GFlowNets for Learning Better Drug-Drug Interaction Representations
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908619561238528 |
|---|---|
| author | Wasi, Azmine Toushik |
| author_facet | Wasi, Azmine Toushik |
| contents | Drug-drug interactions pose a significant challenge in clinical pharmacology, with severe class imbalance among interaction types limiting the effectiveness of predictive models. Common interactions dominate datasets, while rare but critical interactions remain underrepresented, leading to poor model performance on infrequent cases. Existing methods often treat DDI prediction as a binary problem, ignoring class-specific nuances and exacerbating bias toward frequent interactions. To address this, we propose a framework combining Generative Flow Networks (GFlowNet) with Variational Graph Autoencoders (VGAE) to generate synthetic samples for rare classes, improving model balance and generate effective and novel DDI pairs. Our approach enhances predictive performance across interaction types, ensuring better clinical reliability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_06576 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GFlowNets for Learning Better Drug-Drug Interaction Representations Wasi, Azmine Toushik Machine Learning Biomolecules Molecular Networks Drug-drug interactions pose a significant challenge in clinical pharmacology, with severe class imbalance among interaction types limiting the effectiveness of predictive models. Common interactions dominate datasets, while rare but critical interactions remain underrepresented, leading to poor model performance on infrequent cases. Existing methods often treat DDI prediction as a binary problem, ignoring class-specific nuances and exacerbating bias toward frequent interactions. To address this, we propose a framework combining Generative Flow Networks (GFlowNet) with Variational Graph Autoencoders (VGAE) to generate synthetic samples for rare classes, improving model balance and generate effective and novel DDI pairs. Our approach enhances predictive performance across interaction types, ensuring better clinical reliability. |
| title | GFlowNets for Learning Better Drug-Drug Interaction Representations |
| topic | Machine Learning Biomolecules Molecular Networks |
| url | https://arxiv.org/abs/2508.06576 |