Skip to main content

Table 1 Details about benchmark datasets

From: A unified frame of predicting side effects of drugs by using linear neighborhood similarity

Dataset #drug #side effect #substructure #target #transporter #enzyme #pathway # indication
Pauwels’s dataset 888 1385 881 N.A N.A N.A N.A N.A
Mizutani’s dataset 658 1339 881 1368 N.A N.A N.A N.A
Liu’s dataset 832 1385 881 786 72 111 173 869
SIDER 4 dataset 1080 2260 881 1050 96 160 268 2537
  1. N.A means unavailable information