A merged molecular representation learning for molecular properties prediction with a web-based service

Abstract Deep learning has brought a dramatic development in molecular property prediction that is crucial in the field of drug discovery using various representations such as fingerprints, SMILES, and graphs. In particular, SMILES is used in various deep learning models via character-based approach...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hyunseob Kim, Jeongcheol Lee, Sunil Ahn, Jongsuk Ruth Lee
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/2993cc3aff2243a397e8e03b895d819d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2993cc3aff2243a397e8e03b895d819d
record_format	dspace
spelling	oai:doaj.org-article:2993cc3aff2243a397e8e03b895d819d2021-12-02T14:49:18ZA merged molecular representation learning for molecular properties prediction with a web-based service10.1038/s41598-021-90259-72045-2322https://doaj.org/article/2993cc3aff2243a397e8e03b895d819d2021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-90259-7https://doaj.org/toc/2045-2322Abstract Deep learning has brought a dramatic development in molecular property prediction that is crucial in the field of drug discovery using various representations such as fingerprints, SMILES, and graphs. In particular, SMILES is used in various deep learning models via character-based approaches. However, SMILES has a limitation in that it is hard to reflect chemical properties. In this paper, we propose a new self-supervised method to learn SMILES and chemical contexts of molecules simultaneously in pre-training the Transformer. The key of our model is learning structures with adjacency matrix embedding and learning logics that can infer descriptors via Quantitative Estimation of Drug-likeness prediction in pre-training. As a result, our method improves the generalization of the data and achieves the best average performance by benchmarking downstream tasks. Moreover, we develop a web-based fine-tuning service to utilize our model on various tasks.Hyunseob KimJeongcheol LeeSunil AhnJongsuk Ruth LeeNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Hyunseob Kim Jeongcheol Lee Sunil Ahn Jongsuk Ruth Lee A merged molecular representation learning for molecular properties prediction with a web-based service
description	Abstract Deep learning has brought a dramatic development in molecular property prediction that is crucial in the field of drug discovery using various representations such as fingerprints, SMILES, and graphs. In particular, SMILES is used in various deep learning models via character-based approaches. However, SMILES has a limitation in that it is hard to reflect chemical properties. In this paper, we propose a new self-supervised method to learn SMILES and chemical contexts of molecules simultaneously in pre-training the Transformer. The key of our model is learning structures with adjacency matrix embedding and learning logics that can infer descriptors via Quantitative Estimation of Drug-likeness prediction in pre-training. As a result, our method improves the generalization of the data and achieves the best average performance by benchmarking downstream tasks. Moreover, we develop a web-based fine-tuning service to utilize our model on various tasks.
format	article
author	Hyunseob Kim Jeongcheol Lee Sunil Ahn Jongsuk Ruth Lee
author_facet	Hyunseob Kim Jeongcheol Lee Sunil Ahn Jongsuk Ruth Lee
author_sort	Hyunseob Kim
title	A merged molecular representation learning for molecular properties prediction with a web-based service
title_short	A merged molecular representation learning for molecular properties prediction with a web-based service
title_full	A merged molecular representation learning for molecular properties prediction with a web-based service
title_fullStr	A merged molecular representation learning for molecular properties prediction with a web-based service
title_full_unstemmed	A merged molecular representation learning for molecular properties prediction with a web-based service
title_sort	merged molecular representation learning for molecular properties prediction with a web-based service
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/2993cc3aff2243a397e8e03b895d819d
work_keys_str_mv	AT hyunseobkim amergedmolecularrepresentationlearningformolecularpropertiespredictionwithawebbasedservice AT jeongcheollee amergedmolecularrepresentationlearningformolecularpropertiespredictionwithawebbasedservice AT sunilahn amergedmolecularrepresentationlearningformolecularpropertiespredictionwithawebbasedservice AT jongsukruthlee amergedmolecularrepresentationlearningformolecularpropertiespredictionwithawebbasedservice AT hyunseobkim mergedmolecularrepresentationlearningformolecularpropertiespredictionwithawebbasedservice AT jeongcheollee mergedmolecularrepresentationlearningformolecularpropertiespredictionwithawebbasedservice AT sunilahn mergedmolecularrepresentationlearningformolecularpropertiespredictionwithawebbasedservice AT jongsukruthlee mergedmolecularrepresentationlearningformolecularpropertiespredictionwithawebbasedservice
_version_	1718389499055046656

A merged molecular representation learning for molecular properties prediction with a web-based service

Ejemplares similares