TY - GEN
T1 - Accurate quantification of gene expression using fuzzy clustering approaches
AU - Wang, Yu Ping
AU - Gunampally, Maheswar
AU - Chen, Jie
AU - Bittet, Douglas
AU - Butler, Merlin G.
AU - Cai, Wei Wen
PY - 2007
Y1 - 2007
N2 - Despite the widespread application of microarray imaging for biomedical research, barriers still exist regarding its reliability and reproducibility for clinical use. A critical problem lies in accurate spot segmentation and quantification of gene expression level (mRNA) from microarray images. A variety of commercial and research freeware packages are available, but most cannot handle array spots with complex shapes suck as donuts and scratches. Clustering approaches suck as k-means and mixture models were introduced to overcome this difficulty, which used the hard labeling of each pixel. In this paper, we introduce a more sophisticated fuzzy clustering based method. We show that possiblistic c-means clustering performed the best among several fuzzy clustering approaches. In addition, we compared three statistical criteria in measuring gene expression levels and show that a new unbiased statistic is able to quantify the gene expression level more accurately. The proposed algorithms have been tested on a variety of simulated and real microarray images, demonstrating their better performance.
AB - Despite the widespread application of microarray imaging for biomedical research, barriers still exist regarding its reliability and reproducibility for clinical use. A critical problem lies in accurate spot segmentation and quantification of gene expression level (mRNA) from microarray images. A variety of commercial and research freeware packages are available, but most cannot handle array spots with complex shapes suck as donuts and scratches. Clustering approaches suck as k-means and mixture models were introduced to overcome this difficulty, which used the hard labeling of each pixel. In this paper, we introduce a more sophisticated fuzzy clustering based method. We show that possiblistic c-means clustering performed the best among several fuzzy clustering approaches. In addition, we compared three statistical criteria in measuring gene expression levels and show that a new unbiased statistic is able to quantify the gene expression level more accurately. The proposed algorithms have been tested on a variety of simulated and real microarray images, demonstrating their better performance.
UR - http://www.scopus.com/inward/record.url?scp=47049120467&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=47049120467&partnerID=8YFLogxK
U2 - 10.1109/GENSIPS.2007.4365833
DO - 10.1109/GENSIPS.2007.4365833
M3 - Conference contribution
AN - SCOPUS:47049120467
SN - 1424409993
SN - 9781424409990
T3 - GENSIPS'07 - 5th IEEE International Workshop on Genomic Signal Processing and Statistics
BT - 5th IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS'07
T2 - 5th IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS'07
Y2 - 10 June 2007 through 12 June 2007
ER -