Neural graph distance embedding for molecular geometry generation

© 2024 The Authors. Journal of Computational Chemistry published by Wiley Periodicals LLC.

Détails bibliographiques
Publié dans:Journal of computational chemistry. - 1984. - 45(2024), 21 vom: 05. Aug., Seite 1784-1790
Auteur principal: Margraf, Johannes T (Auteur)
Format: Article en ligne
Langue:English
Publié: 2024
Accès à la collection:Journal of computational chemistry
Sujets:Journal Article conformers geometry prediction graph neural network machine learning
LEADER 01000caa a22002652c 4500
001 NLM371447410
003 DE-627
005 20250306031352.0
007 cr uuu---uuuuu
008 240426s2024 xx |||||o 00| ||eng c
024 7 |a 10.1002/jcc.27349  |2 doi 
028 5 2 |a pubmed25n1237.xml 
035 |a (DE-627)NLM371447410 
035 |a (NLM)38655845 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Margraf, Johannes T  |e verfasserin  |4 aut 
245 1 0 |a Neural graph distance embedding for molecular geometry generation 
264 1 |c 2024 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 20.07.2024 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a © 2024 The Authors. Journal of Computational Chemistry published by Wiley Periodicals LLC. 
520 |a This article introduces neural graph distance embedding (nGDE), a method for generating 3D molecular geometries. Leveraging a graph neural network trained on the OE62 dataset of molecular geometries, nGDE predicts interatomic distances based on molecular graphs. These distances are then used in multidimensional scaling to produce 3D geometries, subsequently refined with standard bioorganic forcefields. The machine learning-based graph distance introduced herein is found to be an improvement over the conventional shortest path distances used in graph drawing. Comparative analysis with a state-of-the-art distance geometry method demonstrates nGDE's competitive performance, particularly showcasing robustness in handling polycyclic molecules-a challenge for existing methods 
650 4 |a Journal Article 
650 4 |a conformers 
650 4 |a geometry prediction 
650 4 |a graph neural network 
650 4 |a machine learning 
773 0 8 |i Enthalten in  |t Journal of computational chemistry  |d 1984  |g 45(2024), 21 vom: 05. Aug., Seite 1784-1790  |w (DE-627)NLM098138448  |x 1096-987X  |7 nnas 
773 1 8 |g volume:45  |g year:2024  |g number:21  |g day:05  |g month:08  |g pages:1784-1790 
856 4 0 |u http://dx.doi.org/10.1002/jcc.27349  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 45  |j 2024  |e 21  |b 05  |c 08  |h 1784-1790