☆ 4.8 Article

Polymer graph neural networks for multitask property learning

NPJ COMPUTATIONAL MATERIALS (2023)

Related references

Note: Only part of the references are listed.

Article Biochemical Research Methods

Cross-dependent graph neural networks for molecular property prediction

Hehuan Ma et al.

Summary: This study explores a multi-view modeling approach (MVGNN) for molecular property prediction using graph neural networks (GNN). The approach considers both atom and bond information to provide more accurate predictions. The model's expressive power is enhanced through a cross-dependent message-passing scheme. Experimental results demonstrate that this approach outperforms state-of-the-art models on various benchmark tests.

BIOINFORMATICS (2022)

Add to Collection

Article Polymer Science

Canonicalizing BigSMILES for Polymers with Defined Backbones

Tzyy-Shyang Lin et al.

Summary: This paper proposes two strategies for deriving canonical representations for linear polymers and introduces a standardization scheme to address the issue of multiplicity in BigSMILES. The algorithms presented in this work provide text identifiers for chemical information systems and other polymer informatics applications.

ACS POLYMERS AU (2022)

Add to Collection

Article Polymer Science

Prediction and Interpretation of Polymer Properties Using the Graph Convolutional Network

Jaehong Park et al.

Summary: This study presents machine learning models based on the graph convolutional network (GCN) for predicting the thermal and mechanical properties of polymers. The GCN-based models perform well in predicting properties such as glass transition temperature, melting temperature, density, and elastic modulus, with the best performance observed for the glass transition temperature and the worst for the elastic modulus. The study shows that the GCN representations of polymers can provide prediction performances comparable to the popular extended-connectivity circular fingerprint (ECFP) representation. The combination of GCN and neural network regression slightly outperforms ECFP. The study investigates how GCN captures important structural features of polymers to learn their properties and finds that the representation space organization adaptively changes with training and through the neural network layers, facilitating the prediction of target properties based on the structure-property relationships. The study also demonstrates that GCN models can automatically extract backbone rigidity, which is strongly correlated with the glass transition temperature, and have the potential to predict other properties associated with backbone rigidity.

ACS POLYMERS AU (2022)

Add to Collection

Article Chemistry, Multidisciplinary

A graph representation of molecular ensembles for polymer property prediction

Matteo Aldeghi et al.

Summary: This study introduces a graph representation and graph neural network architecture for polymer property prediction. By constructing a large dataset of polymer materials and developing corresponding machine learning models, it achieves accurate capture of critical features and outperforms traditional cheminformatics methodologies.

CHEMICAL SCIENCE (2022)

Add to Collection

Article Chemistry, Medicinal

Benchmarking Machine Learning Models for Polymer Informatics: An Example of Glass Transition Temperature

Lei Tao et al.

Summary: The utilization of machine learning techniques in polymer informatics for evaluating properties such as glass transition temperature (T-g) has gained significant attention. A benchmark study was conducted to compare different ML models and explore key factors affecting the prediction of T-g, including structure representations, feature representations, and ML algorithms. This study not only provides guidance for Tg prediction, but also serves as a valuable reference for other polymer informatics tasks.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2021)

Add to Collection

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)

Add to Collection

Article Chemistry, Medicinal

XGraphBoost: Extracting Graph Neural Network-Based Features for a Better Prediction of Molecular Properties

Daiguo Deng et al.

Summary: The study explores how to automatically extract chemical molecule features using graph neural networks (GNN) and build an accurate prediction model of molecular properties by combining with the XGBoost classifier. Experimental results suggest that the proposed XGraphBoost framework can facilitate efficient and accurate predictions of various molecular properties.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2021)

Add to Collection

Article Chemistry, Multidisciplinary

Machine learning glass transition temperature of polymethacrylates

Yun Zhang et al.

Summary: This study focused on predicting the glass transition temperature Tg of polymethacrylates using a Gaussian process regression model, which successfully revealed the relationship between quantum chemical descriptors and Tg. By examining 37 samples with Tg ranging from 203K to 428K, the model demonstrated high stability and accuracy, contributing to fast and low-cost estimations of Tg.

MOLECULAR CRYSTALS AND LIQUID CRYSTALS (2021)

Add to Collection

Article Chemistry, Physical

Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials

Minyi Dai et al.

Summary: In this study, a graph neural network (GNN) model was developed to accurately predict the properties of polycrystalline materials, considering both individual grain features and their interactions. The model demonstrated low prediction error across diverse microstructures, showcasing its ability to predict accurately.

NPJ COMPUTATIONAL MATERIALS (2021)

Add to Collection

Article Chemistry, Physical

Benchmarking graph neural networks for materials chemistry

Victor Fung et al.

Summary: The study found that in the materials field, graph neural networks perform better and have more flexibility in input with compositionally diverse datasets compared to traditional models. However, GNNs also have some weaknesses, such as high data requirements, which need further improvement.

NPJ COMPUTATIONAL MATERIALS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Machine learning discovery of high-temperature polymers

Lei Tao et al.

Summary: By formulating a machine learning model, accurate predictions of the glass transition temperature for polymers with different molecular structures can be made, leading to the discovery of numerous promising candidates for high-temperature polymers.

PATTERNS (2021)

Add to Collection

Article Polymer Science

Machine learning glass transition temperature of polyacrylamides using quantum chemical descriptors

Yun Zhang et al.

Summary: Glass transition temperature, T-g, is an important thermophysical property of polyacrylamides that can be difficult and resource-intensive to determine. A Gaussian process regression model based on quantum chemical descriptors is developed to predict T-g, showing high stability and accuracy for fast and low-cost estimations.

POLYMER CHEMISTRY (2021)

Add to Collection

Article Multidisciplinary Sciences

U1 snRNP regulates cancer cell migration and invasion in vitro

Jung-Min Oh et al.

NATURE COMMUNICATIONS (2020)

Add to Collection

Article Materials Science, Multidisciplinary

Explainable Machine Learning Algorithms For Predicting Glass Transition Temperatures

Edesio Alcobaca et al.

ACTA MATERIALIA (2020)

Add to Collection

Article Multidisciplinary Sciences

Machine learning glass transition temperature of polymers

Yun Zhang et al.

HELIYON (2020)

Add to Collection

Article Physics, Applied

Machine-learning predictions of polymer properties with Polymer Genome

Huan Doan Tran et al.

JOURNAL OF APPLIED PHYSICS (2020)

Add to Collection

Article Chemistry, Physical

Automated exploration of the low-energy chemical space with fast quantum chemical methods

Philipp Pracht et al.

PHYSICAL CHEMISTRY CHEMICAL PHYSICS (2020)

Add to Collection

Article Chemistry, Multidisciplinary

Neural Networks Are Promising Tools for the Prediction of the Viscosity of Unsaturated Polyester Resins

Julien Molina et al.

FRONTIERS IN CHEMISTRY (2019)

Add to Collection

Article Chemistry, Physical

Machine-learning-assisted discovery of polymers with high thermal conductivity using a molecular design algorithm

Stephen Wu et al.

NPJ COMPUTATIONAL MATERIALS (2019)

Add to Collection

Article Chemistry, Physical

Machine learning enables polymer cloud-point engineering via inverse design

Jatin N. Kumar et al.

NPJ COMPUTATIONAL MATERIALS (2019)

Add to Collection

Article Chemistry, Multidisciplinary

BigSMILES: A Structurally-Based Line Notation for Describing Macromolecules

Tzyy-Shyang Lin et al.

ACS CENTRAL SCIENCE (2019)

Add to Collection

Article Engineering, Chemical

Supervised machine learning for prediction of zirconocene-catalyzed α-olefin polymerization

Benjamin A. Rizkin et al.

CHEMICAL ENGINEERING SCIENCE (2019)

Add to Collection

Review Chemistry, Multidisciplinary

How to explore chemical space using algorithms and automation

Piotr S. Gromski et al.

NATURE REVIEWS CHEMISTRY (2019)

Add to Collection

Article Chemistry, Physical

Tuning the molecular weight distribution from atom transfer radical polymerization using deep reinforcement learning

Haichen Li et al.

MOLECULAR SYSTEMS DESIGN & ENGINEERING (2018)

Add to Collection

Proceedings Paper Automation & Control Systems

PET Viscosity Prediction Using JIT-based Extreme Learning Machine

Zhenxing Li et al.

IFAC PAPERSONLINE (2018)

Add to Collection

Review Chemistry, Multidisciplinary

The Chemical Space Project

Jean-Louis Reymond

ACCOUNTS OF CHEMICAL RESEARCH (2015)

Add to Collection

Article Materials Science, Multidisciplinary

On representing chemical environments

Albert P. Bartok et al.

PHYSICAL REVIEW B (2013)

Add to Collection

Review Chemistry, Applied

Biodegradable Polyesters from Renewable Resources

Amy Tsui et al.

ANNUAL REVIEW OF CHEMICAL AND BIOMOLECULAR ENGINEERING, VOL 4 (2013)

Add to Collection

Article Physics, Multidisciplinary

Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning

Matthias Rupp et al.

PHYSICAL REVIEW LETTERS (2012)

Add to Collection

Review Biochemistry & Molecular Biology

Chemical space as a source for new drugs

Jean-Louis Reymond et al.

MEDCHEMCOMM (2010)

Add to Collection

© Peeref 2019-2024. All rights reserved.