MolProphecy: Bridging Medicinal Chemists' Knowledge and Molecular Pre-Trained Models via a Multi-Modal Framework
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913926125453312 |
|---|---|
| author | Zhao, Jianping Zhou, Qiong Wang, Tian Fan, Yusi Yang, Qian Jiao, Li Liu, Chang Guo, Zhehao Lu, Qi Zhou, Fengfeng Zhang, Ruochi |
| author_facet | Zhao, Jianping Zhou, Qiong Wang, Tian Fan, Yusi Yang, Qian Jiao, Li Liu, Chang Guo, Zhehao Lu, Qi Zhou, Fengfeng Zhang, Ruochi |
| contents | MolProphecy is a human-in-the-loop (HITL) multi-modal framework designed to integrate chemists' domain knowledge into molecular property prediction models. While molecular pre-trained models have enabled significant gains in predictive accuracy, they often fail to capture the tacit, interpretive reasoning central to expert-driven molecular design. To address this, MolProphecy employs ChatGPT as a virtual chemist to simulate expert-level reasoning and decision-making. The generated chemist knowledge is embedded by the large language model (LLM) as a dedicated knowledge representation and then fused with graph-based molecular features through a gated cross-attention mechanism, enabling joint reasoning over human-derived and structural features. Evaluated on four benchmark datasets (FreeSolv, BACE, SIDER, and ClinTox), MolProphecy outperforms state-of-the-art (SOTA) models, achieving a 15.0 percent reduction in RMSE on FreeSolv and a 5.39 percent improvement in AUROC on BACE. Analysis reveals that chemist knowledge and structural features provide complementary contributions, improving both accuracy and interpretability. MolProphecy offers a practical and generalizable approach for collaborative drug discovery, with the flexibility to incorporate real chemist input in place of the current simulated proxy--without the need for model retraining. The implementation is publicly available at https://github.com/zhangruochi/MolProphecy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_02932 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MolProphecy: Bridging Medicinal Chemists' Knowledge and Molecular Pre-Trained Models via a Multi-Modal Framework Zhao, Jianping Zhou, Qiong Wang, Tian Fan, Yusi Yang, Qian Jiao, Li Liu, Chang Guo, Zhehao Lu, Qi Zhou, Fengfeng Zhang, Ruochi Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science MolProphecy is a human-in-the-loop (HITL) multi-modal framework designed to integrate chemists' domain knowledge into molecular property prediction models. While molecular pre-trained models have enabled significant gains in predictive accuracy, they often fail to capture the tacit, interpretive reasoning central to expert-driven molecular design. To address this, MolProphecy employs ChatGPT as a virtual chemist to simulate expert-level reasoning and decision-making. The generated chemist knowledge is embedded by the large language model (LLM) as a dedicated knowledge representation and then fused with graph-based molecular features through a gated cross-attention mechanism, enabling joint reasoning over human-derived and structural features. Evaluated on four benchmark datasets (FreeSolv, BACE, SIDER, and ClinTox), MolProphecy outperforms state-of-the-art (SOTA) models, achieving a 15.0 percent reduction in RMSE on FreeSolv and a 5.39 percent improvement in AUROC on BACE. Analysis reveals that chemist knowledge and structural features provide complementary contributions, improving both accuracy and interpretability. MolProphecy offers a practical and generalizable approach for collaborative drug discovery, with the flexibility to incorporate real chemist input in place of the current simulated proxy--without the need for model retraining. The implementation is publicly available at https://github.com/zhangruochi/MolProphecy. |
| title | MolProphecy: Bridging Medicinal Chemists' Knowledge and Molecular Pre-Trained Models via a Multi-Modal Framework |
| topic | Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2507.02932 |