Abstract
Neurodegenerative diseases, including Alzheimer’s, Parkinson’s, Huntington’s, and amyotrophic lateral sclerosis (ALS), pose significant challenges to global healthcare due to their complexity and severe impact on patients. A shared pathogenic feature of these diseases is protein misfolding and aggregation, which leads to neuronal death. Traditional experimental methods for identifying disease-associated proteins are limited by the nervous system’s complexity and the difficulty of obtaining biological samples. This study introduces a novel computational model, ITPND, which combines features of single proteins with protein-protein interaction (PPI) networks to identify proteins linked to neurodegenerative diseases. By leveraging Graph Attention Networks (GAT) and the ProtBERT model, our approach effectively classifies proteins by extracting significant features from sequences and PPI graphs. The model outperforms existing methods, achieving an accuracy of 80%, a precision of 85%, and a recall of 90%. Biological validation through pathway enrichment analysis confirms the involvement of predicted proteins in critical neurodegenerative pathways. Furthermore, drug-protein interaction analysis reveals potential therapeutic candidates, underscoring the model’s utility in drug target discovery. This approach provides new insights into the molecular mechanisms of neurodegenerative diseases and potential therapeutic interventions
Reyhaneh Ebrahimi
Graduated Master
Seyed Hassan Alavi
I am a bioinformatics researcher working on deep learning for biological sequences, with a focus on protein language models, drug activity prediction, and low-data learning.
Fatemeh Zare-Mirakabad
Associate Professor
My research interests include bioinformatics, computational biology and artificial intelligence.