Table 2 The details of the training set and four test sets
From: ZeroBind: a protein-specific zero-shot predictor with subgraph matching for drug-target interactions
Dataset | Number of proteins | Number of drugs | Number of interactions |
|---|---|---|---|
Training set | 426 | 248,997 | 392,032 |
Transductive test set | 392 | 16,946 | 17,314 |
Semi-inductive test set | 1575 | 159,182 | 228,320 |
Inductive test set | 688 | 7261 | 10,165 |
Few-shot test set | 1253 | 127,665 | 160,948 |
