MaskMol: knowledge-guided molecular image pre-training framework for activity cliffs with pixel masking
This study raises awareness about activity cliffs and introduces a novel method for molecular image representation learning and virtual screening, advancing drug discovery and providing new insights into structure-activity relationships (SAR).
Authors
- Hongxin Xiang (ORCID: https://orcid.org/0000-0001-8345-8735)
- Xiangxiang Zeng (ORCID: https://orcid.org/0000-0001-6201-0114)
- Li Zeng (ORCID: https://orcid.org/0000-0002-8879-951X)
- Bosheng Song (ORCID: https://orcid.org/0000-0002-1479-5399)
- Yang Deng (ORCID: https://orcid.org/0000-0002-2795-6796)
- Jianxin Lin (ORCID: https://orcid.org/0000-0003-0359-8821)
- Pengsen Ma
- Xinxin Feng (ORCID: https://orcid.org/0000-0003-1166-2280)
- Changhui Deng
- Xixi Yang (ORCID: https://orcid.org/0000-0001-9839-2249)
- Xin Jin (ORCID: https://orcid.org/0000-0002-1820-8358)
- Zhixiang Cheng
Institutions
- Hunan University (CN)
- Shanghai CASB Biotechnology (China) (CN)
- Third Hospital of Changsha (CN)
- Ningbo Institute of Industrial Technology (CN)
Publication Details
- Journal
- BMC Biology
- Published
- 2025-09-24
- DOI
- https://doi.org/10.1186/s12915-025-02389-3
- Citations
- 2
- Primary Topic
- Computational Drug Discovery Methods
- Type
- article
- Field-Weighted Citation Impact
- 3.01
Funders
- National Natural Science Foundation of China
- Natural Science Foundation of Hunan Province