Hierarchical Structure-Property Alignment for Data-Efficient Molecular Generation and Editing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917073084481536 |
|---|---|
| author | Fan, Ziyu Huang, Zhijian Li, Yahan Hu, Xiaowen Shen, Siyuan Wang, Yunliang Zhong, Zeyu Liu, Shuhong Yang, Shuning Wu, Shangqian Wu, Min Deng, Lei |
| author_facet | Fan, Ziyu Huang, Zhijian Li, Yahan Hu, Xiaowen Shen, Siyuan Wang, Yunliang Zhong, Zeyu Liu, Shuhong Yang, Shuning Wu, Shangqian Wu, Min Deng, Lei |
| contents | Property-constrained molecular generation and editing are crucial in AI-driven drug discovery but remain hindered by two factors: (i) capturing the complex relationships between molecular structures and multiple properties remains challenging, and (ii) the narrow coverage and incomplete annotations of molecular properties weaken the effectiveness of property-based models. To tackle these limitations, we propose HSPAG, a data-efficient framework featuring hierarchical structure-property alignment. By treating SMILES and molecular properties as complementary modalities, the model learns their relationships at atom, substructure, and whole-molecule levels. Moreover, we select representative samples through scaffold clustering and hard samples via an auxiliary variational auto-encoder (VAE), substantially reducing the required pre-training data. In addition, we incorporate a property relevance-aware masking mechanism and diversified perturbation strategies to enhance generation quality under sparse annotations. Experiments demonstrate that HSPAG captures fine-grained structure-property relationships and supports controllable generation under multiple property constraints. Two real-world case studies further validate the editing capabilities of HSPAG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08080 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hierarchical Structure-Property Alignment for Data-Efficient Molecular Generation and Editing Fan, Ziyu Huang, Zhijian Li, Yahan Hu, Xiaowen Shen, Siyuan Wang, Yunliang Zhong, Zeyu Liu, Shuhong Yang, Shuning Wu, Shangqian Wu, Min Deng, Lei Machine Learning Artificial Intelligence Property-constrained molecular generation and editing are crucial in AI-driven drug discovery but remain hindered by two factors: (i) capturing the complex relationships between molecular structures and multiple properties remains challenging, and (ii) the narrow coverage and incomplete annotations of molecular properties weaken the effectiveness of property-based models. To tackle these limitations, we propose HSPAG, a data-efficient framework featuring hierarchical structure-property alignment. By treating SMILES and molecular properties as complementary modalities, the model learns their relationships at atom, substructure, and whole-molecule levels. Moreover, we select representative samples through scaffold clustering and hard samples via an auxiliary variational auto-encoder (VAE), substantially reducing the required pre-training data. In addition, we incorporate a property relevance-aware masking mechanism and diversified perturbation strategies to enhance generation quality under sparse annotations. Experiments demonstrate that HSPAG captures fine-grained structure-property relationships and supports controllable generation under multiple property constraints. Two real-world case studies further validate the editing capabilities of HSPAG. |
| title | Hierarchical Structure-Property Alignment for Data-Efficient Molecular Generation and Editing |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2511.08080 |