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 0.721 (leave-one-out). Best cutoff for this model is 0.142. See ModelDescription.html for more detailed information about this model.
|
Test set validation: ROC score = 0.767065390749602 Model Rating: Accuracy 0.767: Fair Confusion Matrix: True Positives = 76, False Negatives = 34, False Positives = 36, True Negatives = 78
|
|
5-Fold Cross-Validation Result |
Model Name |
ROC Score |
ROC Rating |
True Positive |
False Negative |
False Positive |
True Negative |
Sensitivity |
Specificity |
Concordance |
BayesianTempModel-10 |
0.702 |
Fair |
394 |
45 |
52 |
402 |
0.897 |
0.885 |
0.891 |
|
|
|
Validation Result Using External Test Set testset-3.sd |
Model Name |
ROC Score |
ROC Rating |
True Positive |
False Negative |
False Positive |
True Negative |
Sensitivity |
Specificity |
Concordance |
BayesianTempModel-10 |
0.767 |
Fair |
76 |
34 |
36 |
78 |
0.691 |
0.684 |
0.688 |
|
|
|
|
|
|
Results
|
|
|
Parameters
|
|
|
|
|
 
|
Property for Active
|
class
|
|
 
|
Model Name
|
BayesianTempModel-10
|
|
|
Independent Properties
|
ALogP,ECFP_14,Apol,Molecular_Weight,Num_H_Donors,Wiener
|
|
Calculable Properties
|
ALogP,ECFP_14,Apol,Molecular_Weight,Num_H_Donors,Wiener
|
User Properties
|
|
|
|
|
|
Learn Options
|
Validate Models
|
Remove Uninformative Bins
|
Equipopulate Bins
|
|
|
Model Domain Fingerprint
|
FCFP_2
|
Additional Properties
|
|
|
|
|
|
© 2021 Accelrys Software Inc.
|