Structure-sensitive transformer and multi-view graph contrastive learning enhanced prediction of drug-related microbes
The extensive experimental results show that SMMDA outperforms several state-of-the-art methods for predicting the drug-related candidate microbes. The ablation studies show the effectiveness of the major innovations which include the learnable data augmentation, structure-sensitive transformer-based node feature learning, and multi-view contrastive learning. The case studies on three drugs also demonstrate SMMDA's capability in retrieving the potential microbe candidates for the drugs.
Authors
- Tiangang Zhang (ORCID: https://orcid.org/0000-0002-7528-3581)
- Hui Cui (ORCID: https://orcid.org/0000-0001-8224-4698)
- Ping Xuan (ORCID: https://orcid.org/0000-0001-5328-691X)
- Jing Gu (ORCID: https://orcid.org/0000-0002-0291-3263)
- Rui Wang (ORCID: https://orcid.org/0000-0001-9048-2979)
Institutions
- Heilongjiang University of Science and Technology (CN)
- La Trobe University (AU)
- Hainan University (CN)
- Shantou University (CN)
- Heilongjiang University (CN)
Publication Details
- Journal
- BMC Bioinformatics
- Published
- 2025-09-26
- DOI
- https://doi.org/10.1186/s12859-025-06199-w
- Citations
- 1
- Primary Topic
- Computational Drug Discovery Methods
- Type
- article
- Field-Weighted Citation Impact
- 1.50
Funders
- National Natural Science Foundation of China
- Natural Science Foundation of Heilongjiang Province
- Basic and Applied Basic Research Foundation of Guangdong Province