Hyperparameter Optimization of Graph Neural Networks for mRNA Degradation Prediction

• Published in: 2023 46th MIPRO ICT and Electronics Convention (MIPRO) pp. 423 - 428
• Main Authors: Vodilovska, Viktorija, Gievska, Sonja, Ivanoska, Ilinka
• Format: Conference Proceeding
• Language: English
• Published: MIPRO Croatian Society 22.05.2023
• Subjects: Artificial Bee Colony; Bayesian search; Degradation; GAT; GCN; Genetic Algorithm; Graph neural networks; Hill Climbing; Hyperparameter optimization; mRNA degradation; mRNA vaccines; Particle Swarm Optimization; Prediction algorithms; Random Search; Simulated annealing; Sociology; Surveys

Graph Neural Networks (GNN) emerged as increasingly attractive deep learning models for complex data, making them extremely useful in biochemical and pharmaceutical domains. However, building a good-performing GNN requires lots of parameter choices and Hyperparameter optimization (HPO) can aid in ex...