_PROBLEM CoEPrA-2006_Classification_001

_GROUP_NAME Bart De Moor

_GROUP_MEMBERS
Olivier Gevaert
Joke Allemeersch
Steven Van Vooren
Leo Tranchevent
Nathalie Pochet
Frizo Janssens
Bart De Moor

_ADDRESS
ESAT-SCD
Katholieke Universiteit Leuven
Kasteelpark Arenberg 10
3001 Leuven
Belgium

_MODELING_PROCEDURE
The data was modeled by using Bayesian networks. First a model is learned
 for each amino acid position separately by selecting features that
 correlate well with the class variable. Then these features are selected,
 normalised and discretised before Bayesian network learning (the selected
 features per amino acid are in a matlab file). Then a Bayesian network
 is trained for every amino acid position. Using junction tree inference
 we then can predict the class variable and combine the different
 predictions using weights (The bayesian networks are gathered in a matlab
 file). By using a cross validation approach both the number of features
 used per amino acid position and the weights for the decision integration
 are learned. The best number of features after 10 randomizations of the
 training data was 50. Moreover each position was given equal weight since
 different weighting schemes did not provide better results (again evaluated
 with 10 randomizations). Since probabilities were emitted we chose a point
 on the Receiver Operating Characteristic Curve (ROC) curve, equal to a
 maximum sum of the sensitivity and specificity.

_PREDICTION
Obj_00001 -1
Obj_00002 -1
Obj_00003 -1
Obj_00004 -1
Obj_00005 +1
Obj_00006 +1
Obj_00007 -1
Obj_00008 -1
Obj_00009 -1
Obj_00010 +1
Obj_00011 +1
Obj_00012 -1
Obj_00013 +1
Obj_00014 +1
Obj_00015 -1
Obj_00016 +1
Obj_00017 -1
Obj_00018 +1
Obj_00019 -1
Obj_00020 -1
Obj_00021 +1
Obj_00022 -1
Obj_00023 -1
Obj_00024 +1
Obj_00025 -1
Obj_00026 +1
Obj_00027 +1
Obj_00028 -1
Obj_00029 +1
Obj_00030 +1
Obj_00031 +1
Obj_00032 +1
Obj_00033 -1
Obj_00034 -1
Obj_00035 +1
Obj_00036 -1
Obj_00037 -1
Obj_00038 -1
Obj_00039 -1
Obj_00040 +1
Obj_00041 -1
Obj_00042 -1
Obj_00043 -1
Obj_00044 -1
Obj_00045 +1
Obj_00046 -1
Obj_00047 +1
Obj_00048 +1
Obj_00049 +1
Obj_00050 -1
Obj_00051 +1
Obj_00052 -1
Obj_00053 -1
Obj_00054 +1
Obj_00055 +1
Obj_00056 +1
Obj_00057 +1
Obj_00058 -1
Obj_00059 -1
Obj_00060 -1
Obj_00061 -1
Obj_00062 +1
Obj_00063 +1
Obj_00064 -1
Obj_00065 +1
Obj_00066 -1
Obj_00067 +1
Obj_00068 -1
Obj_00069 +1
Obj_00070 -1
Obj_00071 -1
Obj_00072 -1
Obj_00073 -1
Obj_00074 -1
Obj_00075 -1
Obj_00076 -1
Obj_00077 -1
Obj_00078 +1
Obj_00079 -1
Obj_00080 +1
Obj_00081 +1
Obj_00082 -1
Obj_00083 -1
Obj_00084 +1
Obj_00085 -1
Obj_00086 -1
Obj_00087 -1
Obj_00088 +1