Gene selection in time-series gene expression data

QC 20140909
The dimensionality of biological data is often very high. Feature selection can be used to tackle the problem of high dimensionality. However, majority of the work in feature selection consists of supervised feature selection methods which require class labels. The problem further escalates when the data is time-series gene expression measurements that measure the effect of external stimuli on biological system. In this paper we propose an unsupervised method for gene selection from time-series gene expression data founded on statistical significance testing and swap randomization. We perform experiments with a publicly available mouse gene expression dataset and also a human gene expression dataset describing the exposure to asbestos. The results in both datasets show a considerable decrease in number of genes.

NATURVETENSKAP Biologi Bioinformatik och systembiologi hsv//swe
NATURAL SCIENCES Biological Sciences Bioinformatics and Systems Biology hsv//eng
Feature Selection
Randomization
Statistical Significance
Time-series
Biological data
Class labels
Data sets
Expression measurements
External stimulus
Feature selection methods
Gene selection
High dimensionality
Time-series gene expression data
Unsupervised method
Bioinformatics
Feature extraction
Mammals
Gene expression

Ingår i:6th IAPR International Conference on Pattern Recognition in Bioinformatics, PRIB 2011Berlin, Heidelberg : Springer Berlin Heidelberg, s. 145-1569783642248542

Av författaren/redakt...: Adhikari, P. R.; Upadhyaya, B. B.; Meng, Chen; Hollmén, J.

Om ämnet

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.