Abstract | ||
---|---|---|
In this paper we use a modular neural network to predict the molecular functions of yeast proteins. To solve this class problem, our proposed approach decomposes the originalproblem into a set of solvable 2-class subproblems using class information. Each 2-class problem has a set of positive and negative data. The yeast data is not equally distributedin function classes and hinders the learning of each neural network. We adopt a sampling strategy that generates a set of new class data to the subordinate class in order to balance the positive and negative data set. In data preparation, the biological concept of "guilt-by-interaction" is used for covering possible interaction partners among proteins of known functions. The proposed framework has been tested as a predictive model of yeast protein functions where the data source is stored in a relational database. In the experiments,the proposed system shows an average accuracy of 91:0% in the test set. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1109/BIBE.2003.1188984 | BIBE |
Keywords | Field | DocType |
predictive model,data preparation,class information,subordinate class,data source,distributedin function class,modular neural approach,yeast data,yeast protein,negative data,test set,class problem,new class data,neural network,prediction model,testing,neural networks,relational database,molecular biophysics,relational databases,neural nets,genetics,proteins,computer networks,computer science,predictive models | Data source,Relational database,Computer science,Modular neural network,Yeast,Artificial intelligence,Sampling (statistics),Bioinformatics,Modular design,Artificial neural network,Machine learning,Test set | Conference |
ISBN | Citations | PageRank |
0-7695-1907-5 | 0 | 0.34 |
References | Authors | |
3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Doosung Hwang | 1 | 47 | 4.75 |
Farshad Fotouhi | 2 | 1023 | 122.73 |
Russell L. Finley Jr. | 3 | 57 | 3.06 |
William I. Grosky | 4 | 696 | 223.08 |