Skip to main content

Table 2 Cell line with type of cancer in parenthesis, scaffolds involved, regression summary and number of compounds in various cell lines based QSAR models.

From: Analogue-based approaches in anti-cancer compound modelling: the relevance of QSAR models

No Cell line
(Type)
Scf Regression equation R2 Rcv 2 AE O s2 F # Comp.
           TR TS PD
M1 A375
(melanoma)
S6, S8 = 20.6264* MiVH -6.19186* ZXS/ZXR -9719.75*MiNRC -10.9946 0.79 0.76 0.40 1 0.308 43.24 38 12 19
M2 B16-F1
(melanoma)
S6, S8 = -91.8353*MaPCH-4.3472* ZXS/ZXR-96.017*Ma1ERN +10.0303 0.83 0.80 0.36 1 0.255 55.71 38 12 19
M4 KB
(nasopharyngeal)
S4 = 769.472* HC-2/Tz +9193.37* Mi1ERN +68.531* MiNACH -7.67576 0.80 0.71 0.24 0 0.065 40.02 17 4 0
M5 WM-164
(melanoma)
S6 P = 0.172982*PS-3AZ-0.968448* KHI3-1205.47* MiNRN+7.6019 0.81 0.77 0.16 1 0.062 33.70 24 6 7
M6 PC-3
(prostate)
S6, S8 = -3.14901* ZXS/ZXR -95.5552* MaPCH -2.37816*FS-2Pz+ 9.10613 0.83 0.79 0.31 0 0.136 77.55 29 12 23
M8 UACC-62
(melanoma)
S10 = -256.732* MaPCN +13.6563 *MaPC+6.61641 *MaVO-34.0055 0.81 0.74 0.30 1 0.094 51.96 21 5 6
M9 SF-539
(CNS)
S10 = 0.000240276*GIAP+ 0.113696*TPCCMD +13.1633*MaBOO-20.9902 0.81 0.75 0.28 0 0.120 37.46 21 6 3
M10 LNCaP
(prostate)
S6, S7, S8 = -0.0396034* ZXS +0.412216* SIC0-24.4713* RNN +0.80884 0.75 0.74 0.46 1 0.370 67.18 58 15 24
M11 PPC-1
(prostate)
S6, S8 = 0.00211384* PS-1Z-17.6992* RPCGZ -11.5927* MaNACH +8.51731 0.80 0.77 0.27 1 0.150 48.02 37 12 20
M12 HCT-116
(colon)
S10 = -7.48415* ZXS/ZXR+ 0.157414 *TPCCMD-0.0635789* RNCSQ+ 7.09755 0.86 0.77 0.19 1 0.157 17.06 24 9 5
M15 MB-231
(breast)
S2, S9 = -0.031465*YZS+ 5.30324* FBCSq +1.16981* MaPBO+1.40089 0.70 0.66 0.35 1 0.191 25.79 37 11 21
M17 A549
(lung)
S1, S4 = -0.505821* RPCSZ -3.59234* MiVO +2.58951* MiBOO + 9.37614 0.64 0.56 0.32 1 0.135 30.22 38 9 12
M19 HOP-62
(lung)
S10 = -12.0428* ZXS/ZXR -4.44967* RPCSQ -0.819861* NF +12.2371 0.70 0.66 0.38 0 0.278 14.69 23 5 2
M20 KBvin
(nasopharyngeal)
S4 = -5.01349**HC-1/T -5.01844* PP/SD -0.768924* MaNACC +3.76504 0.99 0.97 0.02 0 0.047 31.28 17 4 0
M21 MCF-7
(breast)
S1, S10 = -5.62149*ZXS/ZXR-64.0123* MiNRO-100.36*Mi1ERC+5.76988 0.72 0.65 0.32 1 0.138 31.51 39 9 36
M23 SN12C
(renal)
S10 = -0.339628*NN-8.49682* XYS/XYR-1.57052* MiVC+ 14.5423 0.60 0.51 0.25 1 0.048 17.50 17 8 5
M26 OVCR-3
(ovarian)
S1, S10 = -0.00524177* MSA -0.300618*THCMD +2.31159* MaVO -0.441172 0.63 0.51 0.25 2 0.072 25.39 18 8 18
M29 DU 145
(prostate)
S4, S6, S8, S9, S10 = 15.0725* RNO +0.00985941* HS-1Z-25.5879* H-HC-2/ST +2.19779 0.46 0.43 0.44 1 0.391 28.73 99 18 36
M3 HeLa
(cervical)
S2, S5 = 0.298986*NN+0.00213416*W-1wP+0.849867*MiVC-2.24538 0.83 0.76 0.13 1 0.043 71.93 44 16 11
M7 U937
(lymphoma)
S3 = -22.0891* MiBOH +8.67391* MiVN -52.0125* H-HD-2/T -7.6190 0.84 0.75 0.14 0 0.029 32.41 15 4 8
M13 Hs-638
(glioblas toma)
S1 = 9.68671* MaVC -1671.96* A1ERC -2.78721*MiVO -30.7528 0.83 0.70 0.08 1 0.009 29.13 17 5 16
M14 HCT-15
(colon)
S1 = 2.33664* AVN -2.02577* MiNACN +9.95155* MaVC -46.34 0.86 0.77 0.08 0 0.021 14.25 17 8 14
M16 HL-60
(blood)
S5 = -7.57298*RNH-2.67981*RNO+ 3.66509*MaVO-2.2655 0.65 0.61 0.17 0 0.053 18.98 29 8 0
M18 MB468
(breast)
S2 = -0.184603* RPCSZ +0.0249929* RNCSZ-2.74917*MiBOH+4.0713 0.64 0.50 0.16 0 0.044 11.23 19 6 10
M22 LoVo
(colon)
S1 = 106.594* MaERC +5.20066* MaBOO-47.3247*MaVH +37.9454 0.60 0.53 0.16 0 0.038 13.92 25 6 8
M24 K562
(blood)
S2 = 0.034093* H-HC-1Q -0.273258* RPCSZ -24886* MiERC +1.64689 0.62 0.54 0.20 0 0.061 8.70 19 6 10
M25 U373-MG
(glioblas toma)
S1 = -27.0375* ANRN -0.297945* H-1E -0.195554*MaBON 0.55 0.46 0.17 0 0.043 8.18 23 6 10
M27 Fibroblast
(fibroblast)
S6 = 20.3816* MiVN +0.783874* L1E-70.268548*THCMD-59.2997 0.79 0.72 0.12 0 0.046 22.98 20 5 7
M28 RH7777
(prostate)
S6 = -43.2403*MI-A-1.24807*MaBOC-69.6817*AERN+4.96796 0.58 0.38 0.16 0 0.057 3.45 23 6 7
  1. R2 is the square of the correlation coefficient and represents the statistical significance of the model. Rcv2 is the cross-validated R2, a measure of the quality of the QSAR model. O is the number of outlier for the model. s2 is the standard deviation. F is the Fischer statistics, the ratio between explained and unexplained variance for a given number of degrees of freedom, thereby indicating a factual correlation or the significance level for QSAR models. AE is the average of absolute difference between experimental and predicted IC50 values. TR is number of molecules in training set, TE is test set molecules, PD is number of molecules for which activity was not reported, and the QSAR model predicted it.