_PROBLEM CoEPrA-2006_Regression_002

_GROUP_NAME Reiji Teramoto

_GROUP_MEMBERS
Reiji Teramoto

_ADDRESS

_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
2-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 2-fold cross-validation as follows:
  MCK2(h=5): c=64.0, g=1.0, p=0.0625, mean squared
error=0.39569.

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 7.492
Obj_00002 7.729
Obj_00003 8.088
Obj_00004 7.831
Obj_00005 7.723
Obj_00006 7.844
Obj_00007 7.869
Obj_00008 8.079
Obj_00009 7.145
Obj_00010 7.145
Obj_00011 8.331
Obj_00012 7.145
Obj_00013 7.247
Obj_00014 7.492
Obj_00015 8.092
Obj_00016 7.723
Obj_00017 8.220
Obj_00018 7.144
Obj_00019 6.750
Obj_00020 7.247
Obj_00021 6.746
Obj_00022 7.491
Obj_00023 7.696
Obj_00024 6.747
Obj_00025 7.260
Obj_00026 8.111
Obj_00027 7.247
Obj_00028 8.079
Obj_00029 7.869
Obj_00030 8.169
Obj_00031 6.747
Obj_00032 7.723
Obj_00033 7.252
Obj_00034 7.247
Obj_00035 7.145
Obj_00036 7.669
Obj_00037 8.170
Obj_00038 7.191
Obj_00039 8.079
Obj_00040 7.145
Obj_00041 7.145
Obj_00042 7.492
Obj_00043 8.171
Obj_00044 7.692
Obj_00045 6.747
Obj_00046 7.869
Obj_00047 6.966
Obj_00048 7.700
Obj_00049 7.871
Obj_00050 7.145
Obj_00051 7.869
Obj_00052 7.548
Obj_00053 7.145
Obj_00054 7.886
Obj_00055 7.492
Obj_00056 6.747
Obj_00057 8.079
Obj_00058 6.966
Obj_00059 7.247
Obj_00060 8.089
Obj_00061 7.525
Obj_00062 7.869
Obj_00063 7.869
Obj_00064 8.083
Obj_00065 7.152
Obj_00066 7.702
Obj_00067 7.700
Obj_00068 6.602
Obj_00069 6.918
Obj_00070 7.247
Obj_00071 8.180
Obj_00072 7.247
Obj_00073 8.171
Obj_00074 8.080
Obj_00075 8.287
Obj_00076 7.145