Benchmarking Experiments with External Data, Domain-Specific Features, and Learning Strategies for Modeling ADME and Potency of Coronavirus Main Protease Inhibitors
This work tested the key molecular descriptors capable of identifying antivirals, augmenting challenge data sets with curated public data, and building both classical machine learning and graph neural network (GNN) variants, providing both practical benchmarked modeling strategies for ADME and potency prediction and a...