FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203669164> ?p ?o ?g. }

• W3203669164 abstract "Abstract Graph representations are traditionally used to represent protein structures in sequence design protocols where the folding pattern 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. This use case is motivating because it allows larger protein design problems to fit onto near-term quantum computers. 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 problem size of our use case by more than a factor of 3. Additionally, XENet displayed an ability to handle deeper architectures than competing convolutions. Author summary Graphs data structures are ubiquitous in the field of protein design and are at the core of the recent advances in artificial intelligence brought forth by graph neural networks (GNNs). GNNs have led to some impressive results in modeling protein interactions, but are not as common as other tensor representations. Most GNN architectures tend to put little to no emphasis on the information stored on edges; however, protein modeling tools often use edges to represent vital geometric relationships about residue pair interactions. In this paper, we show that a more advanced processing of edge attributes can lead to considerable benefits when modeling chemical data. We introduce XENet, a new member of the GNN family that is shown to have improved ability to model protein residue environments based on chemical and geometric data. We use XENet to intelligently simplify the optimization problem that is solved when designing proteins. This task is important to us and others because it allows larger proteins to be designed on near-term quantum computers. We show that XENet is able to train on our protein modeling data better than existing methods, successfully resulting in a dramatic decrease in protein design sample space with no loss in quality." @default.
• W3203669164 created "2021-10-11" @default.
• W3203669164 creator A5006974299 @default.
• W3203669164 creator A5023257622 @default.
• W3203669164 creator A5056012636 @default.
• W3203669164 creator A5057725187 @default.
• W3203669164 creator A5063275405 @default.
• W3203669164 date "2021-05-05" @default.
• W3203669164 modified "2023-10-17" @default.
• W3203669164 title "XENet: Using a new graph convolution to accelerate the timeline for protein design on quantum computers" @default.
• W3203669164 cites W1501856433 @default.
• W3203669164 cites W1677182931 @default.
• W3203669164 cites W1969644422 @default.
• W3203669164 cites W1992426410 @default.
• W3203669164 cites W2015403140 @default.
• W3203669164 cites W2135815512 @default.
• W3203669164 cites W2151581834 @default.
• W3203669164 cites W2166681504 @default.
• W3203669164 cites W2201713963 @default.
• W3203669164 cites W2345914382 @default.
• W3203669164 cites W2472466887 @default.
• W3203669164 cites W2519539312 @default.
• W3203669164 cites W2538176089 @default.
• W3203669164 cites W2606202972 @default.
• W3203669164 cites W2766856748 @default.
• W3203669164 cites W2797944611 @default.
• W3203669164 cites W2809583854 @default.
• W3203669164 cites W2944245644 @default.
• W3203669164 cites W2951256120 @default.
• W3203669164 cites W2956569764 @default.
• W3203669164 cites W2963396480 @default.
• W3203669164 cites W2968494487 @default.
• W3203669164 cites W2970291663 @default.
• W3203669164 cites W2996986155 @default.
• W3203669164 cites W2997035976 @default.
• W3203669164 cites W2997494090 @default.
• W3203669164 cites W2998116736 @default.
• W3203669164 cites W2998737920 @default.
• W3203669164 cites W3014805132 @default.
• W3203669164 cites W3015047409 @default.
• W3203669164 cites W3036016037 @default.
• W3203669164 cites W3044773187 @default.
• W3203669164 cites W3098128018 @default.
• W3203669164 cites W3100159300 @default.
• W3203669164 cites W3104097946 @default.
• W3203669164 cites W3104488039 @default.
• W3203669164 cites W3105738938 @default.
• W3203669164 cites W3117548275 @default.
• W3203669164 cites W4289436753 @default.
• W3203669164 doi "https://doi.org/10.1101/2021.05.05.442729" @default.
• W3203669164 hasPublicationYear "2021" @default.
• W3203669164 type Work @default.
• W3203669164 sameAs 3203669164 @default.
• W3203669164 citedByCount "1" @default.
• W3203669164 countsByYear W32036691642023 @default.
• W3203669164 crossrefType "posted-content" @default.
• W3203669164 hasAuthorship W3203669164A5006974299 @default.
• W3203669164 hasAuthorship W3203669164A5023257622 @default.
• W3203669164 hasAuthorship W3203669164A5056012636 @default.
• W3203669164 hasAuthorship W3203669164A5057725187 @default.
• W3203669164 hasAuthorship W3203669164A5063275405 @default.
• W3203669164 hasBestOaLocation W32036691641 @default.
• W3203669164 hasConcept C115903868 @default.
• W3203669164 hasConcept C132525143 @default.
• W3203669164 hasConcept C138885662 @default.
• W3203669164 hasConcept C154945302 @default.
• W3203669164 hasConcept C2779808786 @default.
• W3203669164 hasConcept C41008148 @default.
• W3203669164 hasConcept C41895202 @default.
• W3203669164 hasConcept C55166926 @default.
• W3203669164 hasConcept C80444323 @default.
• W3203669164 hasConceptScore W3203669164C115903868 @default.
• W3203669164 hasConceptScore W3203669164C132525143 @default.
• W3203669164 hasConceptScore W3203669164C138885662 @default.
• W3203669164 hasConceptScore W3203669164C154945302 @default.
• W3203669164 hasConceptScore W3203669164C2779808786 @default.
• W3203669164 hasConceptScore W3203669164C41008148 @default.
• W3203669164 hasConceptScore W3203669164C41895202 @default.
• W3203669164 hasConceptScore W3203669164C55166926 @default.
• W3203669164 hasConceptScore W3203669164C80444323 @default.
• W3203669164 hasLocation W32036691641 @default.
• W3203669164 hasLocation W32036691642 @default.
• W3203669164 hasLocation W32036691643 @default.
• W3203669164 hasOpenAccess W3203669164 @default.
• W3203669164 hasPrimaryLocation W32036691641 @default.
• W3203669164 hasRelatedWork W1523525818 @default.
• W3203669164 hasRelatedWork W1585932355 @default.
• W3203669164 hasRelatedWork W2073666908 @default.
• W3203669164 hasRelatedWork W2368629829 @default.
• W3203669164 hasRelatedWork W2391431582 @default.
• W3203669164 hasRelatedWork W2392953011 @default.
• W3203669164 hasRelatedWork W2474469336 @default.
• W3203669164 hasRelatedWork W3194701996 @default.
• W3203669164 hasRelatedWork W3211088295 @default.
• W3203669164 hasRelatedWork W51861053 @default.
• W3203669164 isParatext "false" @default.
• W3203669164 isRetracted "false" @default.
• W3203669164 magId "3203669164" @default.
• W3203669164 workType "article" @default.