ConvAHKG: Action-Based Hybrid Knowledge Graph with a Dual-Channel Convolutional Approach for Drug Repurposing

Drug repurposing, which is the process of finding new therapeutic usage for already approved medications, has become a more efficient, time-saving and cost-effective approach compared to traditional drug discovery methods. ConvAHKG, an action-based hybrid knowledge graph approach, is proposed to improve the prediction of drug-disease associations by leveraging biological relationships among drugs, proteins, and diseases. AHKG is designed to integrate both drug and disease features to provide a comprehensive framework. To represent these relationships, Word2Vec embeddings are used to capture the semantic similarities among entities, and a novel dual-channel 1D convolutional neural network (IDC_Conv1D) is introduced for the classification of drug-disease pairs. This architecture is specifically intended to handle the complexity and heterogeneity of biological data. Furthermore, to tackle the challenge of class imbalance in the dataset, a weighted binary cross-entropy loss function is proposed, which significantly improved the model's predictive performance. ConvAHKG outperforms state-of-the-art models, with an AUC of 0.9836 and an AUPRC of 0.9686. To validate its practical utility, we apply ConvAHKG to study non-small cell lung cancer (NSCLC), the most prevalent form of lung cancer. Through this application, we identify promising repurposed drugs, such as Trastuzumab, that have the potential to treat NSCLC. Additionally, in the case of a predicted compound which was not experimentally validated, molecular docking studies showed strong binding interactions, further confirming its potential as a novel therapeutic candidate. All data and code used in this study are available at {https://github.com/Marzieh-Khodadadi/ConvAHKG}