Mining subspace clusters from DNA microarray data using large itemset techniques. Export

@article{citeulike:6095488, abstract = {Mining subspace clusters from the DNA microarrays could help researchers identify those genes which commonly contribute to a disease, where a subspace cluster indicates a subset of genes whose expression levels are similar under a subset of conditions. Since in a DNA microarray, the number of genes is far larger than the number of conditions, those previous proposed algorithms which compute the maximum dimension sets (MDSs) for any two genes will take a long time to mine subspace clusters. In this article, we propose the Large Itemset-Based Clustering (LISC) algorithm for mining subspace clusters. Instead of constructing MDSs for any two genes, we construct only MDSs for any two conditions. Then, we transform the task of finding the maximal possible gene sets into the problem of mining large itemsets from the condition-pair MDSs. Since we are only interested in those subspace clusters with gene sets as large as possible, it is desirable to pay attention to those gene sets which have reasonable large support values in the condition-pair MDSs. From our simulation results, we show that the proposed algorithm needs shorter processing time than those previous proposed algorithms which need to construct gene-pair MDSs.}, author = {Chang, Ye-In I. and Chen, Jiun-Rung R. and Tsai, Yueh-Chi C.}, citeulike-article-id = {6095488}, citeulike-linkout-0 = {http://dx.doi.org/10.1089/cmb.2008.0161}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/19432542}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=19432542}, doi = {10.1089/cmb.2008.0161}, issn = {1557-8666}, journal = {Journal of computational biology : a journal of computational molecular cell biology}, keywords = {clustering, microarray\_analysis}, month = {May}, number = {5}, pages = {745--768}, posted-at = {2009-11-10 17:38:09}, priority = {1}, title = {Mining subspace clusters from DNA microarray data using large itemset techniques.}, url = {http://dx.doi.org/10.1089/cmb.2008.0161}, volume = {16}, year = {2009} }

TY - JOUR ID - citeulike:6095488 L3 - citeulike-article-id:6095488 N2 - Mining subspace clusters from the DNA microarrays could help researchers identify those genes which commonly contribute to a disease, where a subspace cluster indicates a subset of genes whose expression levels are similar under a subset of conditions. Since in a DNA microarray, the number of genes is far larger than the number of conditions, those previous proposed algorithms which compute the maximum dimension sets (MDSs) for any two genes will take a long time to mine subspace clusters. In this article, we propose the Large Itemset-Based Clustering (LISC) algorithm for mining subspace clusters. Instead of constructing MDSs for any two genes, we construct only MDSs for any two conditions. Then, we transform the task of finding the maximal possible gene sets into the problem of mining large itemsets from the condition-pair MDSs. Since we are only interested in those subspace clusters with gene sets as large as possible, it is desirable to pay attention to those gene sets which have reasonable large support values in the condition-pair MDSs. From our simulation results, we show that the proposed algorithm needs shorter processing time than those previous proposed algorithms which need to construct gene-pair MDSs. IS - 5 JF - Journal of computational biology : a journal of computational molecular cell biology SN - 1557-8666 EP - 768 TI - Mining subspace clusters from DNA microarray data using large itemset techniques. VL - 16 SP - 745 KW - clustering KW - microarray_analysis AU - Chang, Ye-In AU - Chen, Jiun-Rung AU - Tsai, Yueh-Chi PY - 2009/05// UR - http://dx.doi.org/10.1089/cmb.2008.0161 ER -