biostudies-literatureParrilla-Gutierrez JMRCUK | Engineering and Physical Sciences Research Council (EPSRC)European Research CouncilRCUK | Engineering and Physical Sciences Research Council200-209https://www.ebi.ac.uk/biostudies/studies/S-EPMC10965440biostudies-literatureUnknown4(3)Here we present a machine learning model trained on electron density for the production of host-guest binders. These are read out as simplified molecular-input line-entry system (SMILES) format with >98% accuracy, enabling a complete characterization of the molecules in two dimensions. Our model generates three-dimensional representations of the electron density and electrostatic potentials of host-guest systems using a variational autoencoder, and then utilizes these representations to optimize the generation of guests via gradient descent. Finally the guests are converted to SMILES using a transformer. The successful practical application of our model to established molecular host systems, cucurbit[n]uril and metal-organic cages, resulted in the discovery of 9 previously validated guests for CB[6] and 7 unreported guests (with association constant K_a ranging from 13.5 M^-1 to 5,470 M^-1) and the discovery of 4 unreported guests for [Pd₂1₄]⁴⁺ (with K_a ranging from 44 M^-1 to 529 M^-1).Nature computational scienceElectron density-based GPT for optimization and suggestion of host-guest binders.PMC10965440EP/L023652/1, EP/R020914/1, EP/S030603/1, EP/R01308X/1, EP/S017046/1, and EP/S019472/1670467Ayme JFCronin LWilbraham LParrilla-Gutierrez JMGranda JMBajczyk MDfalseElectron density-based GPT for optimization and suggestion of host-guest binders.Here we present a machine learning model trained on electron density for the production of host-guest binders. These are read out as simplified molecular-input line-entry system (SMILES) format with >98% accuracy, enabling a complete characterization of the molecules in two dimensions. Our model generates three-dimensional representations of the electron density and electrostatic potentials of host-guest systems using a variational autoencoder, and then utilizes these representations to optimize the generation of guests via gradient descent. Finally the guests are converted to SMILES using a transformer. The successful practical application of our model to established molecular host systems, cucurbit[n]uril and metal-organic cages, resulted in the discovery of 9 previously validated guests for CB[6] and 7 unreported guests (with association constant K_a ranging from 13.5 M^-1 to 5,470 M^-1) and the discovery of 4 unreported guests for [Pd₂1₄]⁴⁺ (with K_a ranging from 44 M^-1 to 529 M^-1).2024-01-01T00:00:00Z2024 Mar2025-04-27T03:11:25.513Z2025-04-06T18:45:09.016ZS-EPMC109654403845927210.1038/s43588-024-00602-x