GFlowNets for Learning Better Drug-Drug Interaction Representations
By: Azmine Toushik Wasi
Potential Business Impact:
Finds dangerous medicine mixes doctors miss.
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.
Similar Papers
Predicting Drug-Drug Interactions Using Heterogeneous Graph Neural Networks: HGNN-DDI
Machine Learning (CS)
Finds dangerous medicine mixes before they hurt.
Interpreting GFlowNets for Drug Discovery: Extracting Actionable Insights for Medicinal Chemistry
Machine Learning (CS)
Shows how computers design new medicines.
Multi-domain Distribution Learning for De Novo Drug Design
Machine Learning (CS)
Finds new medicines by designing molecules.