_PROBLEM CoEPrA-2006_Regression_001
 
_GROUP_NAME Curt Breneman

_GROUP_MEMBERS
Kristin Bennett
Charles Bergeron
Curt Breneman
Michael Krein
Min Li
Steven Mulick
Sukumar Nagamani
Matthew Sundling

_ADDRESS
Rensselaer Exploratory Centre for Cheminformatics Research, Rensselaer 
Polytechnic Institute, 110 Eighth Street, Troy, New York 12180-3522, 
United States of America

_MODELING_PROCEDURE
For each nonapeptide, 5787 descriptors are provided. Additionally, 584 
RECON (TAE/RECON electron-density derived descriptors), MOE 
(geometrical, structural, physiochemical and topological 2D descriptors) and RAD 
(topological autocorrelation 2D surface descriptors) features. 
Descriptor names and values for each sample are provided in attached 
comma-separated files CoEPrA-2006-001-Calibration-RECON-RA2D-MOE2D.ff and 
CoEPrA-2006-001-Prediction-RECON-RA2D-MOE2D.ff. Invariant descriptors in either 
of the calibration or prediction sets were eliminated, and the number 
of descriptors is doubled as both the raw values and the order of 
magnitude (as calculated by taking base-10 logarithms) were used as distinct 
descriptors. Kernel partial least squares was used for modeling. Model 
selection found that 7 latent variables and a Gaussian kernel function 
with sigma=198.97 was retained. The resulting q^2 was 0.7120 for 
leave-one-out cross-validation across the calibration set. Consider model 
f=KB+b where f is the prediction reported below, K is the kernel matrix, B 
are the regression coefficients and b is the bias constant. Then B and 
b are given as follows:

B =

      -7.0366
      -9.0362
      -4.6662
     -0.92212
      -1.4065
      -1.3545
      -1.3446
      -2.8389
     -0.25222
      -2.0326
     -0.61765
     -0.11273
    -0.089821
      -1.2014
      0.82427
      -1.1382
      -1.3106
      -1.3981
       1.0272
     -0.48433
     -0.36261
      0.95789
      0.31089
      -1.8209
       1.8962
      -7.9889
      0.79015
      -1.4425
      -2.5393
      0.61188
     -0.47669
      -3.8753
     -0.50616
    -0.017512
     -0.70749
    -0.032159
      0.20132
      -1.9632
       1.1421
      -1.9053
      -1.9466
      -2.8479
       1.4421
     -0.24486
      -1.3126
     -0.94971
      -1.3875
     -0.50348
     -0.32953
       1.0948
      0.23828
       0.5623
      0.25653
     0.043826
     0.033366
       -1.786
       1.6869
     0.023497
      -2.5753
      0.50546
        1.181
       2.7925
       -1.217
       1.3486
     0.074856
     -0.45026
     -0.78018
       1.5561
       -1.481
      0.28087
      0.26093
      0.37203
        4.004
       2.6655
     0.038801
       1.2526
      -1.1011
      0.30471
       2.4407
        2.128
       5.1445
       1.3764
       1.1632
       3.1865
       1.4779
       5.0752
       1.7739
       8.9058
       13.047


b =

       5.4117

_PREDICTION
Obj_00001 5.706
Obj_00002 5.915
Obj_00003 4.652
Obj_00004 5.021
Obj_00005 7.162
Obj_00006 6.786
Obj_00007 5.227
Obj_00008 3.850
Obj_00009 5.094
Obj_00010 4.433
Obj_00011 6.507
Obj_00012 3.935
Obj_00013 5.503
Obj_00014 4.742
Obj_00015 6.474
Obj_00016 5.870
Obj_00017 5.015
Obj_00018 5.793
Obj_00019 4.297
Obj_00020 3.750
Obj_00021 3.839
Obj_00022 4.839
Obj_00023 5.177
Obj_00024 5.144
Obj_00025 5.011
Obj_00026 6.346
Obj_00027 6.693
Obj_00028 5.926
Obj_00029 5.231
Obj_00030 4.385
Obj_00031 5.524
Obj_00032 6.197
Obj_00033 5.845
Obj_00034 6.059
Obj_00035 5.403
Obj_00036 6.326
Obj_00037 4.361
Obj_00038 5.104
Obj_00039 5.900
Obj_00040 4.683
Obj_00041 5.870
Obj_00042 4.723
Obj_00043 7.203
Obj_00044 4.531
Obj_00045 5.606
Obj_00046 5.337
Obj_00047 4.231
Obj_00048 5.891
Obj_00049 5.237
Obj_00050 4.887
Obj_00051 6.065
Obj_00052 6.126
Obj_00053 5.354
Obj_00054 4.095
Obj_00055 5.013
Obj_00056 5.874
Obj_00057 4.885
Obj_00058 4.643
Obj_00059 6.942
Obj_00060 4.015
Obj_00061 5.902
Obj_00062 4.921
Obj_00063 5.169
Obj_00064 5.445
Obj_00065 5.822
Obj_00066 6.348
Obj_00067 6.601
Obj_00068 5.926
Obj_00069 5.724
Obj_00070 4.972
Obj_00071 3.277
Obj_00072 5.857
Obj_00073 5.085
Obj_00074 5.037
Obj_00075 5.907
Obj_00076 4.548
Obj_00077 5.972
Obj_00078 6.268
Obj_00079 4.061
Obj_00080 5.752
Obj_00081 6.661
Obj_00082 5.983
Obj_00083 4.540
Obj_00084 5.378
Obj_00085 6.496
Obj_00086 5.648
Obj_00087 5.214
Obj_00088 4.931