SMICLR: Contrastive Learning on Multiple Molecular Representations for Semisupervised and Unsupervised Representation Learning
- 31 August 2022
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 62 (17) , 3948-3960
Abstract
Machine learning as a tool for chemical space exploration broadens horizons to work with known and unknown molecules. At its core lies molecular representation, an essential key to improve learning about structure-property relationships. Recently, contrastive frameworks have been showing impressive results for representation learning in diverse domains. Therefore, this paper proposes a contrastive framework that embraces multimodal molecular data. Specifically, our approach jointly trains a graph encoder and an encoder for the simplified molecular-input line-entry system (SMILES) string to perform the contrastive learning objective. Since SMILES is the basis of our method, i.e., we built the molecular graph from the SMILES, we call our framework as SMILES Contrastive Learning (SMICLR). When stacking a nonlinear regressor on the SMICLR's pretrained encoder and fine-tuning the entire model, we reduced the prediction error by, on average, 44% and 25% for the energetic and electronic properties of the QM9 data set, respectively, over the supervised baseline. We further improved our framework's performance when applying data augmentations in each molecular-input representation. Moreover, SMICLR demonstrated competitive representation learning results in an unsupervised setting.Keywords
Funding Information
- Ag?ncia Nacional do Petr?leo, G?s Natural e Biocombust?veis
- Funda??o de Amparo ? Pesquisa do Estado de S?o Paulo (2017/11631 2, 2018/21401 7, 2021/08852-2)
This publication has 62 references indexed in Scilit:
- Convolutional Embedding of Attributed Molecular Graphs for Physical Property PredictionJournal of Chemical Information and Modeling, 2017
- node2vec2016
- Deep Graph Kernels2015
- Quantum chemistry structures and properties of 134 kilo moleculesScientific Data, 2014
- Open Babel: An open chemical toolboxJournal of Cheminformatics, 2011
- Extended-Connectivity FingerprintsJournal of Chemical Information and Modeling, 2010
- Protein function prediction via graph kernelsBioinformatics, 2005
- Distinguishing Enzyme Structures from Non-enzymes Without AlignmentsJournal of Molecular Biology, 2003
- Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. Correlation with molecular orbital energies and hydrophobicityJournal of Medicinal Chemistry, 1991
- SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rulesJournal of Chemical Information and Computer Sciences, 1988