|
Abstract
|
|
|---|---|
| In this work we describe a new segmentation technique for the Affymetrix microarray images. We prove that our method can offer better predictions on the gene levels as opposed to the standard Affymetrix segmentation implemented in the Affymetrix GeneChip Operating Software (GCOS). To check the accuracy and show the benefits of the new segmentation method we use a previously implemented methodology to simulate microarray images with realistic features. Using such an "artificial" image provides us with the actual levels for each spot and each gene investigated in the microarray. Using this information we then proceed to segment the same image twice (with GCOS and our new method). The two segmentations will produce two sets of gene levels that are then compared to the known gene levels (known since the moment of generating the "artificial" image). Using this methodology we are able to show statistically (using 50 replicates of the same steps of generating the image, segmenting, comparing the results) that in some cases our new method greatly outperforms the GCOS implemented segmentation method, while in the rest of the cases performs in similar fashion. | |
|
International
|
Si |
|
JCR
|
No |
|
Title
|
Theoretical Computer Science |
|
ISBN
|
0304-3975 |
|
Impact factor JCR
|
|
|
Impact info
|
|
|
Volume
|
|
|
|
|
|
Journal number
|
|
|
From page
|
108 |
|
To page
|
118 |
|
Month
|
SIN MES |
|
Ranking
|
|