Skip to main content

Table 1 Overview of the 24 test assays used in the validation set

From: Combining structural and bioactivity-based fingerprints improves prediction performance and scaffold hopping capability

AID Compounds tested Actives % Actives Target information Assay type
522 64907 1225 1.89% Nuclear receptor Steroidogenic Factor 1 (SF-1) Cell-based
527 24074 64 0.27% Bacterial Quorum Sensing Cell-based
555 65239 316 0.48% Mevalonate kinase Biochemical
560 64907 979 1.51% Retinoic Acid Receptor-related orphan receptor A (RORA) Cell-based
746 59787 366 0.61% c-Jun N-Terminal Kinase 3 (JNK3) Biochemical
798 218716 302 0.14% Coagulation factor XIa Biochemical
1006 195564 2976 1.52% Compounds inhibiting luciferase Biochemical
1273 127297 1153 0.91% Insulin promoter activity—Proinsulin Cell-baseda
1515 217964 445 0.20% Retinoblastoma binding protein 9 (RBBP9) Biochemical
2129 315002 2199 0.70% BCL2-related protein, long isoform (BCLXL). Biochemical
2280 324750 1419 0.44% GLD-1 protein—TGE RNA interaction. Biochemical
2540 330397 4119 1.25% Sentrin-specific protease 8 (SENP8) Biochemical
2544 330397 393 0.12% Intestinal alkaline phosphatase Biochemical
2553 305614 3253 1.06% Transient receptor potential cation channel C6 (TRPC6) Cell-baseda
2606 324751 157 0.05% Membrane-associated serine protease Rv3671c Biochemical
463104 331676 1100 0.33% Adaptive arm of the Unfolded Protein response Cell-based
504406 323914 194 0.06% UDP-galactopyranose mutase (UGM) enzyme Biochemical
504454 339285 1446 0.43% Beta-2AR agonists-b2AR Cell-based
588497 340322 780 0.23% Botulinum neurotoxin light chain F protease Biochemical
602363 347157 446 0.13% Modulators of the fidelity of start codon recognition Cell-based
623901 332759 470 0.14% Inhibitors of miR-122 (miRNA) Cell-based
624414 400339 482 0.12% Mucolipin-1 Transient Receptor Potential 1 (TRPML1) Cell-based
686964 369939 1149 0.31% Methyl-CpG binding domain protein 2 Biochemical
720700 369939 3123 0.84% Phospholipase C, gamma 1 Biochemical
  1. Shown are their PubChem AID, total number of compounds tested in assay, and the proportion of active compounds, assay target information, and assay type. Compounds are labeled active or inactive based on the activity flag set in the PubChem data
  2. aAssay types were not indicated in PubChem for these assays and were interpreted manually