Efficient generative modeling of protein sequences using simple autoregressive models

Deep learning is a powerful tool for the design of novel protein sequences, yet can be computationally very inefficient. Here the authors propose using simple forecasting models to efficiently generate a large number of novel protein structures.

Guardado en:
Detalles Bibliográficos
Autores principales: Jeanne Trinquier, Guido Uguzzoni, Andrea Pagnani, Francesco Zamponi, Martin Weigt
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/26264fe401544f27b9d9bdba0ab20a68
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:26264fe401544f27b9d9bdba0ab20a68
record_format dspace
spelling oai:doaj.org-article:26264fe401544f27b9d9bdba0ab20a682021-12-02T16:57:09ZEfficient generative modeling of protein sequences using simple autoregressive models10.1038/s41467-021-25756-42041-1723https://doaj.org/article/26264fe401544f27b9d9bdba0ab20a682021-10-01T00:00:00Zhttps://doi.org/10.1038/s41467-021-25756-4https://doaj.org/toc/2041-1723Deep learning is a powerful tool for the design of novel protein sequences, yet can be computationally very inefficient. Here the authors propose using simple forecasting models to efficiently generate a large number of novel protein structures.Jeanne TrinquierGuido UguzzoniAndrea PagnaniFrancesco ZamponiMartin WeigtNature PortfolioarticleScienceQENNature Communications, Vol 12, Iss 1, Pp 1-11 (2021)
institution DOAJ
collection DOAJ
language EN
topic Science
Q
spellingShingle Science
Q
Jeanne Trinquier
Guido Uguzzoni
Andrea Pagnani
Francesco Zamponi
Martin Weigt
Efficient generative modeling of protein sequences using simple autoregressive models
description Deep learning is a powerful tool for the design of novel protein sequences, yet can be computationally very inefficient. Here the authors propose using simple forecasting models to efficiently generate a large number of novel protein structures.
format article
author Jeanne Trinquier
Guido Uguzzoni
Andrea Pagnani
Francesco Zamponi
Martin Weigt
author_facet Jeanne Trinquier
Guido Uguzzoni
Andrea Pagnani
Francesco Zamponi
Martin Weigt
author_sort Jeanne Trinquier
title Efficient generative modeling of protein sequences using simple autoregressive models
title_short Efficient generative modeling of protein sequences using simple autoregressive models
title_full Efficient generative modeling of protein sequences using simple autoregressive models
title_fullStr Efficient generative modeling of protein sequences using simple autoregressive models
title_full_unstemmed Efficient generative modeling of protein sequences using simple autoregressive models
title_sort efficient generative modeling of protein sequences using simple autoregressive models
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/26264fe401544f27b9d9bdba0ab20a68
work_keys_str_mv AT jeannetrinquier efficientgenerativemodelingofproteinsequencesusingsimpleautoregressivemodels
AT guidouguzzoni efficientgenerativemodelingofproteinsequencesusingsimpleautoregressivemodels
AT andreapagnani efficientgenerativemodelingofproteinsequencesusingsimpleautoregressivemodels
AT francescozamponi efficientgenerativemodelingofproteinsequencesusingsimpleautoregressivemodels
AT martinweigt efficientgenerativemodelingofproteinsequencesusingsimpleautoregressivemodels
_version_ 1718382613536702464