Limits...
M3G: maximum margin microarray gridding.

Bariamis D, Iakovidis DK, Maroulis D - BMC Bioinformatics (2010)

Bottom Line: The optimal positioning of the lines is determined by maximizing the margin between these rows and columns by using a maximum margin linear classifier, effectively facilitating the localization of the spots.The results show that M3G outperforms state of the art methods, demonstrating robustness in the presence of noise and artefacts.The proposed method performs highly accurate gridding in the presence of noise and artefacts, while taking into account the input image rotation.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Informatics and Telecommunications, University of Athens, Athens, Greece. d.bariamis@di.uoa.gr

ABSTRACT

Background: Complementary DNA (cDNA) microarrays are a well established technology for studying gene expression. A microarray image is obtained by laser scanning a hybridized cDNA microarray, which consists of thousands of spots representing chains of cDNA sequences, arranged in a two-dimensional array. The separation of the spots into distinct cells is widely known as microarray image gridding.

Methods: In this paper we propose M3G, a novel method for automatic gridding of cDNA microarray images based on the maximization of the margin between the rows and the columns of the spots. Initially the microarray image rotation is estimated and then a pre-processing algorithm is applied for a rough spot detection. In order to diminish the effect of artefacts, only a subset of the detected spots is selected by matching the distribution of the spot sizes to the normal distribution. Then, a set of grid lines is placed on the image in order to separate each pair of consecutive rows and columns of the selected spots. The optimal positioning of the lines is determined by maximizing the margin between these rows and columns by using a maximum margin linear classifier, effectively facilitating the localization of the spots.

Results: The experimental evaluation was based on a reference set of microarray images containing more than two million spots in total. The results show that M3G outperforms state of the art methods, demonstrating robustness in the presence of noise and artefacts. More than 98% of the spots reside completely inside their respective grid cells, whereas the mean distance between the spot center and the grid cell center is 1.2 pixels.

Conclusions: The proposed method performs highly accurate gridding in the presence of noise and artefacts, while taking into account the input image rotation. Thus, it provides the potential of achieving perfect gridding for the vast majority of the spots.

Show MeSH

Related in: MedlinePlus

The distribution of spot diameters in the data set compared to the modified normal distribution Nm (x ; μ, σ) with μ = 8.07 and σ = 1.66.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2823709&req=5

Figure 6: The distribution of spot diameters in the data set compared to the modified normal distribution Nm (x ; μ, σ) with μ = 8.07 and σ = 1.66.

Mentions: Two data sets were used for the evaluation of M3G. The first data set consists of 54 cDNA microarray images from the Stanford Microarray Database [29]. The images are TIFF files with a resolution of 1900 × 5500 pixels and 16-bit grey level depth. Each image includes 48 blocks of 870 spots each, resulting in a total of 2,255,040 spots in the data set. These images have been produced for the study of the gene expression profiles of 54 specimens of BCR-ABL-positive and -negative acute lymphoblastic leukemia [30]. This data set is a superset of the one used by the preliminary version of the proposed method [19] and the genetic algorithm approach proposed in [15]. This data set is accompanied by ground truth annotations regarding the positions and the sizes of the spots. Fig. 6 visually validates the resemblance of the distribution of the sizes of the spots in the data set to the Nm(x; μ, σ) distribution.


M3G: maximum margin microarray gridding.

Bariamis D, Iakovidis DK, Maroulis D - BMC Bioinformatics (2010)

The distribution of spot diameters in the data set compared to the modified normal distribution Nm (x ; μ, σ) with μ = 8.07 and σ = 1.66.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2823709&req=5

Figure 6: The distribution of spot diameters in the data set compared to the modified normal distribution Nm (x ; μ, σ) with μ = 8.07 and σ = 1.66.
Mentions: Two data sets were used for the evaluation of M3G. The first data set consists of 54 cDNA microarray images from the Stanford Microarray Database [29]. The images are TIFF files with a resolution of 1900 × 5500 pixels and 16-bit grey level depth. Each image includes 48 blocks of 870 spots each, resulting in a total of 2,255,040 spots in the data set. These images have been produced for the study of the gene expression profiles of 54 specimens of BCR-ABL-positive and -negative acute lymphoblastic leukemia [30]. This data set is a superset of the one used by the preliminary version of the proposed method [19] and the genetic algorithm approach proposed in [15]. This data set is accompanied by ground truth annotations regarding the positions and the sizes of the spots. Fig. 6 visually validates the resemblance of the distribution of the sizes of the spots in the data set to the Nm(x; μ, σ) distribution.

Bottom Line: The optimal positioning of the lines is determined by maximizing the margin between these rows and columns by using a maximum margin linear classifier, effectively facilitating the localization of the spots.The results show that M3G outperforms state of the art methods, demonstrating robustness in the presence of noise and artefacts.The proposed method performs highly accurate gridding in the presence of noise and artefacts, while taking into account the input image rotation.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Informatics and Telecommunications, University of Athens, Athens, Greece. d.bariamis@di.uoa.gr

ABSTRACT

Background: Complementary DNA (cDNA) microarrays are a well established technology for studying gene expression. A microarray image is obtained by laser scanning a hybridized cDNA microarray, which consists of thousands of spots representing chains of cDNA sequences, arranged in a two-dimensional array. The separation of the spots into distinct cells is widely known as microarray image gridding.

Methods: In this paper we propose M3G, a novel method for automatic gridding of cDNA microarray images based on the maximization of the margin between the rows and the columns of the spots. Initially the microarray image rotation is estimated and then a pre-processing algorithm is applied for a rough spot detection. In order to diminish the effect of artefacts, only a subset of the detected spots is selected by matching the distribution of the spot sizes to the normal distribution. Then, a set of grid lines is placed on the image in order to separate each pair of consecutive rows and columns of the selected spots. The optimal positioning of the lines is determined by maximizing the margin between these rows and columns by using a maximum margin linear classifier, effectively facilitating the localization of the spots.

Results: The experimental evaluation was based on a reference set of microarray images containing more than two million spots in total. The results show that M3G outperforms state of the art methods, demonstrating robustness in the presence of noise and artefacts. More than 98% of the spots reside completely inside their respective grid cells, whereas the mean distance between the spot center and the grid cell center is 1.2 pixels.

Conclusions: The proposed method performs highly accurate gridding in the presence of noise and artefacts, while taking into account the input image rotation. Thus, it provides the potential of achieving perfect gridding for the vast majority of the spots.

Show MeSH
Related in: MedlinePlus