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

Hugging Face Daily Papers Papers

Summary

This paper introduces EDMolGPT, an autoregressive framework that generates 3D molecular conformations from low-resolution electron density point clouds, improving structure-based drug design by leveraging physically meaningful density signals.

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 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/.
Original Article
View Cached Full Text

Cached at: 05/12/26, 02:50 AM

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

Source: https://huggingface.co/papers/2605.08767

Abstract

EDMolGPT is a decoder-only autoregressive framework that generates molecules from low-resolution electron density point clouds, leveraging physically meaningful density signals to produce structurally accurate 3D conformations.

Recent advances ingenerative modelinghave enabled significant progress instructure-based drug design(SBDD). Existing methods typically conditionmolecule generationon empty binding pockets from holo complexes, overlooking informative components such as the filler (ligands and solvent). Here, we leverage low-resolutionelectron density(ED) derived from the filler as a physically grounded condition forde 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 capturesconformational flexibilityand provides a more faithful description of the binding environment. Based on this, we introduce EDMolGPT, a decoder-onlyautoregressive frameworkthat generates molecules from low-resolution ED point clouds. By grounding generation in physically meaningful density signals, EDMolGPT mitigates structural bias and produces molecules with3D conformations. Evaluations on 101 biological targets verify the effectiveness. Our project page: https://jiahaochen1.github.io/EDMolGPT_Page/.

View arXiv pageView PDFProject pageGitHub0Add to collection

Get this paper in your agent:

hf papers read 2605\.08767

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.08767 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.08767 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.08767 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

DrugGen 2: A disease-aware language model for enhancing drug discovery

Hugging Face Daily Papers

DrugGen-2 fine-tunes GPT-2 using supervised learning and reinforcement learning (GRPO) to generate small molecules conditioned on both disease ontology and target protein sequences, achieving superior diversity and binding affinity for drug discovery.