On the use of MDL principle in gene expression prediction (Q5957454)
From MaRDI portal
scientific article; zbMATH DE number 1716925
Language | Label | Description | Also known as |
---|---|---|---|
English | On the use of MDL principle in gene expression prediction |
scientific article; zbMATH DE number 1716925 |
Statements
On the use of MDL principle in gene expression prediction (English)
0 references
25 April 2002
0 references
Summary: The structure and biological behavior of a cell are determined by the pattern of gene expressions within that cell. The so-called gene prediction problem refers to finding rules, or sets of possible rules, on how certain genes expressions determine the expression level of a given target gene. We investigate the gene prediction problem and propose the use of new predictors, selected according to the minimum description length (MDL) principle. We compare the use of Boolean predictors, ternary predictors and perceptron predictors. We resort to MDL as a tool for selecting the proper size of the prediction window. MDL is also well suited for comparing predictors having different complexities. We show that the best description can be achieved by the Boolean and ternary predictors, since they obtain better fitting of the data with a lower complexity of the model. To illustrate the comparison, both synthetic and experimental data are used.
0 references
nonlinear predictors
0 references
gene expressions
0 references
minimum description length
0 references
perceptron predictors
0 references
MDL
0 references
ternary predictors
0 references