Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309367890> ?p ?o ?g. }
- W4309367890 endingPage "7750" @default.
- W4309367890 startingPage "7733" @default.
- W4309367890 abstract "Some recent advances in biomolecular simulation and global optimization have used hybrid restraint potentials, where harmonic restraints that penalize conformations inconsistent with experimental data are combined with molecular mechanics force fields. These hybrid potentials can be used to improve the performance of molecular dynamics, structure prediction, energy landscape sampling, and other computational methods that rely on the accuracy of the underlying force field. Here, we develop a hybrid restraint potential based on NapShift, an artificial neural network trained to predict protein nuclear magnetic resonance (NMR) chemical shifts from sequence and structure. In addition to providing accurate predictions of experimental chemical shifts, NapShift is fully differentiable with respect to atomic coordinates, which allows us to use it for structural refinement. By employing NapShift to predict chemical shifts from the protein conformation at each simulation step, we can compute an energy penalty and the corresponding hybrid restraint forces based on the difference between the predicted values and the experimental chemical shifts. The performance of the hybrid restraint potential was benchmarked using both basin-hopping global optimization and molecular dynamics simulations. In each case, the NapShift hybrid potential improved the accuracy, leading to better structure prediction via basin-hopping and increased local stability in molecular dynamics simulations. Our results suggest that neural network hybrid potentials based on NMR observables can enhance a broad range of molecular simulation methods, and the prediction accuracy will improve as more experimental training data become available." @default.
- W4309367890 created "2022-11-26" @default.
- W4309367890 creator A5012971931 @default.
- W4309367890 creator A5022301289 @default.
- W4309367890 creator A5029941351 @default.
- W4309367890 creator A5040770488 @default.
- W4309367890 creator A5042705612 @default.
- W4309367890 creator A5055444134 @default.
- W4309367890 creator A5075219459 @default.
- W4309367890 creator A5078520379 @default.
- W4309367890 creator A5085193434 @default.
- W4309367890 date "2022-11-17" @default.
- W4309367890 modified "2023-10-16" @default.
- W4309367890 title "Enhancing Biomolecular Simulations with Hybrid Potentials Incorporating NMR Data" @default.
- W4309367890 cites W1031578623 @default.
- W4309367890 cites W1536428180 @default.
- W4309367890 cites W1566214213 @default.
- W4309367890 cites W1773478864 @default.
- W4309367890 cites W1963871440 @default.
- W4309367890 cites W1964869994 @default.
- W4309367890 cites W1968588341 @default.
- W4309367890 cites W1969554454 @default.
- W4309367890 cites W1976499671 @default.
- W4309367890 cites W1979760008 @default.
- W4309367890 cites W1991037483 @default.
- W4309367890 cites W2004751437 @default.
- W4309367890 cites W2008850469 @default.
- W4309367890 cites W2011148270 @default.
- W4309367890 cites W2013785414 @default.
- W4309367890 cites W2018662121 @default.
- W4309367890 cites W2027408247 @default.
- W4309367890 cites W2028675432 @default.
- W4309367890 cites W2029120587 @default.
- W4309367890 cites W2031430816 @default.
- W4309367890 cites W2032697213 @default.
- W4309367890 cites W2035266068 @default.
- W4309367890 cites W2038344003 @default.
- W4309367890 cites W2041119019 @default.
- W4309367890 cites W2050272734 @default.
- W4309367890 cites W2051434435 @default.
- W4309367890 cites W2051669046 @default.
- W4309367890 cites W2051763485 @default.
- W4309367890 cites W2057477511 @default.
- W4309367890 cites W2064959295 @default.
- W4309367890 cites W2067174909 @default.
- W4309367890 cites W2068268759 @default.
- W4309367890 cites W2081246530 @default.
- W4309367890 cites W2082425146 @default.
- W4309367890 cites W2093381148 @default.
- W4309367890 cites W2094890103 @default.
- W4309367890 cites W2097164847 @default.
- W4309367890 cites W2099211347 @default.
- W4309367890 cites W2100736103 @default.
- W4309367890 cites W2103072162 @default.
- W4309367890 cites W2109154308 @default.
- W4309367890 cites W2115482276 @default.
- W4309367890 cites W2117000100 @default.
- W4309367890 cites W2118233996 @default.
- W4309367890 cites W2119301405 @default.
- W4309367890 cites W2122427541 @default.
- W4309367890 cites W2128572087 @default.
- W4309367890 cites W2130479394 @default.
- W4309367890 cites W2133179696 @default.
- W4309367890 cites W2147917253 @default.
- W4309367890 cites W2153865022 @default.
- W4309367890 cites W2156012420 @default.
- W4309367890 cites W2161605421 @default.
- W4309367890 cites W2162166182 @default.
- W4309367890 cites W2203031395 @default.
- W4309367890 cites W2313905315 @default.
- W4309367890 cites W2314362768 @default.
- W4309367890 cites W2319226565 @default.
- W4309367890 cites W2332712348 @default.
- W4309367890 cites W2415916782 @default.
- W4309367890 cites W2739328240 @default.
- W4309367890 cites W2756257742 @default.
- W4309367890 cites W2893591056 @default.
- W4309367890 cites W2909674173 @default.
- W4309367890 cites W2992829742 @default.
- W4309367890 cites W3010272512 @default.
- W4309367890 cites W3104575368 @default.
- W4309367890 cites W3104767865 @default.
- W4309367890 cites W3105621768 @default.
- W4309367890 cites W4210757594 @default.
- W4309367890 cites W4229743141 @default.
- W4309367890 doi "https://doi.org/10.1021/acs.jctc.2c00657" @default.
- W4309367890 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36395419" @default.
- W4309367890 hasPublicationYear "2022" @default.
- W4309367890 type Work @default.
- W4309367890 citedByCount "1" @default.
- W4309367890 countsByYear W43093678902022 @default.
- W4309367890 crossrefType "journal-article" @default.
- W4309367890 hasAuthorship W4309367890A5012971931 @default.
- W4309367890 hasAuthorship W4309367890A5022301289 @default.
- W4309367890 hasAuthorship W4309367890A5029941351 @default.
- W4309367890 hasAuthorship W4309367890A5040770488 @default.
- W4309367890 hasAuthorship W4309367890A5042705612 @default.
- W4309367890 hasAuthorship W4309367890A5055444134 @default.