From Holo Pockets to Electron Density: GPT-style Drug Design with Density

TL;DR

This paper introduces EDMolGPT, a novel generative model that designs molecules conditioned on electron density data, capturing binding environment flexibility and improving 3D conformations in drug discovery.

Contribution

It leverages low-resolution electron density as a physically grounded condition for de novo drug design, integrating experimental data into generative modeling.

Findings

Effective molecule generation conditioned on electron density.

Improved 3D conformations and reduced structural bias.

Validated on 101 biological targets.

Abstract

Recent advances in generative modeling have enabled significant progress in structure-based drug design (SBDD). Existing methods typically condition molecule generation on empty binding pockets from holo complexes, overlooking informative components such as the filler (ligands and solvent). Here, we leverage low-resolution electron density (ED) derived from the filler as a physically grounded condition for \textit{de novo} drug design. We consider two types of ED, calculated and cryo-EM/X-ray, obtainable from computational or experimental sources, supporting unified pre-training and experimental integration. Compared with rigid pocket representations, experimental ED naturally captures conformational flexibility and provides a more faithful description of the binding environment. Based on this, we introduce EDMolGPT, a decoder-only autoregressive framework that generates molecules from low-resolution ED point clouds. By grounding generation in physically meaningful density signals, EDMolGPT mitigates structural bias and produces molecules with 3D conformations. Evaluations on 101 biological targets verify the effectiveness. Our project page: https://jiahaochen1.github.io/EDMolGPT_Page/.