_PROBLEM CoEPrA-2006_Regression_001

_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=0.125, mean squared
error=0.7125.  

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 5.414
Obj_00002 6.273
Obj_00003 4.428
Obj_00004 5.495
Obj_00005 7.590
Obj_00006 5.123
Obj_00007 4.665
Obj_00008 4.271
Obj_00009 5.699
Obj_00010 4.622
Obj_00011 5.950
Obj_00012 4.905
Obj_00013 5.101
Obj_00014 4.383
Obj_00015 6.288
Obj_00016 5.456
Obj_00017 4.767
Obj_00018 5.716
Obj_00019 4.575
Obj_00020 5.109
Obj_00021 5.025
Obj_00022 5.698
Obj_00023 4.552
Obj_00024 4.736
Obj_00025 4.656
Obj_00026 7.066
Obj_00027 6.319
Obj_00028 5.486
Obj_00029 5.377
Obj_00030 4.582
Obj_00031 5.807
Obj_00032 5.790
Obj_00033 5.330
Obj_00034 5.776
Obj_00035 5.109
Obj_00036 5.698
Obj_00037 4.477
Obj_00038 5.170
Obj_00039 5.566
Obj_00040 4.540
Obj_00041 5.701
Obj_00042 4.797
Obj_00043 6.292
Obj_00044 4.495
Obj_00045 5.700
Obj_00046 5.819
Obj_00047 4.667
Obj_00048 4.960
Obj_00049 4.913
Obj_00050 6.203
Obj_00051 6.222
Obj_00052 5.425
Obj_00053 4.328
Obj_00054 4.659
Obj_00055 4.801
Obj_00056 5.860
Obj_00057 5.369
Obj_00058 4.713
Obj_00059 7.595
Obj_00060 4.423
Obj_00061 5.025
Obj_00062 5.315
Obj_00063 5.701
Obj_00064 3.901
Obj_00065 5.071
Obj_00066 5.094
Obj_00067 6.417
Obj_00068 4.495
Obj_00069 6.203
Obj_00070 4.673
Obj_00071 5.104
Obj_00072 4.936
Obj_00073 4.830
Obj_00074 5.571
Obj_00075 5.915
Obj_00076 4.512
Obj_00077 6.324
Obj_00078 5.956
Obj_00079 4.969
Obj_00080 6.053
Obj_00081 5.342
Obj_00082 6.343
Obj_00083 4.976
Obj_00084 5.031
Obj_00085 6.758
Obj_00086 5.680
Obj_00087 5.698
Obj_00088 5.700