Graph Convolutional Neural Networks for Polymers Property Prediction

A fast and accurate predictive tool for polymer properties is demanding and will pave the way to iterative inverse design. In this work, we apply graph convolutional neural networks (GCNN) to predict the dielectric constant and energy bandgap of polymers. Using density functional theory (DFT) calculated properties as the ground truth, GCNN can achieve remarkable agreement with DFT results. Moreover, we show that GCNN outperforms other machine learning algorithms. Our work proves that GCNN relies only on morphological data of polymers and removes the requirement for complicated hand-crafted descriptors, while still offering accuracy in fast predictions.

[1]  Anand Chandrasekaran,et al.  Polymer Genome: A Data-Powered Polymer Informatics Platform for Property Predictions , 2018, The Journal of Physical Chemistry C.

[2]  Martina H. Stenzel,et al.  Complex polymer architectures via RAFT polymerization: From fundamental process to extending the scope using click chemistry and nature's building blocks , 2012 .

[3]  Alán Aspuru-Guzik,et al.  Reinforced Adversarial Neural Computer for de Novo Molecular Design , 2018, J. Chem. Inf. Model..

[4]  Arun Mannodi-Kanakkithodi,et al.  Critical assessment of regression-based machine learning methods for polymer dielectrics , 2016 .

[5]  Tian Xie,et al.  Hierarchical Visualization of Materials Space with Graph Convolutional Neural Networks , 2018, The Journal of chemical physics.

[6]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[7]  Jeffrey C Grossman,et al.  Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties. , 2017, Physical review letters.

[8]  Arun Mannodi-Kanakkithodi,et al.  Machine Learning Strategy for Accelerated Design of Polymer Dielectrics , 2016, Scientific Reports.

[9]  Arun Mannodi-Kanakkithodi,et al.  Scoping the polymer genome: A roadmap for rational polymer dielectrics design and beyond , 2017, Materials Today.

[10]  Arun Mannodi-Kanakkithodi,et al.  Mining materials design rules from data: The example of polymer dielectrics , 2017 .

[11]  Raymond B. Seymour,et al.  Structure-property relationships in polymers , 1984 .

[12]  Alán Aspuru-Guzik,et al.  The Harvard Clean Energy Project: Large-Scale Computational Screening and Design of Organic Photovoltaics on the World Community Grid , 2011 .

[13]  Chiho Kim,et al.  A polymer dataset for accelerated property prediction and design , 2016, Scientific Data.

[14]  Kyle Chard,et al.  Matminer: An open source toolkit for materials data mining , 2018, Computational Materials Science.

[15]  Alán Aspuru-Guzik,et al.  Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules , 2016, ACS central science.

[16]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.