Matches in SemOpenAlex for { <https://semopenalex.org/work/W3162926955> ?p ?o ?g. }
- W3162926955 abstract "We study a fundamental problem in computational chemistry known as molecular conformation generation, trying to predict stable 3D structures from 2D molecular graphs. Existing machine learning approaches usually first predict distances between atoms and then generate a 3D structure satisfying the distances, where noise in predicted distances may induce extra errors during 3D coordinate generation. Inspired by the traditional force field methods for molecular dynamics simulation, in this paper, we propose a novel approach called ConfGF by directly estimating the gradient fields of the log density of atomic coordinates. The estimated gradient fields allow directly generating stable conformations via Langevin dynamics. However, the problem is very challenging as the gradient fields are roto-translation equivariant. We notice that estimating the gradient fields of atomic coordinates can be translated to estimating the gradient fields of interatomic distances, and hence develop a novel algorithm based on recent score-based generative models to effectively estimate these gradients. Experimental results across multiple tasks show that ConfGF outperforms previous state-of-the-art baselines by a significant margin." @default.
- W3162926955 created "2021-05-24" @default.
- W3162926955 creator A5020430648 @default.
- W3162926955 creator A5024003882 @default.
- W3162926955 creator A5064112226 @default.
- W3162926955 creator A5077231313 @default.
- W3162926955 date "2021-05-09" @default.
- W3162926955 modified "2023-10-02" @default.
- W3162926955 title "Learning Gradient Fields for Molecular Conformation Generation" @default.
- W3162926955 cites W1548652691 @default.
- W3162926955 cites W1550061415 @default.
- W3162926955 cites W1971572370 @default.
- W3162926955 cites W2003250847 @default.
- W3162926955 cites W2013035813 @default.
- W3162926955 cites W2013979082 @default.
- W3162926955 cites W2030971064 @default.
- W3162926955 cites W2094278785 @default.
- W3162926955 cites W2167433878 @default.
- W3162926955 cites W2212660284 @default.
- W3162926955 cites W2244785476 @default.
- W3162926955 cites W2271736303 @default.
- W3162926955 cites W2290847742 @default.
- W3162926955 cites W2519887557 @default.
- W3162926955 cites W2527189750 @default.
- W3162926955 cites W2606780347 @default.
- W3162926955 cites W2726184500 @default.
- W3162926955 cites W2742127985 @default.
- W3162926955 cites W2761786744 @default.
- W3162926955 cites W2786722833 @default.
- W3162926955 cites W2788775653 @default.
- W3162926955 cites W2899771611 @default.
- W3162926955 cites W2904141086 @default.
- W3162926955 cites W2962711740 @default.
- W3162926955 cites W2963521729 @default.
- W3162926955 cites W2963711743 @default.
- W3162926955 cites W2964113829 @default.
- W3162926955 cites W2964121744 @default.
- W3162926955 cites W2964213081 @default.
- W3162926955 cites W2964378242 @default.
- W3162926955 cites W2971034910 @default.
- W3162926955 cites W2996443485 @default.
- W3162926955 cites W2996604169 @default.
- W3162926955 cites W3001935646 @default.
- W3162926955 cites W3024385728 @default.
- W3162926955 cites W3034227768 @default.
- W3162926955 cites W3034497530 @default.
- W3162926955 cites W3034806393 @default.
- W3162926955 cites W3073845700 @default.
- W3162926955 cites W3098052055 @default.
- W3162926955 cites W3100269082 @default.
- W3162926955 cites W3105013723 @default.
- W3162926955 cites W3105259638 @default.
- W3162926955 cites W3119095170 @default.
- W3162926955 cites W3121085039 @default.
- W3162926955 cites W3123726298 @default.
- W3162926955 cites W3128426889 @default.
- W3162926955 cites W3131204112 @default.
- W3162926955 cites W3034219952 @default.
- W3162926955 cites W3170835441 @default.
- W3162926955 doi "https://doi.org/10.48550/arxiv.2105.03902" @default.
- W3162926955 hasPublicationYear "2021" @default.
- W3162926955 type Work @default.
- W3162926955 sameAs 3162926955 @default.
- W3162926955 citedByCount "3" @default.
- W3162926955 countsByYear W31629269552021 @default.
- W3162926955 countsByYear W31629269552022 @default.
- W3162926955 countsByYear W31629269552023 @default.
- W3162926955 crossrefType "posted-content" @default.
- W3162926955 hasAuthorship W3162926955A5020430648 @default.
- W3162926955 hasAuthorship W3162926955A5024003882 @default.
- W3162926955 hasAuthorship W3162926955A5064112226 @default.
- W3162926955 hasAuthorship W3162926955A5077231313 @default.
- W3162926955 hasBestOaLocation W31629269551 @default.
- W3162926955 hasConcept C104317684 @default.
- W3162926955 hasConcept C105580179 @default.
- W3162926955 hasConcept C11413529 @default.
- W3162926955 hasConcept C121332964 @default.
- W3162926955 hasConcept C121864883 @default.
- W3162926955 hasConcept C147597530 @default.
- W3162926955 hasConcept C149364088 @default.
- W3162926955 hasConcept C154945302 @default.
- W3162926955 hasConcept C185592680 @default.
- W3162926955 hasConcept C202444582 @default.
- W3162926955 hasConcept C2780004032 @default.
- W3162926955 hasConcept C33923547 @default.
- W3162926955 hasConcept C41008148 @default.
- W3162926955 hasConcept C55493867 @default.
- W3162926955 hasConcept C59593255 @default.
- W3162926955 hasConcept C9652623 @default.
- W3162926955 hasConceptScore W3162926955C104317684 @default.
- W3162926955 hasConceptScore W3162926955C105580179 @default.
- W3162926955 hasConceptScore W3162926955C11413529 @default.
- W3162926955 hasConceptScore W3162926955C121332964 @default.
- W3162926955 hasConceptScore W3162926955C121864883 @default.
- W3162926955 hasConceptScore W3162926955C147597530 @default.
- W3162926955 hasConceptScore W3162926955C149364088 @default.
- W3162926955 hasConceptScore W3162926955C154945302 @default.
- W3162926955 hasConceptScore W3162926955C185592680 @default.
- W3162926955 hasConceptScore W3162926955C202444582 @default.
- W3162926955 hasConceptScore W3162926955C2780004032 @default.