Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.09020 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918157964279808 |
|---|---|
| author | Chen, Zekai Li, Xunkai Zhang, Sirui Sun, Henan Li, Jia Li, Zhenjun Zhou, Bing Li, Rong-Hua Wang, Guoren |
| author_facet | Chen, Zekai Li, Xunkai Zhang, Sirui Sun, Henan Li, Jia Li, Zhenjun Zhou, Bing Li, Rong-Hua Wang, Guoren |
| contents | De novo ligand design is a fundamental task that seeks to generate protein or molecule candidates that can effectively dock with protein receptors and achieve strong binding affinity entirely from scratch. It holds paramount significance for a wide spectrum of biomedical applications. However, most existing studies are constrained by the \textbf{Pseudo De Novo}, \textbf{Limited Docking Modeling}, and \textbf{Inflexible Ligand Type}. To address these issues, we propose MagicDock, a forward-looking framework grounded in the progressive pipeline and differentiable surface modeling. (1) We adopt a well-designed gradient inversion framework. To begin with, general docking knowledge of receptors and ligands is incorporated into the backbone model. Subsequently, the docking knowledge is instantiated as reverse gradient flows by binding prediction, which iteratively guide the de novo generation of ligands. (2) We emphasize differentiable surface modeling in the docking process, leveraging learnable 3D point-cloud representations to precisely capture binding details, thereby ensuring that the generated ligands preserve docking validity through direct and interpretable spatial fingerprints. (3) We introduce customized designs for different ligand types and integrate them into a unified gradient inversion framework with flexible triggers, thereby ensuring broad applicability. Moreover, we provide rigorous theoretical guarantees for each component of MagicDock. Extensive experiments across 9 scenarios demonstrate that MagicDock achieves average improvements of 27.1\% and 11.7\% over SOTA baselines specialized for protein or molecule ligand design, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09020 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MagicDock: Toward Docking-oriented De Novo Ligand Design via Gradient Inversion Chen, Zekai Li, Xunkai Zhang, Sirui Sun, Henan Li, Jia Li, Zhenjun Zhou, Bing Li, Rong-Hua Wang, Guoren Machine Learning De novo ligand design is a fundamental task that seeks to generate protein or molecule candidates that can effectively dock with protein receptors and achieve strong binding affinity entirely from scratch. It holds paramount significance for a wide spectrum of biomedical applications. However, most existing studies are constrained by the \textbf{Pseudo De Novo}, \textbf{Limited Docking Modeling}, and \textbf{Inflexible Ligand Type}. To address these issues, we propose MagicDock, a forward-looking framework grounded in the progressive pipeline and differentiable surface modeling. (1) We adopt a well-designed gradient inversion framework. To begin with, general docking knowledge of receptors and ligands is incorporated into the backbone model. Subsequently, the docking knowledge is instantiated as reverse gradient flows by binding prediction, which iteratively guide the de novo generation of ligands. (2) We emphasize differentiable surface modeling in the docking process, leveraging learnable 3D point-cloud representations to precisely capture binding details, thereby ensuring that the generated ligands preserve docking validity through direct and interpretable spatial fingerprints. (3) We introduce customized designs for different ligand types and integrate them into a unified gradient inversion framework with flexible triggers, thereby ensuring broad applicability. Moreover, we provide rigorous theoretical guarantees for each component of MagicDock. Extensive experiments across 9 scenarios demonstrate that MagicDock achieves average improvements of 27.1\% and 11.7\% over SOTA baselines specialized for protein or molecule ligand design, respectively. |
| title | MagicDock: Toward Docking-oriented De Novo Ligand Design via Gradient Inversion |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.09020 |