From Holo Pockets to Electron Density: GPT-style Drug Design with Density
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.
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
Generating Developable 3D Molecules via Pocket-Conditioned Diffusion and Property-Aware Optimization
This paper introduces a novel diffusion-based generative model for structure-based drug design that decouples pocket and ligand representation learning and incorporates multi-scale interaction signals and property-aware optimization to generate developable 3D molecules with improved binding affinity and ADMET properties.
Sesame: Structure-Aware Molecular Generation via Spatial Density-Map Conditioning
This paper introduces Sesame, a diffusion-based molecular generation model that conditions on partial molecular structure and protein pocket via spatial density maps, enabling both de novo generation and fragment-conditioned lead optimization for drug design.
Gene Expression-Informed Jointly Controlled Generative Modeling for Precision Molecular Design
This paper proposes JoPMol, a jointly controlled precision molecular generative model that integrates gene expression profiles, molecular structure text, and chemical properties to generate personalized drug candidates, outperforming state-of-the-art methods.
DrugGen 2: A disease-aware language model for enhancing drug discovery
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.
Folding, Reasoning, and Scaling with Open-source Drug Discovery Engine
Introduces OpenDDE, an open-source all-atom biomolecular foundation model that uses co-folding as a shared structural reasoning layer for drug discovery, achieving high accuracy and identifying scaling laws for further improvement.