Show simple item record

dc.contributor.authorLuu, Rachel K
dc.contributor.authorWysokowski, Marcin
dc.contributor.authorBuehler, Markus J
dc.date.accessioned2024-09-18T17:34:43Z
dc.date.available2024-09-18T17:34:43Z
dc.date.issued2023-06-05
dc.identifier.urihttps://hdl.handle.net/1721.1/156891
dc.description.abstractWe report a series of deep learning models to solve complex forward and inverse design problems in molecular modeling and design. Using both diffusion models inspired by nonequilibrium thermodynamics and attention-based transformer architectures, we demonstrate a flexible framework to capture complex chemical structures. First trained on the Quantum Machines 9 (QM9) dataset and a series of quantum mechanical properties (e.g., homo, lumo, free energy, and heat capacity), we then generalize the model to study and design key properties of deep eutectic solvents (DESs). In addition to separate forward and inverse models, we also report an integrated fully prompt-based multi-task generative pretrained transformer model that solves multiple forward, inverse design, and prediction tasks, flexibly and within one model. We show that the multi-task generative model has the overall best performance and allows for flexible integration of multiple objectives, within one model, and for distinct chemistries, suggesting that synergies emerge during training of this large language model. Trained jointly in tasks related to the QM9 dataset and DESs, the model can predict various quantum mechanical properties and critical properties to achieve deep eutectic solvent behavior. Several combinations of DESs are proposed based on this framework.en_US
dc.language.isoen
dc.publisherAIP Publishingen_US
dc.relation.isversionof10.1063/5.0155890en_US
dc.rightsCreative Commons Attributionen_US
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en_US
dc.sourceAIP Publishingen_US
dc.titleGenerative discovery of de novo chemical designs using diffusion modeling and transformer deep neural networks with application to deep eutectic solventsen_US
dc.typeArticleen_US
dc.identifier.citationRachel K. Luu, Marcin Wysokowski, Markus J. Buehler; Generative discovery of de novo chemical designs using diffusion modeling and transformer deep neural networks with application to deep eutectic solvents. Appl. Phys. Lett. 5 June 2023; 122 (23): 234103.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Laboratory for Atomistic and Molecular Mechanicsen_US
dc.contributor.departmentMassachusetts Institute of Technology. Center for Computational Science and Engineeringen_US
dc.relation.journalApplied Physics Lettersen_US
dc.eprint.versionFinal published versionen_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/PeerRevieweden_US
dc.date.updated2024-09-18T16:19:28Z
dspace.orderedauthorsLuu, RK; Wysokowski, M; Buehler, MJen_US
dspace.date.submission2024-09-18T16:19:30Z
mit.journal.volume122en_US
mit.journal.issue23en_US
mit.licensePUBLISHER_CC
mit.metadata.statusAuthority Work and Publication Information Neededen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record