[Abstract]Microarray data classification is used primarily to predict unseen data using a model built on categorized existing Microarray data. One of the major challenges is that Microarray data contains a large number of genes with a small number of samples. This high dimensionality problem has prevented many existing classification methods from directly dealing with this type of data. Moreover, the small number of samples increases the overfitting problem of Classification, as a result leading to lower accuracy classification performance. Another major challenge is that of the uncertainty of Microarraydata quality. Microarray data contains various levels of noise and quite often high levels of noise, and these data lead to unreliable and low accuracy analysis as well as the high dimensionality problem. Most current classification methods are not robust enough to handle these type of data properly.In our research, accuracy and noise resistance or robustness issues are focused on. Our approach is to design a robust classification method for Microarray data classification.An algorithm, called diversified multiple decision trees (DMDT) is proposed, which makes use of a set of unique trees in the decision committee. The DMDT method has increased the diversity of ensemble committees andtherefore the accuracy performance has been enhanced by avoiding overlapping genes among alternative trees.Some strategies to eliminate noisy data have been looked at. Our method ensures no overlapping genes among alternative trees in an ensemble committee, so a noise gene included in the ensemble committee can affect onetree only; other trees in the committee are not affected at all. This design increases the robustness of Microarray classification in terms of resistance to noise data, and therefore reduces the instability caused by overlapping genes in current ensemble methods.The effectiveness of gene selection methods for improving the performance of Microarray classification methods are also discussed.We conclude that the proposed method DMDT substantially outperforms the other well-known ensemble methods, such as Bagging, Boosting and Random Forests, in terms of accuracy and robustness performance. DMDT is more tolerant to noise than Cascading-and-Sharing trees (CS4), particularywith increasing levels of noise in the data. The results also indicate that some classification methods are insensitive to gene selection while some methodsdepend on particular gene selection methods to improve their performance of classification.

Recently, it has been shown that genetic variation that perturbs the regulation of gene expression is widespread in eukaryotic genomes. Regulatory variation (RV) is expected to be an important driver of phenotypic differences, evolutionary change, and susceptibility to complex genetic diseases. Because trans-acting regulators of gene expression control mRNA levels of multiple genes simultaneously, we hypothesise that RV that affects these components will have a shared-influence upon the expression levels of multiple genes. Since genes are regulated in trans by combinations of basal and tissue specific factors, we further hypothesise that RV in these components may have different effects in each tissue. We used microarrays to identify 755 genes that were affected by RV in at least one of the brain, kidney and liver of two inbred mouse strains, C57BL/6J and DBA/2J. Just 2% were affected in all three tissues, suggesting that the influence of RV is predominantly tissue specific. To study shared-RV, we measured the expression levels of these 755 genes in the same 3 tissues from a panel of recombinant inbred mice, and identified groups of correlated genes that are putatively under the influence of shared trans-acting RV. Using methods that we developed for studying the effects of RV in multiple tissues, we identified 212 genes that are correlated in all three tissues, which include 10 groups of at least 3 genes. We developed a novel method called coherency analysis to show that RV consistently affected the expression levels of these groups of genes in different genetic backgrounds. Strikingly, the relative up- or down-regulation of genes in each group was markedly different in the three tissues of the same mouse, suggesting that the influence of RV itself is not tissue specific as previously expected, but that RV can influence genes with differing outcomes in each tissue. These observations are compatible with RV affecting combinations of basal and tissue specific regulatory factors. This is the first cross-tissue investigation into the influence of shared-RV in multiple tissues, which has important implications in humans, where access to the phenotypically relevant tissue may be necessarily limited.

Microarray data clustering represents a basic exploratory tool to find groups of genes exhibiting similar expression patterns or to detect relevant classes of molecular subtypes. Among a wide range of clustering approaches proposed and applied in the gene expression community to analyze microarray data, mixture model-based clustering has received much attention to its sound statistical framework and its flexibility in data modeling. However, clustering algorithms following the model-based framework suffer from two serious drawbacks. The first drawback is that the performance of these algorithms critically depends on the starting values for their iterative clustering procedures. Additionally, they are not capable of working directly with very high dimensional data sets in the sample clustering problem where the dimension of the data is up to hundreds or thousands. The thesis focuses on the two challenges and includes the following contributions: First, the thesis introduces the statistical model of our proposed normalized Expectation Maximization (EM) algorithm followed by its clustering performance analysis on a number of real microarray data sets. The normalized EM is stable even with random initializations for its EM iterative procedure. The stability of the normalized EM is demonstrated through its performance comparison with other related clustering algorithms. Furthermore, the normalized EM is the first mixture model-based clustering approach to be capable of working directly with very high dimensional microarray data sets in the sample clustering problem, where the number of genes is much larger than the number of samples. This advantage of the normalized EM is illustrated through the comparison with the unnormalized EM (The conventional EM algorithm for Gaussian mixture model-based clustering). Besides, for experimental microarray data sets with the availability of class labels of data points, an interesting property of the convergence speed of the normalized EM with respect to the radius of the hypersphere in its corresponding statistical model is uncovered. Second, to support the performance comparison of different clusterings a new internal index is derived using fundamental concepts from information theory. This index allows the comparison of clustering approaches in which the closeness between data points is evaluated by their cosine similarity. The method for deriving this internal index can be utilized to design other new indexes for comparing clustering approaches which employ a common similarity measure.

Diss. (sammanfattning) Umeå : Univ., 2007. / Härtill 6 uppsatser.

Techn. University, Diss., 2007--Darmstadt.

Zugl.: Freiburg (Breisgau), Univ., Diss., 2006

Tübingen, Univ., Diss., 2004.

Stuttgart, Univ., Diss., 2006.

Stuttgart, Univ., Diss., 2007.

Würzburg, Univ., Diss., 2009. / Zsfassung in dt. Sprache.