HLN-DDI: hierarchical molecular representation learning with co-attention mechanism for drug-drug interaction prediction
Abstract Background Accurate identification of drug-drug interactions (DDIs) is critical in pharmacology, as DDIs can either enhance therapeutic efficacy or trigger adverse reactions when multiple medications are administered concurrently. Traditional methods for identifying DDIs are labor-intensive...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-06-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-025-06157-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850136417684946944 |
|---|---|
| author | Yue Luo Lei Deng Zhijian Huang |
| author_facet | Yue Luo Lei Deng Zhijian Huang |
| author_sort | Yue Luo |
| collection | DOAJ |
| description | Abstract Background Accurate identification of drug-drug interactions (DDIs) is critical in pharmacology, as DDIs can either enhance therapeutic efficacy or trigger adverse reactions when multiple medications are administered concurrently. Traditional methods for identifying DDIs are labor-intensive and time-consuming, prompting the development of computational alternatives. However, existing computational approaches frequently encounter challenges related to interpretability and struggle to effectively capture the complex, multi-level structures inherent in drug molecules. Specifically, they often fail to adequately analyze substructural components and neglect interactions across hierarchical structural levels, resulting in incomplete molecular representations. Results In this study, we propose a Hierarchical Learning Network with a co-attention mechanism tailored to molecular structure representation for predicting DDIs, named HLN-DDI. The proposed method advances existing approaches by explicitly encoding motif-level structures and capturing hierarchical molecular representations at atom-level, motif-level, and whole-molecule scales. These hierarchical representations are integrated using a co-attention mechanism and combined with interaction-type information to enhance predictive performance. Comprehensive evaluations demonstrate that HLN-DDI significantly outperforms state-of-the-art methods across multiple benchmark datasets, achieving over 98% accuracy under transductive scenarios and surpassing 99% on various evaluation metrics. Moreover, HLN-DDI achieves a notable accuracy improvement of 2.75% in predicting DDIs involving unseen drugs. Practical assessments with real-world DDI scenarios further validate the efficacy and utility of our proposed model. Conclusion By leveraging hierarchical molecular structures and employing a co-attention mechanism to effectively integrate multi-level representations, HLN-DDI generates comprehensive and precise drug representations, leading to substantially improved predictions of potential drug-drug interactions. |
| format | Article |
| id | doaj-art-71020640ab1e4fe2a261a0f4efa4250e |
| institution | OA Journals |
| issn | 1471-2105 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj-art-71020640ab1e4fe2a261a0f4efa4250e2025-08-20T02:31:09ZengBMCBMC Bioinformatics1471-21052025-06-0126111710.1186/s12859-025-06157-6HLN-DDI: hierarchical molecular representation learning with co-attention mechanism for drug-drug interaction predictionYue Luo0Lei Deng1Zhijian Huang2School of Computer Science and Engineering, Central South UniversitySchool of Computer Science and Engineering, Central South UniversitySchool of Computer Science and Engineering, Central South UniversityAbstract Background Accurate identification of drug-drug interactions (DDIs) is critical in pharmacology, as DDIs can either enhance therapeutic efficacy or trigger adverse reactions when multiple medications are administered concurrently. Traditional methods for identifying DDIs are labor-intensive and time-consuming, prompting the development of computational alternatives. However, existing computational approaches frequently encounter challenges related to interpretability and struggle to effectively capture the complex, multi-level structures inherent in drug molecules. Specifically, they often fail to adequately analyze substructural components and neglect interactions across hierarchical structural levels, resulting in incomplete molecular representations. Results In this study, we propose a Hierarchical Learning Network with a co-attention mechanism tailored to molecular structure representation for predicting DDIs, named HLN-DDI. The proposed method advances existing approaches by explicitly encoding motif-level structures and capturing hierarchical molecular representations at atom-level, motif-level, and whole-molecule scales. These hierarchical representations are integrated using a co-attention mechanism and combined with interaction-type information to enhance predictive performance. Comprehensive evaluations demonstrate that HLN-DDI significantly outperforms state-of-the-art methods across multiple benchmark datasets, achieving over 98% accuracy under transductive scenarios and surpassing 99% on various evaluation metrics. Moreover, HLN-DDI achieves a notable accuracy improvement of 2.75% in predicting DDIs involving unseen drugs. Practical assessments with real-world DDI scenarios further validate the efficacy and utility of our proposed model. Conclusion By leveraging hierarchical molecular structures and employing a co-attention mechanism to effectively integrate multi-level representations, HLN-DDI generates comprehensive and precise drug representations, leading to substantially improved predictions of potential drug-drug interactions.https://doi.org/10.1186/s12859-025-06157-6Drug-drug interactionMolecular graph learningCo-attention mechanism |
| spellingShingle | Yue Luo Lei Deng Zhijian Huang HLN-DDI: hierarchical molecular representation learning with co-attention mechanism for drug-drug interaction prediction BMC Bioinformatics Drug-drug interaction Molecular graph learning Co-attention mechanism |
| title | HLN-DDI: hierarchical molecular representation learning with co-attention mechanism for drug-drug interaction prediction |
| title_full | HLN-DDI: hierarchical molecular representation learning with co-attention mechanism for drug-drug interaction prediction |
| title_fullStr | HLN-DDI: hierarchical molecular representation learning with co-attention mechanism for drug-drug interaction prediction |
| title_full_unstemmed | HLN-DDI: hierarchical molecular representation learning with co-attention mechanism for drug-drug interaction prediction |
| title_short | HLN-DDI: hierarchical molecular representation learning with co-attention mechanism for drug-drug interaction prediction |
| title_sort | hln ddi hierarchical molecular representation learning with co attention mechanism for drug drug interaction prediction |
| topic | Drug-drug interaction Molecular graph learning Co-attention mechanism |
| url | https://doi.org/10.1186/s12859-025-06157-6 |
| work_keys_str_mv | AT yueluo hlnddihierarchicalmolecularrepresentationlearningwithcoattentionmechanismfordrugdruginteractionprediction AT leideng hlnddihierarchicalmolecularrepresentationlearningwithcoattentionmechanismfordrugdruginteractionprediction AT zhijianhuang hlnddihierarchicalmolecularrepresentationlearningwithcoattentionmechanismfordrugdruginteractionprediction |