Overcoming class imbalance in drug discovery problems: graph neural networks and balancing approaches
Carregando...
Data
Título da Revista
ISSN da Revista
Título de Volume
Editor
Universidade Federal de Minas Gerais
Descrição
Tipo
Artigo de periódico
Título alternativo
Primeiro orientador
Membros da banca
Resumo
This research investigates the application of Graph Neural Networks (GNNs) to enhance the cost-effectiveness of drug development, addressing the limitations of cost and time. Class imbalances within classification datasets, such as the discrepancy between active and inactive compounds, give rise to difficulties that can be resolved through strategies like oversampling, undersampling, and manipulation of the loss function. A comparison is conducted between three distinct datasets using three different GNN architectures. This benchmarking research can steer future investigations and enhance the efficacy of GNNs in drug discovery and design. Three hundred models for each combination of architecture and dataset were trained using hyperparameter tuning techniques and evaluated using a range of metrics. Notably, the oversampling technique outperforms eight experiments, showcasing its potential. While balancing techniques boost imbalanced dataset models, their efficacy depends on dataset specifics and problem type. Although oversampling aids molecular graph datasets, more research is needed to optimize its usage and explore other class imbalance solutions.
Abstract
Assunto
Redes neurais (Computação)
Palavras-chave
Graph neural networks, Unbalanced dataset, Drug discovery, The usage of a robust architecture can be beneficial for unbalanced datasets. Weighted loss function and oversampling improve performance on unbalanced datasets. Oversampled models have a higher chance of attaining a high MCC score. Case-specific strategies analysis for each dataset is recommended for better results.
Citação
Departamento
Curso
Endereço externo
https://www.sciencedirect.com/science/article/pii/S1093326323002255