This file contains experimental and calculated values of the endpoint for visible sets


Optimization based on the traditional correlation coefficient (r2)


SMILES is used in the model
Data from SMILES-file (#TrainingSet.txt)
Threshold=1
The number of active SMILES attributes (ASA) =110

Index of ideality of correlation has been involved
for the Monte Carlo optimization (weight= 0.1000)
Attention! Some SMILES are containing dot (i.e. "."); Dots are replaced by "^"

IMPORTANT: In the case of classic scheme W%=N101/Nall, otherwise W%=N111/Nall
Percent of ASA with presence in all sets (W%) =71

Split Quality (TRN,TST) = 26,4312

Intercept (c0) and slope (c1) calculated for each set individually:
Training set   : c0=  -8.16981 c1=   0.11527
InvTraining set: c0= -18.22419 c1=   0.25092
Calibration set: c0=  -6.22605 c1=   0.08654

Slope and intesept calculated with subtraining set give the model:

Endpoint =  -8.1698086 ( 0.1234745) +    0.1152715 ( 0.0016942) * DCW(1,25)

Statistical characteristics of the model:

N is the number of compounds in the set;
R is correlation coefficient;
Q is cross-validated correlation coefficient;
CCC is concordance correlation coefficient;
IIC is index of ideality of correlation;
s is standard error of estimation;
MAE is mean absolute error;
F is Fischer F-ratio

Blk is the number of SMILES attributes in given SMILES, which are blocked
All is the number of all SMILES attributes in given SMILES string

Y-randomization: 1000 permutations for each average
The randomized correlation coefficients are not constants,
but they have some range, as rule, about 0.03. 

                                 : Train  :InvTrain: Calib 
                                 :      39:      27:      17
                                 :  0.7214:  0.8702:  0.8250
                                1:  0.1088:  0.1499:  0.0638
                                2:  0.0019:  0.0030:  0.0066
                                3:  0.0090:  0.0106:  0.0390
                                4:  0.0843:  0.0512:  0.0226
                                5:  0.0001:  0.0994:  0.0834
                                6:  0.1986:  0.0006:  0.1445
                                7:  0.0079:  0.0014:  0.1080
                                8:  0.0032:  0.0014:  0.0602
                                9:  0.0562:  0.0446:  0.1379
                               10:  0.0810:  0.0137:  0.0922
Rr2, i.e. average randomized R   :  0.0551:  0.0376:  0.0758
   CRp2=R*sqrt(R2-Rr2) [1]       :  0.6933:  0.8512:  0.7861:

 CRp2 should be greater 0.5 [1]

REFERENCE for Y-scrambling
[1] P.K. Ojha, K. Roy, Comparative QSARs for antimalarial endochins:
    Importance of descriptor-thinning and noise reduction prior to
     feature selection, Chemometr. Intell. Lab. 109 (2011) 146-161

External validation characteristics for the model taken from
REFERNCES
[1] Golbraikh A., Tropsha A. J.Mol.Graph.Model. 20(2002)269; // R02, k,kk
[2] Roy P.P., Roy K. Chem. Biol. Drug Des. 73(2009) 442; // Rm2
[3] PK Ojha,I Mitra, RN Das,K Roy,Chemometr Intell Lab 107(2011)194-205
    // Average of Rm2 and absolute difference Rm2(x,y)-Rm2(y,x)
    // x,y are experimental and predicted values of endpoint
[4] I-Kuei Lin, L. A concordance correlation coefficient to
    evaluate reproducibility (1989) Biometrics, 45 (1), 255-268.
[5] Toropova, A.P.,Toropov, A.A. The index of ideality of correlation:
    A criterion of predictability of QSAR models for skin permeability?
    (2016) Science of the Total Environment, . Article in Press.

The range of endpoint:
Min= -2.1 Max=  1.7 Middle= -0.2

n           =      17
r2          =    0.8250
r02         =    0.8144
rr02        =    0.8146
(r2-r02)/r2 =    0.0129 should be < 0.1 [1]
(r2-rr02)/r2=    0.0126 should be < 0.1 [1]
k           =    1.0927 should be 0.85 <  k < 1.15 [1]
kk          =    0.7458 should be 0.85 < kk < 1.15 [1]
Rm2(test)   =    0.7400 should be > 0.5 [2]

n           =      17
r2          =    0.8250
r02         =    0.8146
rr02        =    0.8144
(r2-r02)/r2 =    0.0126 should be < 0.1 [1]
(r2-rr02)/r2=    0.0129 should be < 0.1 [1]
k           =    0.7458 should be 0.85 <  k < 1.15 [1]
kk          =    1.0927 should be 0.85 < kk < 1.15 [1]
R*m2(test)  =    0.7408 should be > 0.5 [2]

Average Rm2 = 0.7404 should be larger 0.5 [3]
Delta Rm2 = 0.0008 should be lower 0.2 [3]

        :  n :  R2   :  CCC  :  IIC  :  Q2   :     s  :    MAE :  F     
Training:  39: 0.7214: 0.8381: 0.8069: 0.6947:   0.487:   0.363:       96
InvTrain:  27: 0.8702: 0.6703: 0.6950: 0.8495:   0.769:   0.631:      168
Calib   :  17: 0.8250: 0.8869: 0.9080: 0.7896:   0.492:   0.368:       71

Training set is indicated by    +;
Invisisble training set is indicated by -;
Calibration set is indicated by #

C l a s s i c a l   s c h e m e :
    Training set - Calibration set
B a l a n c e   o f   c o r r e l a t i o n s :
    Training set - invisible Training set - Calibration set

 :SMILES                                                                 :         DCW:        Expr:        Calc:   Expr-Calc:Blk/All: ID 
+:Cl^O=C(O)C2=CN(c1nc(c(F)cc1C2=O)N3CCC(N)C3)c4ccccn4                    :    60.37086:     -1.4330:     -1.2108:     -0.2222:  0/100: 3
+:Cl^Cc1cc(on1)N2C=C(C(=O)O)C(=O)c3cc(F)c(nc23)N4CCC(N)C4                :    70.21406:     -0.1910:     -0.0761:     -0.1149:  0/108: 7
+:Cl^NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nncs4                     :    62.39022:     -1.1650:     -0.9780:     -0.1870:  0/ 98: 8
+:Cl^NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4                     :    68.20057:     -1.4100:     -0.3082:     -1.1018:  0/ 98: 10
+:Cl^NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nc(cs4)C(C)(C)C           :    71.00533:     -0.3100:      0.0151:     -0.3251:  0/118: 14
+:Cl^NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nc(cs4)c5ccccc5           :    70.39354:      0.9390:     -0.0554:      0.9944:  0/118: 15
+:Cl^NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4ncc(Br)s4                 :    78.33462:      0.7280:      0.8599:     -0.1319:  0/104: 17
+:Cl^NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4ncc(OC)s4                 :    70.76652:      0.0640:     -0.0124:      0.0764:  0/106: 18
+:Cl^NC1CCN(C1)c2nc5c(cc2F)C(=O)C(=CN5c3nc4ccccc4s3)C(=O)O               :    78.33565:      0.9390:      0.8601:      0.0789:  0/110: 19
+:Cl^NC1CCN(C1)c2cc3N(C=C(C(=O)c3cn2)C(=O)O)c4nccs4                      :    69.20339:     -0.4470:     -0.1926:     -0.2544:  0/ 96: 22
+:Cl^O=C(O)C2=CN(c1nccs1)c3nc(NCCN)c(F)cc3C2=O                           :    58.36909:     -1.4570:     -1.4415:     -0.0155:  0/ 86: 25
+:Cl^O=C(O)C3=CN(c1nccs1)c4nc(N2CCCC2)c(F)cc4C3=O                        :    76.36635:      1.0190:      0.6331:      0.3859:  0/ 92: 26
+:Cl^O[C@H]1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4                 :    81.32856:      1.2750:      1.2051:      0.0699:  0/106: 28
+:Cl^N[C@@H]1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4                :    76.70293:      1.3710:      0.6719:      0.6991:  0/106: 29
+:Cl^CN(C)C1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4                 :    74.94502:      0.8500:      0.4692:      0.3808:  0/106: 31
+:Cl^CC1(N)CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4                  :    79.32339:      1.1750:      0.9739:      0.2011:  0/104: 32
+:Cl^C[C@@H]1CN(C[C@@H]1N)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4          :    80.44546:      0.8350:      1.1033:     -0.2683:  0/116: 34
+:Cl^N[C@H]1CN(C[C@@H]1O)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4           :    74.00788:     -0.7280:      0.3612:     -1.0892:  0/116: 35
+:Cl^N[C@H]1CN(C[C@H]1OC)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4           :    72.80937:      0.6840:      0.2230:      0.4610:  0/118: 38
+:Cl^OC[C@@]1(N)CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4             :    77.49812:      0.6840:      0.7635:     -0.0795:  0/112: 40
+:Cl^O=C(O)C4=CN(c1nccs1)c5nc(N2C[C@@H]3CCCN[C@@H]3C2)c(F)cc5C4=O        :    71.91795:      0.1360:      0.1203:      0.0157:  0/120: 42
+:Cl^CN2CC=C1CN(CC12)c3nc4N(C=C(C(=O)c4cc3F)C(=O)O)c5nccs5               :    74.95298:      1.0370:      0.4701:      0.5669:  0/110: 43
+:Cl^NCC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4                    :    70.38255:      0.5860:     -0.0567:      0.6427:  0/100: 45
+:Cl^NC1CCN(CC1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4                    :    70.38255:     -0.6220:     -0.0567:     -0.5653:  0/100: 48
+:Cl^COc1ccccc1N2CCN(CC2)c3nc4N(C=C(C(=O)c4cc3F)C(=O)O)c5nccs5           :    64.87836:     -0.3170:     -0.6912:      0.3742:  0/118: 49
+:Cl^O=C(O)C3=CN(c2nc(N1CCSCC1)c(F)cc2C3=O)c4nccs4                       :    66.18707:     -0.6470:     -0.5403:     -0.1067:  0/ 94: 51
+:Cl^O=C(O)C2=CN(c1nccs1)c3nc(O)c(F)cc3C2=O                              :    54.77031:     -1.5120:     -1.8564:      0.3444:  0/ 80: 54
+:Cl^NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2N)C(=O)O)c4nccs4                     :    70.26063:     -0.4330:     -0.0708:     -0.3622:  0/ 98: 57
+:Cl^FC(F)(F)c1cc(nc2N(C=C(C(=O)c12)C(=O)O)c3nccs3)N4CCC(N)C4            :    76.09628:      0.6370:      0.6019:      0.0351:  0/116: 61
+:Cl^C[C@H]1CN(C[C@@H]1N)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O            :    79.24911:      1.5880:      0.9654:      0.6226:  0/114: 66
+:Cl^O=C(O)C2=CN(c1nccs1)c3nc(ccc3C2=O)N4C[C@@H]5CCCN[C@@H]5C4           :    83.01513:      1.3690:      1.3995:     -0.0305:  0/114: 72
+:Cl^CNC1CCCN(C1)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O                    :    79.88277:     -0.1300:      1.0384:     -1.1684:  0/100: 83
+:Cl^O=C(O)C2=CN(c1nccs1)c3nc(ccc3C2=O)N4Cc5ccccc5CC4                    :    64.81802:     -1.3930:     -0.6981:     -0.6949:  0/100: 84
+:Cl^O=C(O)C2=CN(c1nccs1)c3nc(C=C)ccc3C2=O                               :    61.12184:     -0.5240:     -1.1242:      0.6002:  0/ 78: 88
+:NC1CCN(C1)c2nc3N(C=CC(=O)c3cc2F)c4nccs4                                :    75.32320:      0.2770:      0.5128:     -0.2358:  0/ 78: 92
+:NC1CCN(C1)c3nc4N(C=C(Cc2ccccc2)C(=O)c4cc3F)c5nccs5                     :    75.76878:      0.7690:      0.5642:      0.2048:  0/100: 93
+:NC1CCN(C1)c2nc3N(C=C(O)C(=O)c3cc2F)c4nccs4                             :    72.57748:      0.3160:      0.1963:      0.1197:  0/ 84: 96
+:CN[C@H]1CN(C[C@@H]1OC)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C=O                :    78.65842:      1.0960:      0.8973:      0.1987:  0/108: 97
+:CN[C@H]1CN(C[C@@H]1OC)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C(C)=O             :    79.10140:      0.8290:      0.9483:     -0.1193:  0/114: 99
-:Cl^NC1CCN(C1)c2nc3c(cc2F)C(=O)C(=CN3C4CC4)C(=O)O                       :    65.87594:     -1.3760:     -0.5762:     -0.7998:  0/ 94: 4
-:Cl^NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4ccno4                     :    66.64766:     -1.4180:     -0.4872:     -0.9308:  1/ 98: 6
-:Cl^NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4ncc(Cl)s4                 :    74.84225:      0.6390:      0.4574:      0.1816:  2/104: 16
-:Cl^NC1CCN(C1)c3ncc4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O                      :    77.89510:      0.8820:      0.8093:      0.0727:  0/ 96: 20
-:Cl^NC1CCN(C1)c2nc3N(N=C(C(=O)c3cc2F)C(=O)O)c4nccs4                     :    66.82961:     -1.4240:     -0.4663:     -0.9577:  1/ 98: 21
-:Cl^NC1CCN(C1)c2cc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4                     :    69.38741:     -1.4270:     -0.1714:     -1.2556:  0/ 98: 23
-:Cl^NC1CCN(C1)c3c(F)cc4C(=O)C(=CN(c2nccs2)c4c3F)C(=O)O                  :    66.71080:     -2.1470:     -0.4800:     -1.6670:  0/104: 24
-:Cl^C[C@H]1CN(C[C@@H]1N)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4           :    77.87987:      1.5500:      0.8075:      0.7425:  0/116: 33
-:Cl^N[C@@H]1CN(C[C@H]1OC)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4          :    75.37496:      0.7750:      0.5188:      0.2562:  0/118: 36
-:Cl^N[C@H]1CN(C[C@@H]1OC)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4          :    75.37496:      1.2460:      0.5188:      0.7272:  0/118: 37
-:Cl^O=C(O)C4=CN(c1nccs1)c5nc(N2C[C@@H]3NCCO[C@H]3C2)c(F)cc5C4=O         :    70.42403:     -0.3790:     -0.0519:     -0.3271:  0/120: 41
-:Cl^N[C@H]1C=CC[C@H]2CN(C[C@@H]12)c3nc4N(C=C(C(=O)c4cc3F)C(=O)O)c5nccs5~:    75.92386:      0.4550:      0.5820:     -0.1270:  1/136: 44
-:Cl^NC[C@H]1CN(C[C@H]1Cl)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4          :    74.25015:      0.4340:      0.3891:      0.0449:  2/118: 46
-:Cl^NCC1CN(CCO1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4                   :    69.87948:     -0.6300:     -0.1147:     -0.5153:  0/102: 50
-:Cl^O=C(O)C3=CN(c1nccs1)c4nc(n2ccnc2)c(F)cc4C3=O                        :    69.50994:     -1.4470:     -0.1573:     -1.2897:  0/ 92: 52
-:Cl^NC1CCN(C1)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O                      :    74.51676:      1.5530:      0.4199:      1.1331:  0/ 96: 55
-:Cl^NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2O)C(=O)O)c4nccs4                     :    66.82393:     -1.0620:     -0.4669:     -0.5951:  1/ 98: 58
-:Cl^NC1CCN(C1)c3cc(N)c4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O                   :    77.45143:      1.6610:      0.7581:      0.9029:  0/102: 62
-:Cl^CNC1CCN(C1)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O                     :    77.70079:      1.5700:      0.7869:      0.7831:  0/ 98: 63
-:Cl^C[C@H]1CN(C[C@@H]1NC)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O           :    76.93051:      1.5070:      0.6981:      0.8089:  0/116: 67
-:Cl^ClC[C@H]1CN(C[C@@H]1N)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O          :    78.05962:      1.2280:      0.8282:      0.3998:  1/116: 68
-:Cl^N[C@H]1CN(C[C@@H]1OC)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O           :    76.74420:      1.3330:      0.6766:      0.6564:  0/116: 73
-:Cl^CN[C@H]1CN(C[C@@H]1OC)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O          :    79.92823:      1.3030:      1.0436:      0.2594:  0/118: 78
-:Cl^C[C@H]1CN(C[C@@H](C)N1)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O         :    78.24478:      0.6780:      0.8496:     -0.1716:  1/120: 81
-:Cl^COc1ccccc1N2CCN(CC2)c4ccc5C(=O)C(=CN(c3nccs3)c5n4)C(=O)O            :    72.70039:     -0.3340:      0.2105:     -0.5445:  0/116: 82
-:Cl^Cc1cc(cc(C)n1)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O                  :    66.72137:     -1.2870:     -0.4787:     -0.8083:  0/104: 87
-:NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)OCC)c4nccs4                      :    75.68961:      0.4720:      0.5550:     -0.0830:  0/ 98: 91
#:Cl^O=C(O)C2=CN(c1nc(c(F)cc1C2=O)N3CCC(N)C3)c4ccc(F)cc4                 :    59.19233:     -0.7350:     -1.3466:      0.6116:  0/106: 2
#:Cl^NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4cccs4                     :    66.88400:     -0.5060:     -0.4600:     -0.0460:  0/ 98: 5
#:Cl^Cn4nccc4N1C=C(C(=O)O)C(=O)c2cc(F)c(nc12)N3CCC(N)C3                  :    58.53590:     -1.4290:     -1.4223:     -0.0067:  1/104: 9
#:Cl^NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4ncc(C)s4                  :    71.20499:      0.1750:      0.0381:      0.1369:  0/104: 12
#:Cl^NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nc(C)c(C)s4               :    72.01543:      0.3500:      0.1315:      0.2185:  0/110: 13
#:Cl^O[C@@H]1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(=O)O)c4nccs4                :    83.89415:      0.7630:      1.5008:     -0.7378:  0/106: 27
#:Cl^O=C(O)C2=CN(c1nccs1)c3nc(SCCN)c(F)cc3C2=O                           :    55.99875:     -1.4360:     -1.7147:      0.2787:  1/ 86: 53
#:Cl^[O-][N+](=O)c3cc4C(=O)C(=CN(c1nccs1)c4nc3N2CCC(N)C2)C(=O)O          :    75.44680:     -0.7550:      0.5271:     -1.2821:  9/120: 56
#:Cl^CC1(N)CCN(C1)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O                   :    85.63958:      1.2910:      1.7020:     -0.4110:  0/102: 64
#:Cl^CC1CC(N)CN1c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O                     :    78.13650:      0.5280:      0.8371:     -0.3091:  0/ 98: 69
#:Cl^CCN[C@H]1CN(C[C@@H]1OC)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C(=O)O         :    82.11021:      1.2200:      1.2952:     -0.0752:  0/120: 76
#:Cl^O=C(O)C2=CN(c1nccs1)c3nc(ccc3C2=O)N4CCOCC4                          :    69.85751:      0.4750:     -0.1172:      0.5922:  0/ 88: 85
#:Cl^O=C(O)C2=CN(c1nccs1)c3nc(ccc3C2=O)c4ccccc4                          :    62.25369:     -1.2580:     -0.9937:     -0.2643:  0/ 88: 86
#:Cl^O=C(O)C2=CN(c1nccs1)c3nc(ccc3C2=O)c4ccnn4                           :    58.07428:     -1.1070:     -1.4755:      0.3685:  0/ 86: 90
#:NC1CCN(C1)c2nc3N(C=C(C(=O)c3cc2F)C(N)=O)c4nccs4                        :    76.07033:      0.1440:      0.5989:     -0.4549:  0/ 94: 95
#:CN[C@H]1CN(C[C@@H]1OC)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)CO                 :    79.09987:      0.8470:      0.9482:     -0.1012:  0/106: 98
#:CN[C@H]1CN(C[C@@H]1OC)c3ccc4C(=O)C(=CN(c2nccs2)c4n3)C\C=C/C(=O)OC      :    79.89797:      0.6820:      1.0402:     -0.3582:  6/128: 100
