Abstract
In microarray processing, the appearance of artifacts, donuts, and irregularly shaped spots is a problem. In current microarray analysis, most approaches stress the segmentation of pixel intensities rather than emphasizing ratio estimators. To avoid segmenting spot target areas and to minimize sensitivity to aberrant pixels, we propose a robust ratio estimator of gene expression via inverse-variance weighting. Moreover, a metric is proposed to evaluate the spot quality. Both the simulation and numerical examples explored reveal that the proposed algorithm is superior to existing approaches with respect to mean square error. The acceptance quality measure recommended confirms the validity of the proposed ratio estimator. Crown
Original language | English |
---|---|
Pages (from-to) | 1577-1589 |
Number of pages | 13 |
Journal | Computational Statistics and Data Analysis |
Volume | 53 |
Issue number | 5 |
DOIs | |
Publication status | Published - 2009 Mar 15 |
All Science Journal Classification (ASJC) codes
- Statistics and Probability
- Computational Mathematics
- Computational Theory and Mathematics
- Applied Mathematics