_PROBLEM CoEPrA-2006_Regression_003 _GROUP_NAME Reiji Teramoto _GROUP_MEMBERS Reiji Teramoto _ADDRESS Fundamental and Environmental Research Laboratories, NEC Corporatopn. _MODELING_PROCEDURE We used marginalized count kernels for amino acid sequences to generate new descriptors and suppor vector regression as a learning machine.[1,2]. To select descriptors and calibrate model, we performed 10-fold cross-validation via tuning types of marginalized count kernel, gaussian kernel parameter g, coefficient of slack variables C and epsilon-insensitive p using the calibration dataset. We examined 6 types of marginalized count kernel as follows: 1. 1st-order maginalized count kernel with hidden markov models that hidden states is 3(abbreviation MCK1(h=3)). 2. 2nd-order maginalized count kernel with hidden markov models that hidden states is 3(abbreviation MCK2(h=3)). 3. 1st-order maginalized count kernel with hidden markov models that hidden states is 3(abbreviation MCK1(h=4)). 4. 2nd-order maginalized count kernel with hidden markov models that hidden states is 4(abbreviation MCK2(h=4)). 5. 1st-order maginalized count kernel with hidden markov models that hidden states is 5(abbreviation MCK1(h=5)). 6. 2nd-order maginalized count kernel with hidden markov models that hidden states is 5(abbreviation MCK2(h=5)). We examined gaussian kernel parameter g defined as follows: K(u,v) = exp(-g*|u-v|^2) We determined the final model based on the best performance of 10-fold cross-validation as follows: MCK1(h=5): c=64.0, g=0.5, p=0.5, mean squared error=0.0.53697. 1. Tsuda K, Kin T, Asai K., Marginalized kernels for biological sequences, Bioinformatics. 2002;18 Suppl 1:S268-75. 2. Vapnik V, The Nature of Statistical Learning Theory, Springer, 1999. _PREDICTION Obj_00001 7.331 Obj_00002 6.904 Obj_00003 6.618 Obj_00004 6.516 Obj_00005 7.161 Obj_00006 7.673 Obj_00007 6.967 Obj_00008 6.633 Obj_00009 7.442 Obj_00010 7.318 Obj_00011 7.141 Obj_00012 7.534 Obj_00013 7.815 Obj_00014 7.591 Obj_00015 7.250 Obj_00016 7.226 Obj_00017 7.588 Obj_00018 7.036 Obj_00019 7.402 Obj_00020 7.808 Obj_00021 6.456 Obj_00022 6.510 Obj_00023 7.225 Obj_00024 6.894 Obj_00025 7.699 Obj_00026 7.622 Obj_00027 6.274 Obj_00028 6.635 Obj_00029 7.380 Obj_00030 6.688 Obj_00031 7.582 Obj_00032 7.684 Obj_00033 6.762 Obj_00034 7.210 Obj_00035 6.683 Obj_00036 6.216 Obj_00037 6.431 Obj_00038 7.883 Obj_00039 6.730 Obj_00040 6.615 Obj_00041 8.002 Obj_00042 7.750 Obj_00043 6.894 Obj_00044 6.957 Obj_00045 7.964 Obj_00046 6.781 Obj_00047 7.214 Obj_00048 7.732 Obj_00049 7.344 Obj_00050 5.911 Obj_00051 7.177 Obj_00052 7.124 Obj_00053 7.342 Obj_00054 6.293 Obj_00055 7.068 Obj_00056 7.537 Obj_00057 6.585 Obj_00058 7.141 Obj_00059 7.469 Obj_00060 7.277 Obj_00061 7.402 Obj_00062 7.893 Obj_00063 7.351 Obj_00064 6.740 Obj_00065 7.698 Obj_00066 6.755 Obj_00067 6.672 Obj_00068 7.129 Obj_00069 6.749 Obj_00070 6.953 Obj_00071 7.853 Obj_00072 7.469 Obj_00073 7.285 Obj_00074 7.054 Obj_00075 7.122 Obj_00076 7.206 Obj_00077 6.402 Obj_00078 7.420 Obj_00079 7.641 Obj_00080 7.036 Obj_00081 6.165 Obj_00082 7.858 Obj_00083 6.841 Obj_00084 7.598 Obj_00085 7.501 Obj_00086 6.598 Obj_00087 7.102 Obj_00088 7.223 Obj_00089 5.612 Obj_00090 7.088 Obj_00091 7.837 Obj_00092 6.868 Obj_00093 7.360 Obj_00094 6.807 Obj_00095 7.182 Obj_00096 7.382 Obj_00097 7.678 Obj_00098 6.523 Obj_00099 7.267 Obj_00100 7.430 Obj_00101 7.709 Obj_00102 6.755 Obj_00103 7.161 Obj_00104 7.875 Obj_00105 6.240 Obj_00106 6.862 Obj_00107 7.014 Obj_00108 7.849 Obj_00109 7.401 Obj_00110 6.431 Obj_00111 7.053 Obj_00112 7.359 Obj_00113 7.829 Obj_00114 7.049 Obj_00115 7.277 Obj_00116 7.390 Obj_00117 7.114 Obj_00118 7.575 Obj_00119 7.426 Obj_00120 6.571 Obj_00121 6.362 Obj_00122 6.855 Obj_00123 7.039 Obj_00124 7.484 Obj_00125 6.816 Obj_00126 7.522 Obj_00127 7.450 Obj_00128 7.300 Obj_00129 6.451 Obj_00130 7.191 Obj_00131 7.768 Obj_00132 7.407 Obj_00133 6.947