When Your Model Does Not Know What It Does Not Know: A Drug Discovery ML Project

1. 1Build a molecular binding affinity prediction pipeline using Graph Attention Networks
2. 2Implement MC Dropout for uncertainty quantification
3. 3Configure the pipeline to handle missing data and outliers
4. 4Test the pipeline using a benchmark dataset
5. 5Apply the pipeline to a real-world drug discovery problem

Data scientists and ML engineers working on drug discovery projects can benefit from this pipeline to improve model performance and reliability

💡 Uncertainty quantification is crucial in drug discovery to identify when a model is uncertain about its predictions

Improve model reliability in drug discovery with Graph Attention Networks and uncertainty quantification