XENet: Using a new graph convolution to accelerate the timeline for protein design on quantum computers.

Graph representations are traditionally used to represent protein structures in sequence design protocols in which the protein backbone conformation is known. This infrequently extends to machine learning projects: existing graph convolution algorithms have shortcomings when representing protein env...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jack B Maguire, Daniele Grattarola, Vikram Khipple Mulligan, Eugene Klyshko, Hans Melo
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/ae2e6f980baa4986ab84f8a0397965c3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ae2e6f980baa4986ab84f8a0397965c3
record_format	dspace
spelling	oai:doaj.org-article:ae2e6f980baa4986ab84f8a0397965c32021-12-02T19:58:13ZXENet: Using a new graph convolution to accelerate the timeline for protein design on quantum computers.1553-734X1553-735810.1371/journal.pcbi.1009037https://doaj.org/article/ae2e6f980baa4986ab84f8a0397965c32021-09-01T00:00:00Zhttps://doi.org/10.1371/journal.pcbi.1009037https://doaj.org/toc/1553-734Xhttps://doaj.org/toc/1553-7358Graph representations are traditionally used to represent protein structures in sequence design protocols in which the protein backbone conformation is known. This infrequently extends to machine learning projects: existing graph convolution algorithms have shortcomings when representing protein environments. One reason for this is the lack of emphasis on edge attributes during massage-passing operations. Another reason is the traditionally shallow nature of graph neural network architectures. Here we introduce an improved message-passing operation that is better equipped to model local kinematics problems such as protein design. Our approach, XENet, pays special attention to both incoming and outgoing edge attributes. We compare XENet against existing graph convolutions in an attempt to decrease rotamer sample counts in Rosetta's rotamer substitution protocol, used for protein side-chain optimization and sequence design. This use case is motivating because it both reduces the size of the search space for classical side-chain optimization algorithms, and allows larger protein design problems to be solved with quantum algorithms on near-term quantum computers with limited qubit counts. XENet outperformed competing models while also displaying a greater tolerance for deeper architectures. We found that XENet was able to decrease rotamer counts by 40% without loss in quality. This decreased the memory consumption for classical pre-computation of rotamer energies in our use case by more than a factor of 3, the qubit consumption for an existing sequence design quantum algorithm by 40%, and the size of the solution space by a factor of 165. Additionally, XENet displayed an ability to handle deeper architectures than competing convolutions.Jack B MaguireDaniele GrattarolaVikram Khipple MulliganEugene KlyshkoHans MeloPublic Library of Science (PLoS)articleBiology (General)QH301-705.5ENPLoS Computational Biology, Vol 17, Iss 9, p e1009037 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Biology (General) QH301-705.5
spellingShingle	Biology (General) QH301-705.5 Jack B Maguire Daniele Grattarola Vikram Khipple Mulligan Eugene Klyshko Hans Melo XENet: Using a new graph convolution to accelerate the timeline for protein design on quantum computers.
description	Graph representations are traditionally used to represent protein structures in sequence design protocols in which the protein backbone conformation is known. This infrequently extends to machine learning projects: existing graph convolution algorithms have shortcomings when representing protein environments. One reason for this is the lack of emphasis on edge attributes during massage-passing operations. Another reason is the traditionally shallow nature of graph neural network architectures. Here we introduce an improved message-passing operation that is better equipped to model local kinematics problems such as protein design. Our approach, XENet, pays special attention to both incoming and outgoing edge attributes. We compare XENet against existing graph convolutions in an attempt to decrease rotamer sample counts in Rosetta's rotamer substitution protocol, used for protein side-chain optimization and sequence design. This use case is motivating because it both reduces the size of the search space for classical side-chain optimization algorithms, and allows larger protein design problems to be solved with quantum algorithms on near-term quantum computers with limited qubit counts. XENet outperformed competing models while also displaying a greater tolerance for deeper architectures. We found that XENet was able to decrease rotamer counts by 40% without loss in quality. This decreased the memory consumption for classical pre-computation of rotamer energies in our use case by more than a factor of 3, the qubit consumption for an existing sequence design quantum algorithm by 40%, and the size of the solution space by a factor of 165. Additionally, XENet displayed an ability to handle deeper architectures than competing convolutions.
format	article
author	Jack B Maguire Daniele Grattarola Vikram Khipple Mulligan Eugene Klyshko Hans Melo
author_facet	Jack B Maguire Daniele Grattarola Vikram Khipple Mulligan Eugene Klyshko Hans Melo
author_sort	Jack B Maguire
title	XENet: Using a new graph convolution to accelerate the timeline for protein design on quantum computers.
title_short	XENet: Using a new graph convolution to accelerate the timeline for protein design on quantum computers.
title_full	XENet: Using a new graph convolution to accelerate the timeline for protein design on quantum computers.
title_fullStr	XENet: Using a new graph convolution to accelerate the timeline for protein design on quantum computers.
title_full_unstemmed	XENet: Using a new graph convolution to accelerate the timeline for protein design on quantum computers.
title_sort	xenet: using a new graph convolution to accelerate the timeline for protein design on quantum computers.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/ae2e6f980baa4986ab84f8a0397965c3
work_keys_str_mv	AT jackbmaguire xenetusinganewgraphconvolutiontoacceleratethetimelineforproteindesignonquantumcomputers AT danielegrattarola xenetusinganewgraphconvolutiontoacceleratethetimelineforproteindesignonquantumcomputers AT vikramkhipplemulligan xenetusinganewgraphconvolutiontoacceleratethetimelineforproteindesignonquantumcomputers AT eugeneklyshko xenetusinganewgraphconvolutiontoacceleratethetimelineforproteindesignonquantumcomputers AT hansmelo xenetusinganewgraphconvolutiontoacceleratethetimelineforproteindesignonquantumcomputers
_version_	1718375795389366272

XENet: Using a new graph convolution to accelerate the timeline for protein design on quantum computers.

Ejemplares similares