TY - JOUR
T1 - Guided diffusion for inverse molecular design
AU - Weiss, Tomer
AU - Mayo Yanes, Eduardo
AU - Chakraborty, Sabyasachi
AU - Cosmo, Luca
AU - Bronstein, Alex M.
AU - Gershoni-Poranne, Renana
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive licence to Springer Nature America, Inc.
PY - 2023/10
Y1 - 2023/10
N2 - The holy grail of materials science is de novo molecular design, meaning engineering molecules with desired characteristics. The introduction of generative deep learning has greatly advanced efforts in this direction, yet molecular discovery remains challenging and often inefficient. Herein we introduce GaUDI, a guided diffusion model for inverse molecular design that combines an equivariant graph neural net for property prediction and a generative diffusion model. We demonstrate GaUDI’s effectiveness in designing molecules for organic electronic applications by using single- and multiple-objective tasks applied to a generated dataset of 475,000 polycyclic aromatic systems. GaUDI shows improved conditional design, generating molecules with optimal properties and even going beyond the original distribution to suggest better molecules than those in the dataset. In addition to point-wise targets, GaUDI can also be guided toward open-ended targets (for example, a minimum or maximum) and in all cases achieves close to 100% validity of generated molecules.
AB - The holy grail of materials science is de novo molecular design, meaning engineering molecules with desired characteristics. The introduction of generative deep learning has greatly advanced efforts in this direction, yet molecular discovery remains challenging and often inefficient. Herein we introduce GaUDI, a guided diffusion model for inverse molecular design that combines an equivariant graph neural net for property prediction and a generative diffusion model. We demonstrate GaUDI’s effectiveness in designing molecules for organic electronic applications by using single- and multiple-objective tasks applied to a generated dataset of 475,000 polycyclic aromatic systems. GaUDI shows improved conditional design, generating molecules with optimal properties and even going beyond the original distribution to suggest better molecules than those in the dataset. In addition to point-wise targets, GaUDI can also be guided toward open-ended targets (for example, a minimum or maximum) and in all cases achieves close to 100% validity of generated molecules.
UR - http://www.scopus.com/inward/record.url?scp=85173749895&partnerID=8YFLogxK
U2 - 10.1038/s43588-023-00532-0
DO - 10.1038/s43588-023-00532-0
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:85173749895
VL - 3
SP - 873
EP - 882
JO - Nature Computational Science
JF - Nature Computational Science
IS - 10
ER -