همایش ملی بیوانفورماتیک ایران

صفحه اصلی / 4th international edition and 13th Iranian Conference on Bioinformatics

Predicting Anticancer Drug Repurposing Candidates using Knowledge Graphs

نویسندگان :

Marzieh Khodadadi AghGhaleh¹ Rooholah Abedian² Reza Zarghami³ Sajjad Gharaghani⁴

1- School of Chemical Engineering, College of Engineering, University of Tehran, Tehran, Iran 2- School of Engineering Science, College of Engineering, University of Tehran, Iran 3- Centers of Excellence for Pharmaceutical Processes, School of Chemical Engineering, College of Engineering, University of Tehran, Tehran, Iran 4- Laboratory of Bioinformatics and Drug Design (LBD), Institute of Biochemistry and Biophysics, University of Tehran, Tehran, Iran

کلمات کلیدی :

Drug repurposing،Dual_Channel Neuralnetwork،Kowladge Graph،Anticancer

چکیده :

Drug repurposing (DR) offers a promising and efficient alternative to traditional drug discovery by identifying new therapeutic applications for existing drugs, reducing the time and costs associated with development. This study introduces a novel framework that leverages a new hybrid knowledge graph integrating drug, disease, and protein interactions, combined with a Convolutional Neural Network for drug-disease association prediction. The knowledge graph captures complex biological relationships through diverse biomedical data. The framework demonstrates superior performance, achieving an accuracy of 0.9586 and F1-score of 0.9094, significantly outperforming state-of-the-art methods, including recommendation systems and binary task classification models. A specific type of cancer was selected as the disease focus. Bevacizumab and Pertuzumab were identified as the top-scoring results from the model's predictions. To further validate these findings, molecular docking simulations were conducted on a small molecule that previously lacked evidence for its role in cancer treatment. These simulations revealed a strong binding affinity, suggesting that the small molecule may possess anticancer properties.