Matches in SemOpenAlex for { <https://semopenalex.org/work/W3172000897> ?p ?o ?g. }
- W3172000897 abstract "Prediction of a molecule's 3D conformer ensemble from the molecular graph holds a key role in areas of cheminformatics and drug discovery. Existing generative models have several drawbacks including lack of modeling important molecular geometry elements (e.g. torsion angles), separate optimization stages prone to error accumulation, and the need for structure fine-tuning based on approximate classical force-fields or computationally expensive methods such as metadynamics with approximate quantum mechanics calculations at each geometry. We propose GeoMol--an end-to-end, non-autoregressive and SE(3)-invariant machine learning approach to generate distributions of low-energy molecular 3D conformers. Leveraging the power of message passing neural networks (MPNNs) to capture local and global graph information, we predict local atomic 3D structures and torsion angles, avoiding unnecessary over-parameterization of the geometric degrees of freedom (e.g. one angle per non-terminal bond). Such local predictions suffice both for the training loss computation, as well as for the full deterministic conformer assembly (at test time). We devise a non-adversarial optimal transport based loss function to promote diverse conformer generation. GeoMol predominantly outperforms popular open-source, commercial, or state-of-the-art machine learning (ML) models, while achieving significant speed-ups. We expect such differentiable 3D structure generators to significantly impact molecular modeling and related applications." @default.
- W3172000897 created "2021-06-22" @default.
- W3172000897 creator A5010124873 @default.
- W3172000897 creator A5011605758 @default.
- W3172000897 creator A5048915657 @default.
- W3172000897 creator A5051475129 @default.
- W3172000897 creator A5064290471 @default.
- W3172000897 creator A5071010920 @default.
- W3172000897 creator A5076162644 @default.
- W3172000897 date "2021-06-08" @default.
- W3172000897 modified "2023-09-27" @default.
- W3172000897 title "GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles" @default.
- W3172000897 cites W1548652691 @default.
- W3172000897 cites W1584733598 @default.
- W3172000897 cites W1974055727 @default.
- W3172000897 cites W1975622380 @default.
- W3172000897 cites W2012684279 @default.
- W3172000897 cites W2030971064 @default.
- W3172000897 cites W2060214544 @default.
- W3172000897 cites W2061583504 @default.
- W3172000897 cites W2071579644 @default.
- W3172000897 cites W2078374001 @default.
- W3172000897 cites W2080635178 @default.
- W3172000897 cites W2086106287 @default.
- W3172000897 cites W2090431249 @default.
- W3172000897 cites W2136567909 @default.
- W3172000897 cites W2147122257 @default.
- W3172000897 cites W2147421370 @default.
- W3172000897 cites W2148950790 @default.
- W3172000897 cites W2244785476 @default.
- W3172000897 cites W2271736303 @default.
- W3172000897 cites W2324419835 @default.
- W3172000897 cites W2606780347 @default.
- W3172000897 cites W2726184500 @default.
- W3172000897 cites W2761273232 @default.
- W3172000897 cites W2761786744 @default.
- W3172000897 cites W2766453196 @default.
- W3172000897 cites W2805516822 @default.
- W3172000897 cites W2884441791 @default.
- W3172000897 cites W2906744519 @default.
- W3172000897 cites W2932297636 @default.
- W3172000897 cites W2952317511 @default.
- W3172000897 cites W2962711740 @default.
- W3172000897 cites W2962767366 @default.
- W3172000897 cites W2963403868 @default.
- W3172000897 cites W2964015378 @default.
- W3172000897 cites W2966357564 @default.
- W3172000897 cites W2972246420 @default.
- W3172000897 cites W2992752586 @default.
- W3172000897 cites W2996443485 @default.
- W3172000897 cites W2999044305 @default.
- W3172000897 cites W3034806393 @default.
- W3172000897 cites W3035356236 @default.
- W3172000897 cites W3092617600 @default.
- W3172000897 cites W3105259638 @default.
- W3172000897 cites W3107666511 @default.
- W3172000897 cites W3111918841 @default.
- W3172000897 cites W3119095170 @default.
- W3172000897 cites W3126679164 @default.
- W3172000897 cites W3127173650 @default.
- W3172000897 cites W3133926737 @default.
- W3172000897 cites W3034219952 @default.
- W3172000897 hasPublicationYear "2021" @default.
- W3172000897 type Work @default.
- W3172000897 sameAs 3172000897 @default.
- W3172000897 citedByCount "3" @default.
- W3172000897 countsByYear W31720008972021 @default.
- W3172000897 crossrefType "posted-content" @default.
- W3172000897 hasAuthorship W3172000897A5010124873 @default.
- W3172000897 hasAuthorship W3172000897A5011605758 @default.
- W3172000897 hasAuthorship W3172000897A5048915657 @default.
- W3172000897 hasAuthorship W3172000897A5051475129 @default.
- W3172000897 hasAuthorship W3172000897A5064290471 @default.
- W3172000897 hasAuthorship W3172000897A5071010920 @default.
- W3172000897 hasAuthorship W3172000897A5076162644 @default.
- W3172000897 hasConcept C11413529 @default.
- W3172000897 hasConcept C121332964 @default.
- W3172000897 hasConcept C121864883 @default.
- W3172000897 hasConcept C134306372 @default.
- W3172000897 hasConcept C147597530 @default.
- W3172000897 hasConcept C154945302 @default.
- W3172000897 hasConcept C185592680 @default.
- W3172000897 hasConcept C186633575 @default.
- W3172000897 hasConcept C18705241 @default.
- W3172000897 hasConcept C202444582 @default.
- W3172000897 hasConcept C202615002 @default.
- W3172000897 hasConcept C32909587 @default.
- W3172000897 hasConcept C33923547 @default.
- W3172000897 hasConcept C41008148 @default.
- W3172000897 hasConcept C45374587 @default.
- W3172000897 hasConcept C59593255 @default.
- W3172000897 hasConcept C62520636 @default.
- W3172000897 hasConcept C68762167 @default.
- W3172000897 hasConcept C80444323 @default.
- W3172000897 hasConceptScore W3172000897C11413529 @default.
- W3172000897 hasConceptScore W3172000897C121332964 @default.
- W3172000897 hasConceptScore W3172000897C121864883 @default.
- W3172000897 hasConceptScore W3172000897C134306372 @default.
- W3172000897 hasConceptScore W3172000897C147597530 @default.
- W3172000897 hasConceptScore W3172000897C154945302 @default.