Create Bayesian Model
|
|
Description
|
|
Builds a user model using Bayesian categorization. Uses Bayesian categorization to build a model that distinguishes between "good" and "bad" ligands. "Good" ligands are defined by having a value of "1" for the property set by Property for Active.
A user model is created, named according to Model Name. The model can be used to predict how "good" ligands are using Calculate Molecular Properties.
|
|
Information
|
|
|
Summary
|
|
ROC score is 0.808 (leave-one-out). Best cutoff for this model is 0.189. See ModelDescription.html for more detailed information about this model.
|
Test set validation: ROC score = 0.891666666666667 Model Rating: Accuracy 0.892: Good Confusion Matrix: True Positives = 33, False Negatives = 7, False Positives = 3, True Negatives = 15
|
|
5-Fold Cross-Validation Result |
Model Name |
ROC Score |
ROC Rating |
True Positive |
False Negative |
False Positive |
True Negative |
Sensitivity |
Specificity |
Concordance |
Best-zhh |
0.779 |
Fair |
152 |
9 |
1 |
70 |
0.944 |
0.986 |
0.957 |
|
|
|
Validation Result Using External Test Set TestSet_290-ZHH-(1).sd |
Model Name |
ROC Score |
ROC Rating |
True Positive |
False Negative |
False Positive |
True Negative |
Sensitivity |
Specificity |
Concordance |
Best-zhh |
0.892 |
Good |
33 |
7 |
3 |
15 |
0.825 |
0.833 |
0.828 |
|
|
|
|
|
|
Results
|
|
|
Parameters
|
|
|
|
|
 
|
Property for Active
|
class-1
|
|
 
|
Model Name
|
Best-zhh
|
|
|
Independent Properties
|
ECFP_6,Molecular_Weight,Num_H_Acceptors,Num_H_Donors,Molecular_PolarSASA
|
|
Calculable Properties
|
ECFP_6,Molecular_Weight,Num_H_Acceptors,Num_H_Donors,Molecular_PolarSASA
|
User Properties
|
|
|
|
|
|
Learn Options
|
Validate Models
|
Remove Uninformative Bins
|
Equipopulate Bins
|
|
|
Model Domain Fingerprint
|
FCFP_2
|
Additional Properties
|
|
|
|
|
|
© 2016 Accelrys Software Inc.
|