This competition is the ADMET prediction of "AI for Drug Discovery" (SI364)

QSAR is a widely used computational method in drug discovery and materials science that predicts properties such as biological activity, toxicity, and solubility using molecular structure descriptors and related activity values.

The theme of this competition is to train an accurate QSAR model using provided datasets, different molecular descriptors, feature selection, and machine learning algorithms to predict the properties of unknown compounds.

Note that introducing additional structure-activity relationship data for the same target is not allowed in the competition to keep all participants focused on machine learning.

Participants can use common methods such as linear regression, support vector machines, or neural networks, but we encourage trying new neural network models such as Transformer and GNN.

Winners will be selected based on the AUROC of participants' prediction and submitted code. Each participant can submit their code twice per day, and please upload the final code before the end of the competition.