Evolutionary Biclustering with Correlation for Gene Interaction Networks.
ABSTRACT In this study, a novel rank correlation-based multiobjective evolutionary biclustering method is proposed to extract simple
gene interaction networks from microarray data. Preprocessing helps to preserve those gene interaction pairs which are strongly
correlated. Experimental results on time series gene expression data from Yeast are biologically validated based on standard
databases and information from literature.
- SourceAvailable from: sjtu.edu.cn
Conference Proceeding: A time-series biclustering algorithm for revealing co-regulated genes[show abstract] [hide abstract]
ABSTRACT: Although existing bicluster algorithms claimed to be able to discover co-regulated genes under a subset of given experiment conditions, they ignore the inherent sequential relationship between crucial time points and thus are not applicable to analyze time-series gene expression data. A simple and effective deletion-based algorithm, using the mean squared residue score as a measure, was developed to bicluster time-series gene expression data. While enforcing a threshold value for the score, the algorithm alternately eliminates genes and time points according to their correlation to the bicluster. To ensure the time locality, only the starting and ending points in the time interval are eligible for deletion. As a result, the number of genes and the length of time interval are simultaneously maximized. Our experimental results shown that the proposed method is capable of identifying co-regulated genes characterized by partial time-course data that previous methods failed to discover.Information Technology: Coding and Computing, 2005. ITCC 2005. International Conference on; 05/2005
- [show abstract] [hide abstract]
ABSTRACT: Defining regulatory networks, linking transcription factors (TFs) to their targets, is a central problem in post-genomic biology. One might imagine one could readily determine these networks through inspection of gene expression data. However, the relationship between the expression timecourse of a transcription factor and its target is not obvious (e.g. simple correlation over the timecourse), and current analysis methods, such as hierarchical clustering, have not been very successful in deciphering them. Here we introduce an approach based on support vector machines (SVMs) to predict the targets of a transcription factor by identifying subtle relationships between their expression profiles. In particular, we used SVMs to predict the regulatory targets for 36 transcription factors in the Saccharomyces cerevisiae genome based on the microarray expression data from many different physiological conditions. We trained and tested our SVM on a data set constructed to include a significant number of both positive and negative examples, directly addressing data imbalance issues. This was non-trivial given that most of the known experimental information is only for positives. Overall, we found that 63% of our TF-target relationships were confirmed through cross-validation. We further assessed the performance of our regulatory network identifications by comparing them with the results from two recent genome-wide ChIP-chip experiments. Overall, we find the agreement between our results and these experiments is comparable to the agreement (albeit low) between the two experiments. We find that this network has a delocalized structure with respect to chromosomal positioning, with a given transcription factor having targets spread fairly uniformly across the genome. The overall network of the relationships is available on the web at http://bioinfo.mbb.yale.edu/expression/echipchipBioinformatics 11/2003; 19(15):1917-26. · 5.32 Impact Factor
- [show abstract] [hide abstract]
ABSTRACT: Progression through the eukaryotic cell cycle is known to be both regulated and accompanied by periodic fluctuation in the expression levels of numerous genes. We report here the genome-wide characterization of mRNA transcript levels during the cell cycle of the budding yeast S. cerevisiae. Cell cycle-dependent periodicity was found for 416 of the 6220 monitored transcripts. More than 25% of the 416 genes were found directly adjacent to other genes in the genome that displayed induction in the same cell cycle phase, suggesting a mechanism for local chromosomal organization in global mRNA regulation. More than 60% of the characterized genes that displayed mRNA fluctuation have already been implicated in cell cycle period-specific biological roles. Because more than 20% of human proteins display significant homology to yeast proteins, these results also link a range of human genes to cell cycle period-specific biological functions.Molecular Cell 08/1998; 2(1):65-73. · 15.28 Impact Factor