Loading...

A Semi-Supervised Algorithms for Clustering Microarray Data

Eslamzadeh, Habibollah | 2009

483 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 40317 (02)
  4. University: Sharif University of Technology
  5. Department: Mathematical Sciences
  6. Advisor(s): Mahdavi Amiri, Nezamoddin; Madadkar Sobhani, Armin
  7. Abstract:
  8. Microarray which is also known as Biochip is a flat substrate of glass with the size of 1 ×1 cm on which a numerous number of biosensors are placed in an array format. Microarray DNAs are used to measure expression level of thousands of genes. Repeating these experiments in different conditions can result in patterns of expression. After preparation, the florescent sample is hybridized with the sensors of microarray surface and fluoresce intensities of the spots are measured by a special camera called CCD. The obtained pictures are examined by a computer and the spot lights converted into numerical data by image processing algorithms. Putting these numbers into matrices of size m×n is logical because the location of spots on the chip is already determined. Expression patterns of genes have a very close relationship to the gene functions, and microarray gives us worthy information about human disease, ageing, drug activities and hormones, mental disease, diets and many several other clinical subjects. Microarray also is used in finding variations in gene sequences, testing, new areas in genetic screening and disease diagnostics. The last step in microarray analysis is data mining and modeling the raw data. Data mining is a new discipline in computer science that has done a lot in analyzing vast amount of raw data. After converting the data into numerical, and normalization, microarray data is required for interpreting information and knowledge at the hand for genes, proteins, tissues, cells and life. In recent years a lot of attentions have been paid to semi-suppervised clustering algoritms. In this study a new algorithms called counting near components has been proposed and analyzed. Also a little change in correlation coefficient as an standard criteria has been proposed and analyzed. The new algorithm and the new semi correlation coefficient applied on a microarray data set. The resulting clusters compared to the output of standard hierarchical algoritms. This comparison showed our new algurithms has better cohesiveness clusters.
  9. Keywords:
  10. Clustering ; Microarray ; Microarray Data ; Gene Expression Data ; Semi-Supervised Algorithm

 Digital Object List

  • محتواي پايان نامه
  •   view

 Bookmark

No TOC