Litcius/Paper detail

Electron density-based GPT for optimization and suggestion of host–guest binders

Juan Manuel Parrilla Gutiérrez, Jarosław M. Granda, Jean‐François Ayme, Michał D. Bajczyk, Liam Wilbraham, Leroy Cronin

2024Nature Computational Science18 citationsDOIOpen Access PDF

Abstract

Abstract 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 [Pd 2 1 4 ] 4+ (with K a ranging from 44 M −1 to 529 M −1 ).

Topics & Concepts

Host (biology)RangingAutoencoderGradient descentElectron densityMoleculeCharacterization (materials science)Computer scienceChemistryElectronMaterials scienceBiological systemNanotechnologyPhysicsArtificial intelligenceDeep learningBiologyOrganic chemistryQuantum mechanicsArtificial neural networkTelecommunicationsEcologyMachine Learning in Materials ScienceCrystallography and molecular interactionsSupramolecular Chemistry and Complexes