Computational-experimental approach to drug-target interaction mapping: A case study on kinase inhibitors
Fig 2
Drug-protein interaction prediction scenarios.
(dx, px) denotes a query drug-protein pair, the binding affinity of which is to be predicted. (a) The Bioactivity Imputation scenario: both the drug dx and protein px are present in the training set, i.e., there exist known bioactivity values for the drug dx and protein px, but not for their interaction (dx, px). (b) The New Drug scenario: the protein px is present in the training set, whereas the drug dx is not, i.e., there exist known bioactivity values for the protein px but not for the drug dx. (c) The New Target scenario: the drug dx is present in the training set, whereas the protein px is not, i.e., there exist known bioactivity values for the drug dx, but not for the protein px. (d) The New Drug-Target Pair scenario: neither the drug dx nor protein px is present in the training set, i.e., there exist no bioactivity values neither for the drug dx nor protein px. In this work, we focused primarily on two most common and practical prediction scenarios of (a) and (b), which correspond to filling the gaps in existing experimentally-measured drug-target interaction maps and prediction of target interactions for an investigational drug compound, respectively.