_PROBLEM CoEPrA-2006_Regression_003_Dataset_2
 
_GROUP_NAME Curt Breneman

_GROUP_MEMBERS
Kristin Bennett
Charles Bergeron
Curt Breneman
Theresa Hepburn
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, 26 SIMIL descriptors were generated;
 these describe similarities in residues based on the following
 classes: tiny, small, positive, negative, polar, non-polar,
 aliphatic, and aromatic.

 Each feature was centred to zero median and unit absolute deviation.

 Lossless data compression was accomplished by seperately considering
 each amino acid's descriptors and the SIMIL descriptors. Principal
 components analysis on each descriptor subset was used to find
 components of nonzero variance. This resulted in 185 components.

 Data reduction was accomplished by considering the covariance
 matrix C and an estimate S of how the covariance differs between
 the calibration and first prediction sets. Minimum noise
 fractions, a generalized principal components analysis, was used.
 The generalized singular value decomposition of C with
 respect to S found "noise"-insensitive features. SNR is given by
 the singular values minus one; an SNR cutoff of 10 was chosen;
 hence, there remained 148 features.

 Kernel partial least squares was used for modeling. Model selection
 found that 4 latent variables and an exponential kernel function
 with sigma=1000 was retained. The resulting q^2 was 0.3822 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 as follows:

B =

         -15.6813607570176
         -9.42790445676816
         -8.66189297018583
         -9.93154009239204
         -6.40969780097585
         -7.28191377167004
         -3.75552876225701
         -8.58276892828209
         -5.17496020098558
         -1.56948884161684
         -6.28822686454907
         -2.61507472154591
         -5.86425128380494
         -8.85129800235377
         -4.23593559781983
         -6.73486221710064
         -4.12845693396226
          -4.8194730359042
          -5.2190443738612
         -7.66522564355446
         -1.96850266183281
         -4.91025334670188
         -6.70842864094941
          1.58143300972474
         -5.99299472281593
         -3.88120885030259
         -1.62241538791443
         -3.29961738383301
         -8.68932734738482
         0.407539209229032
         -2.76064139022652
          1.93847011340118
         -2.52487260758584
         -4.17288516466459
         -7.19374006130904
         -4.17147244232503
         -1.06938072898093
         -3.21137973148393
         -3.14378288204505
         -4.69359064892285
         -5.63090241021722
        -0.298031213500826
         -3.80193646855283
          1.22816239547553
         -4.60465702566834
        -0.162668899258707
         -2.87221837285775
         -3.26583091959754
         -2.47820312028539
         -1.01764339366236
         -2.01809385116099
         -3.35777845113554
         -2.68529382778804
         -1.48095915337912
        -0.392125602921693
          3.52999758995796
         -1.27668119748472
          2.20356231148548
         -2.69012679767703
          -3.0826510459201
         -3.03777263443175
         -3.81522473917964
         -2.95489517678838
         -1.46600801890124
          4.23378012589996
          3.39061920542751
          4.62093170489756
          0.76101485438306
         -1.06831773062057
          1.31720623631879
          2.01639210966206
          1.02250476220519
          1.21190200095021
          4.25164116986223
         -1.75698498591607
         -3.56101506124742
        -0.300836805757353
         -5.38660205732338
        -0.909981125152722
          2.67403652104354
         -1.82030710796276
         -2.77774427223599
        -0.166801220375569
         -1.76625365895771
          1.43441007509574
          2.17295711964932
          4.05118479734694
          1.30004633492913
          4.87054076815175
          5.27700583076627
          5.16595184889003
           3.7505606252977
           8.3393448185694
          1.19683000217075
          4.42678419198064
          4.73584606941331
          2.12149559966008
         0.866464687938236
          5.28262540197609
          3.80298695780498
          5.32102035288612
          1.78314597660842
          1.46565518066376
          4.70673652849943
          5.54360539976645
         -1.68478494784154
          3.48587352143366
          2.07288443265245
          10.2015808845345
          10.6240230165646
          6.12277922727913
         0.281166892358236
          1.42039254800417
          9.32821272773033
          5.03589769607138
          4.38923693760364
          5.63546958374979
          4.64030074553935
           8.7464468188418
         0.750797044768218
          3.61777342217929
          7.62801404890132
          2.92572724661179
          5.57165922118489
          9.23885681544552
          6.83391230252171
          10.0729348780033
          6.57990087263573
          6.03811890294356
          5.48880105355749
          7.54168709434206
          9.47167115652201
          7.57439281512461

b =

          7.08152631578948

_PREDICTION
Obj_00001 7.183
Obj_00002 7.404
Obj_00003 6.710
Obj_00004 7.068
Obj_00005 7.518
Obj_00006 7.954
Obj_00007 6.706
Obj_00008 6.880
Obj_00009 7.395
Obj_00010 8.034
Obj_00011 6.594
Obj_00012 6.821
Obj_00013 6.546
Obj_00014 6.689
Obj_00015 6.451
Obj_00016 7.030
Obj_00017 6.335
Obj_00018 6.546
Obj_00019 6.572
Obj_00020 6.581
Obj_00021 6.999
Obj_00022 6.611
Obj_00023 6.611
Obj_00024 6.951
Obj_00025 6.436
Obj_00026 6.487
Obj_00027 7.288
Obj_00028 6.556
Obj_00029 6.611
Obj_00030 7.100
Obj_00031 6.738
Obj_00032 7.371
Obj_00033 7.285
Obj_00034 7.334
Obj_00035 6.743
Obj_00036 6.774
Obj_00037 7.096
Obj_00038 6.859
Obj_00039 7.511
Obj_00040 5.505
Obj_00041 5.705
Obj_00042 7.147
Obj_00043 7.321
Obj_00044 6.389
Obj_00045 7.061
Obj_00046 6.799
Obj_00047 7.094