FragmentGPT: A Unified GPT Model for Fragment Growing, Linking, and Merging in Molecular Design
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916963163308032 |
|---|---|
| author | Liu, Xuefeng Jiang, Songhao Huang, Qinan Xu, Tinson Foster, Ian Wang, Mengdi Lin, Hening Stevens, Rick |
| author_facet | Liu, Xuefeng Jiang, Songhao Huang, Qinan Xu, Tinson Foster, Ian Wang, Mengdi Lin, Hening Stevens, Rick |
| contents | Fragment-Based Drug Discovery (FBDD) is a popular approach in early drug development, but designing effective linkers to combine disconnected molecular fragments into chemically and pharmacologically viable candidates remains challenging. Further complexity arises when fragments contain structural redundancies, like duplicate rings, which cannot be addressed by simply adding or removing atoms or bonds. To address these challenges in a unified framework, we introduce FragmentGPT, which integrates two core components: (1) a novel chemically-aware, energy-based bond cleavage pre-training strategy that equips the GPT-based model with fragment growing, linking, and merging capabilities, and (2) a novel Reward Ranked Alignment with Expert Exploration (RAE) algorithm that combines expert imitation learning for diversity enhancement, data selection and augmentation for Pareto and composite score optimality, and Supervised Fine-Tuning (SFT) to align the learner policy with multi-objective goals. Conditioned on fragment pairs, FragmentGPT generates linkers that connect diverse molecular subunits while simultaneously optimizing for multiple pharmaceutical goals. It also learns to resolve structural redundancies-such as duplicated fragments-through intelligent merging, enabling the synthesis of optimized molecules. FragmentGPT facilitates controlled, goal-driven molecular assembly. Experiments and ablation studies on real-world cancer datasets demonstrate its ability to generate chemically valid, high-quality molecules tailored for downstream drug discovery tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_11044 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FragmentGPT: A Unified GPT Model for Fragment Growing, Linking, and Merging in Molecular Design Liu, Xuefeng Jiang, Songhao Huang, Qinan Xu, Tinson Foster, Ian Wang, Mengdi Lin, Hening Stevens, Rick Machine Learning Artificial Intelligence Biomolecules Fragment-Based Drug Discovery (FBDD) is a popular approach in early drug development, but designing effective linkers to combine disconnected molecular fragments into chemically and pharmacologically viable candidates remains challenging. Further complexity arises when fragments contain structural redundancies, like duplicate rings, which cannot be addressed by simply adding or removing atoms or bonds. To address these challenges in a unified framework, we introduce FragmentGPT, which integrates two core components: (1) a novel chemically-aware, energy-based bond cleavage pre-training strategy that equips the GPT-based model with fragment growing, linking, and merging capabilities, and (2) a novel Reward Ranked Alignment with Expert Exploration (RAE) algorithm that combines expert imitation learning for diversity enhancement, data selection and augmentation for Pareto and composite score optimality, and Supervised Fine-Tuning (SFT) to align the learner policy with multi-objective goals. Conditioned on fragment pairs, FragmentGPT generates linkers that connect diverse molecular subunits while simultaneously optimizing for multiple pharmaceutical goals. It also learns to resolve structural redundancies-such as duplicated fragments-through intelligent merging, enabling the synthesis of optimized molecules. FragmentGPT facilitates controlled, goal-driven molecular assembly. Experiments and ablation studies on real-world cancer datasets demonstrate its ability to generate chemically valid, high-quality molecules tailored for downstream drug discovery tasks. |
| title | FragmentGPT: A Unified GPT Model for Fragment Growing, Linking, and Merging in Molecular Design |
| topic | Machine Learning Artificial Intelligence Biomolecules |
| url | https://arxiv.org/abs/2509.11044 |