Demystifying Drug Repurposing Domain Comprehension with Knowledge Graph Embedding
| Autor: | Edoardo Ramalli, Alberto Parravicini, Guido W. Di Donato, Mirko Salaris, Celine Hudelot, Marco D. Santambrogio |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Machine Learning Drug Repurposing Computer Science - Machine Learning Artificial Intelligence (cs.AI) Computer Science - Artificial Intelligence Biomedical Knowledge Graph Knowledge Graph Embedding Link Prediction Drug Repurposing Biomedical Knowledge Graph Knowledge Graph Embedding Link Prediction Machine Learning Machine Learning (cs.LG) |
| Popis: | Drug repurposing is more relevant than ever due to drug development's rising costs and the need to respond to emerging diseases quickly. Knowledge graph embedding enables drug repurposing using heterogeneous data sources combined with state-of-the-art machine learning models to predict new drug-disease links in the knowledge graph. As in many machine learning applications, significant work is still required to understand the predictive models' behavior. We propose a structured methodology to understand better machine learning models' results for drug repurposing, suggesting key elements of the knowledge graph to improve predictions while saving computational resources. We reduce the training set of 11.05% and the embedding space by 31.87%, with only a 2% accuracy reduction, and increase accuracy by 60% on the open ogbl-biokg graph adding only 1.53% new triples. 5 pages, IEEE BioCAS 2021 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|