From: PubChem structure–activity relationship (SAR) clusters
Initial | 3-D clusters | 2-D clusters | Any clusters | ||||
---|---|---|---|---|---|---|---|
ST ST-opt | ComboT ST-opt | CT CT-opt | ComboT CT-opt | ||||
Number of CIDs | |||||||
Assay-centric clusters (from Set A) | 843,845 | 669,504 (79.3%) | 746,042 (88.4%) | 747,969 (88.6%) | 747,586 (88.6%) | 802,383 (95.1%) | 829,279 (98.3%) |
Protein-centric clusters (from Set B) | 400,599 | 313,282 (78.2%) | 356,954 (89.1%) | 360,200 (89.9%) | 357,543 (89.3%) | 382,737 (95.5%) | 397,197 (99.2%) |
Pathway-centric clusters (from Set C) | 265,470 | 213,738 (80.5%) | 243,006 (91.5%) | 245,215 (92.4%) | 243,378 (91.7%) | 257,170 (96.9%) | 264,338 (99.6%) |
Number of UIDs | |||||||
Assay-centric clusters (from Set A) | 548,071 | 218,789 (39.9%) | 244,381 (44.6%) | 245,334 (44.8%) | 246,625 (45.0%) | 264,311 (48.2%) | 274,435 (50.1%) |
Protein-centric clusters (from Set B) | 4,280 | 3,340 (78.0%) | 3,419 (79.9%) | 3,438 (80.3%) | 3,428 (80.1%) | 3,620 (84.6%) | 3,660 (85.5%) |
Pathway-centric clusters (from Set C) | 4,540 | 3,973 (87.5%) | 4,073 (89.7%) | 4,097 (90.2%) | 4,089 (90.1%) | 4,149 (91.4%) | 4,168 (91.8%) |