Mostrar el registro sencillo del ítem
dc.contributor.author
Fernandez, Ariel
dc.date.available
2021-10-25T13:54:44Z
dc.date.issued
2020-02-13
dc.identifier.citation
Fernandez, Ariel; Deep Learning Unravels a Dynamic Hierarchy While Empowering molecular Dynamics Simulations; Wiley VCH Verlag; Annalen Der Physik; 532; 3; 13-2-2020; 1-5; 1900526
dc.identifier.issn
0003-3804
dc.identifier.uri
http://hdl.handle.net/11336/144908
dc.description.abstract
Molecular dynamics (MD) provide predictive understanding of the behavior of condensed matter. However, its true potential remains largely untested because relevant timescales are often inaccessible, limited portions of conformation space get sampled, and infrequent events are usually irreproducible. A culprit is the huge informational burden required to iterate integration steps. To address the problem, deep learning is applied to encode the dynamics into a shorthand embodiment retaining only essential topological features of the vector field that steers MD integration. The flow is simplified via an equivalence relation that identifies conformations within basins of attraction in potential energy and encodes the dynamics onto a modulo-basin ?quotient space? where fast motions are averaged out. The quotient space projection enables coverage of realistic timescales while unraveling the underlying dynamic hierarchy. Deep learning is exploited to propagate the simplified trajectory beyond MD-accessible timescales and to reconstruct it at atomistic level. As shown, the quotient-encoding-propagating-decoding scheme generates within a few hours protein folding pathways with experimentally verified outcomes. By contrast, MD computations covering comparable timespans would take over a hundred days on special-purpose supercomputers. Thus, quotient space constitutes a model for hierarchical understanding of MD simulation while enabling access to realistic timescales.
dc.format
application/pdf
dc.language.iso
eng
dc.publisher
Wiley VCH Verlag
dc.rights
info:eu-repo/semantics/restrictedAccess
dc.rights.uri
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.subject
ARTIFICIAL INTELLIGENCE
dc.subject
BASIN OF ATTRACTION
dc.subject
DEEP LEARNING
dc.subject
MOLECULAR DYNAMICS
dc.subject
POTENTIAL ENERGY SURFACE
dc.subject
PROTEIN FOLDING PROBLEM
dc.subject
QUOTIENT SPACE
dc.subject.classification
Ciencias de la Información y Bioinformática
dc.subject.classification
Ciencias de la Computación e Información
dc.subject.classification
CIENCIAS NATURALES Y EXACTAS
dc.title
Deep Learning Unravels a Dynamic Hierarchy While Empowering molecular Dynamics Simulations
dc.type
info:eu-repo/semantics/article
dc.type
info:ar-repo/semantics/artículo
dc.type
info:eu-repo/semantics/publishedVersion
dc.date.updated
2021-02-18T15:44:25Z
dc.journal.volume
532
dc.journal.number
3
dc.journal.pagination
1-5; 1900526
dc.journal.pais
Alemania
dc.journal.ciudad
Weinheim
dc.description.fil
Fil: Fernandez, Ariel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Química del Sur. Universidad Nacional del Sur. Departamento de Química. Instituto de Química del Sur; Argentina
dc.journal.title
Annalen Der Physik
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1002/andp.201900526
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/https://onlinelibrary.wiley.com/doi/10.1002/andp.201900526
Archivos asociados