Transformer neural network for protein-specific de novo drug generation as a machine translation problem

Abstract Drug discovery for a protein target is a very laborious, long and costly process. Machine learning approaches and, in particular, deep generative networks can substantially reduce development time and costs. However, the majority of methods imply prior knowledge of protein binders, their ph...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Daria Grechishnikova
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/1f6c9239101c4b9f8cd68c3e94e570ca
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1f6c9239101c4b9f8cd68c3e94e570ca
record_format	dspace
spelling	oai:doaj.org-article:1f6c9239101c4b9f8cd68c3e94e570ca2021-12-02T15:23:00ZTransformer neural network for protein-specific de novo drug generation as a machine translation problem10.1038/s41598-020-79682-42045-2322https://doaj.org/article/1f6c9239101c4b9f8cd68c3e94e570ca2021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-79682-4https://doaj.org/toc/2045-2322Abstract Drug discovery for a protein target is a very laborious, long and costly process. Machine learning approaches and, in particular, deep generative networks can substantially reduce development time and costs. However, the majority of methods imply prior knowledge of protein binders, their physicochemical characteristics or the three-dimensional structure of the protein. The method proposed in this work generates novel molecules with predicted ability to bind a target protein by relying on its amino acid sequence only. We consider target-specific de novo drug design as a translational problem between the amino acid “language” and simplified molecular input line entry system representation of the molecule. To tackle this problem, we apply Transformer neural network architecture, a state-of-the-art approach in sequence transduction tasks. Transformer is based on a self-attention technique, which allows the capture of long-range dependencies between items in sequence. The model generates realistic diverse compounds with structural novelty. The computed physicochemical properties and common metrics used in drug discovery fall within the plausible drug-like range of values.Daria GrechishnikovaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Daria Grechishnikova Transformer neural network for protein-specific de novo drug generation as a machine translation problem
description	Abstract Drug discovery for a protein target is a very laborious, long and costly process. Machine learning approaches and, in particular, deep generative networks can substantially reduce development time and costs. However, the majority of methods imply prior knowledge of protein binders, their physicochemical characteristics or the three-dimensional structure of the protein. The method proposed in this work generates novel molecules with predicted ability to bind a target protein by relying on its amino acid sequence only. We consider target-specific de novo drug design as a translational problem between the amino acid “language” and simplified molecular input line entry system representation of the molecule. To tackle this problem, we apply Transformer neural network architecture, a state-of-the-art approach in sequence transduction tasks. Transformer is based on a self-attention technique, which allows the capture of long-range dependencies between items in sequence. The model generates realistic diverse compounds with structural novelty. The computed physicochemical properties and common metrics used in drug discovery fall within the plausible drug-like range of values.
format	article
author	Daria Grechishnikova
author_facet	Daria Grechishnikova
author_sort	Daria Grechishnikova
title	Transformer neural network for protein-specific de novo drug generation as a machine translation problem
title_short	Transformer neural network for protein-specific de novo drug generation as a machine translation problem
title_full	Transformer neural network for protein-specific de novo drug generation as a machine translation problem
title_fullStr	Transformer neural network for protein-specific de novo drug generation as a machine translation problem
title_full_unstemmed	Transformer neural network for protein-specific de novo drug generation as a machine translation problem
title_sort	transformer neural network for protein-specific de novo drug generation as a machine translation problem
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/1f6c9239101c4b9f8cd68c3e94e570ca
work_keys_str_mv	AT dariagrechishnikova transformerneuralnetworkforproteinspecificdenovodruggenerationasamachinetranslationproblem
_version_	1718387312089366528

Transformer neural network for protein-specific de novo drug generation as a machine translation problem

Ejemplares similares