Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Explore the application of Graph Neural Network (GNN) approaches for molecule identification in this 1-hour 20-minute tutorial presented by Ivana Milutinovic at DSC Europe 24 in Belgrade. Learn how to transform molecular structures from SMILES strings into graph-based models and implement various GNN architectures to predict molecular activity in biological processes. Discover effective techniques for handling imbalanced datasets, optimizing hyperparameters, and evaluating model performance using real biological and chemical data. Gain valuable insights into the comparative strengths and limitations of different GNN models specifically applied to biological and chemical contexts. This technical session provides practical knowledge for data scientists and researchers working at the intersection of machine learning and molecular science.
