIONS (2017)

Article Biochemistry & Molecular Biology

Molecular graph convolutions: moving beyond fingerprints

Steven Kearnes et al.

JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN (2016)

Article Chemistry, Medicinal

Better Informed Distance Geometry: Using What We Know To Improve Conformation Generation

Sereina Riniker et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2015)

Article Biochemical Research Methods

Computational prediction of octanol-water partition coefficient based on the extended solvent-contact model

Taeho Kim et al.

JOURNAL OF MOLECULAR GRAPHICS & MODELLING (2015)

Article Chemistry, Physical

Calculation of Solvation Free Energies with DCOSMO-RS

Andreas Klamt et al.

JOURNAL OF PHYSICAL CHEMISTRY A (2015)

Article Biochemistry & Molecular Biology

FreeSolv: a database of experimental and calculated hydration free energies, with input files

David L. Mobley et al.

JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN (2014)

Article Medicine, Research & Experimental

Thermodynamic Approaches to the Challenges of Solubility in Drug Discovery and Development

German L. Perlovich

MOLECULAR PHARMACEUTICS (2014)

Article Chemistry, Physical

Atom-centered symmetry functions for constructing high-dimensional neural network potentials

Joerg Behler

JOURNAL OF CHEMICAL PHYSICS (2011)

Review Chemistry, Applied

COSMO-RS: An Alternative to Simulation for Calculating Thermodynamic Properties of Liquid Mixtures

Andreas Klamt et al.

ANNUAL REVIEW OF CHEMICAL AND BIOMOLECULAR ENGINEERING, VOL 1 (2010)

Article Chemistry, Medicinal

Predicting small-molecule solvation free energies: An informal blind test for computational chemistry

Anthony Nicholls et al.

JOURNAL OF MEDICINAL CHEMISTRY (2008)