VADEERS dataset

The dataset D = {XS, XI, XB, YR, (cid:126)yG} consists of five parts, where XS ∈ R304×300 denotes drugs’ SMILES vector representations, XI ∈ R117×294 denotes drugs’ inhibition profiles across a panel of protein kinases, XB ∈ R922×241 denotes a matrix of cell lines biological features, YR ∈ R922×304 denotes a matrix with drug response indicators for a given cell line c and drug d, and (cid:126)yG ∈ R117 denotes a vector of guiding labels for a subset of considered drugs.