This study proposes a deep learning-based framework for predicting lncRNA-drug associations (LDAs) using graph neural networks (GNNs), specifically graph convolutional networks (GCNs) and graph attention networks (GATs). The method constructs lncRNA-drug bipartite graphs and uses similarity matrices derived from lncRNA and drug features to predict potential associations. The model integrates local and global information from the graph structure, leveraging the attention mechanism in GATs to focus on important nodes and enhance prediction accuracy. The framework is validated on five benchmark datasets, achieving high AUC and AUPR values, with the best performance on combined datasets. Case studies and KEGG functional enrichment analysis further confirm the model's effectiveness in identifying novel LDAs. The results demonstrate that the proposed method provides a robust and efficient approach for predicting LDAs, which can accelerate the development of lncRNA-targeted therapies. The study highlights the importance of computational methods in drug discovery and offers a promising solution for identifying potential drug targets based on lncRNA interactions.This study proposes a deep learning-based framework for predicting lncRNA-drug associations (LDAs) using graph neural networks (GNNs), specifically graph convolutional networks (GCNs) and graph attention networks (GATs). The method constructs lncRNA-drug bipartite graphs and uses similarity matrices derived from lncRNA and drug features to predict potential associations. The model integrates local and global information from the graph structure, leveraging the attention mechanism in GATs to focus on important nodes and enhance prediction accuracy. The framework is validated on five benchmark datasets, achieving high AUC and AUPR values, with the best performance on combined datasets. Case studies and KEGG functional enrichment analysis further confirm the model's effectiveness in identifying novel LDAs. The results demonstrate that the proposed method provides a robust and efficient approach for predicting LDAs, which can accelerate the development of lncRNA-targeted therapies. The study highlights the importance of computational methods in drug discovery and offers a promising solution for identifying potential drug targets based on lncRNA interactions.