Skip to main content

Advertisement

Table 1 Distribution of the compounds and their associated protein targets in our ChEMBL17 dataset

From: A multi-label approach to target prediction taking ligand promiscuity into account

Number of Annotated Targets 1 2 3 4 5 6 7 8 9 ≥10
Number of Compounds 54,563 7,937 1,571 321 240 191 132 60 42 530
% of Total Number of Compounds 83.1 % 12.1 % 2.39 % 0.49 % 0.36 % 0.29 % 0.2 % 0.09 % 0.06 % 0.8 %
  1. The table shows that 83.1 % of the total compounds were annotated against only one target protein, while the remaining 16.9 % of compounds were annotated against two or more protein targets; just over one-sixth of our ChEMBL17 dataset comprises multi-label ligands