Convolutional Neural Networks for the Design and Analysis of Non-Fullerene Acceptors
- 11 November 2019
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 59 (12) , 4993-5001
Abstract
Convolutional neural network (CNN) is employed to construct the generative and prediction models for the design and analysis of non-fullerene acceptors (NFAs) in organic solar cells. It is demonstrated that the dilated causal CNN can be trained as a good string-based molecular generation model and the diversity of generated NFAs is influenced by the depth of convolutional layers. In the property prediction model, the features of NFAs are extracted from the string representations by the dilated CNN. Specially, the attention mechanism is adopted to pool the extracted information, from which the contributions of fragments to molecular properties can be obtained by calculating the corresponding weighted sum. The promising NFAs among the predicted molecules are further verified by quantum chemistry calculations. The proposed generative, prediction models and the theoretical calculations perform as a complete cycle from molecular generation, property prediction to verification, which offers a strategy for the application of CNN in material discovery.Keywords
Funding Information
- National Natural Science Foundation of China (21573175, 21773191, 21833006)
This publication has 59 references indexed in Scilit:
- Organic light‐emitting diodes with enhanced out‐coupling efficiency using high‐refractive‐index glass fritJournal of the Society for Information Display, 2012
- Small Molecule Organic Semiconductors on the Move: Promises for Future Solar Energy TechnologyAngewandte Chemie International Edition, 2012
- Multiwfn: A multifunctional wavefunction analyzerJournal of Computational Chemistry, 2011
- Open Babel: An open chemical toolboxJournal of Cheminformatics, 2011
- Accelerated computational discovery of high-performance materials for organic photovoltaics by means of cheminformaticsEnergy & Environmental Science, 2011
- The Harvard Clean Energy Project: Large-Scale Computational Screening and Design of Organic Photovoltaics on the World Community GridThe Journal of Physical Chemistry Letters, 2011
- Extended-Connectivity FingerprintsJournal of Chemical Information and Modeling, 2010
- Design Rules for Donors in Bulk‐Heterojunction Solar Cells—Towards 10 % Energy‐Conversion EfficiencyAdvanced Materials, 2006
- Charge-Transfer and Energy-Transfer Processes in π-Conjugated Oligomers and Polymers: A Molecular PictureChemical Reviews, 2004
- NATURAL BOND ORBITALS AND EXTENSIONS OF LOCALIZED BONDING CONCEPTSChemistry Education Research and Practice, 2001