Litcius/Paper detail

PILOT: equivariant diffusion for pocket-conditioned <i>de novo</i> ligand generation with multi-objective guidance <i>via</i> importance sampling

Julian Cremer, Tuan Le, Frank Noé, Djork-Arné Clevert, Kristof T. Schütt

2024Chemical Science30 citationsDOIOpen Access PDF

Abstract

Creating ligands that fit specific protein pockets and possess desired chemical properties is a key challenge in SBDD. Guided 3D diffusion models present a promising solution, offering precise ligand generation with tailored properties.

Topics & Concepts

Equivariant mapDiffusionLigand (biochemistry)Sampling (signal processing)Control theory (sociology)MathematicsComputer scienceChemistryPhysicsPure mathematicsArtificial intelligenceReceptorThermodynamicsComputer visionBiochemistryFilter (signal processing)Control (management)Computational Drug Discovery MethodsMachine Learning in Materials Science
PILOT: equivariant diffusion for pocket-conditioned <i>de novo</i> ligand generation with multi-objective guidance <i>via</i> importance sampling | Litcius