Random walk biclustering for microarray data

A biclustering algorithm, based on a greedy technique and enriched with a local search strategy to escape poor local minima, is proposed. The algorithm starts with an initial random solution and searches for a locally optimal solution by successive transformations that improve a gain function. The gain function combines the mean squared residue, the row variance, and the size of the bicluster. Different strategies to escape local minima are introduced and compared. Experimental results on several microarray data sets show that the method is able to find significant biclusters, also from a biological point of view.     

A novel ensemble of classifiers for microarray data classification

Micorarray data are often extremely asymmetric in dimensionality, such as thousands or even tens of thousands of genes and a few hundreds of samples. Such extreme asymmetry between the dimensionality of genes and samples presents several challenges to conventional clustering and classification methods. In this paper, a novel ensemble method is proposed. Firstly, in order to extract useful features and reduce dimensionality, different feature selection methods such as correlation analysis, Fisher-ratio is used to form different feature subsets. Then a pool of candidate base classifiers is generated to learn the subsets which are re-sampling from the different feature subsets with PSO (Particle Swarm Optimization) algorithm. At last, appropriate classifiers are selected to construct the classification committee using EDAs (Estimation of Distribution Algorithms). Experiments show that the proposed method produces the best recognition rates on four benchmark databases.     

CoBi: Pattern Based Co-Regulated Biclustering of Gene Expression Data

Co-regulation is a common phenomenon in gene expression. Finding positively and negatively co-regulated gene clusters from gene expression data is a real need. Existing techniques based on global similarity are unable to detect true up- and down-regulated gene clusters. This paper presents an expression pattern based biclustering technique, CoBi, for grouping both positively and negatively regulated genes from microarray expression data. Regulation pattern and similarity in degree of fluctuation are accounted for while computing similarity between two genes. Unlike traditional biclustering techniques, which use greedy iterative approaches, it uses a BiClust tree that needs single pass over the entire dataset to find a set of biologically relevant biclusters. Biclusters determined from different gene expression datasets by the technique show highly enriched functional categories.     

A probabilistic theory of clustering

Data clustering is typically considered a subjective process, which makes it problematic. For instance, how does one make statistical inferences based on clustering? The matter is different with pattern classification, for which two fundamental characteristics can be stated: (1) the error of a classifier can be estimated using “test data,” and (2) a classifier can be learned using “training data.” This paper presents a probabilistic theory of clustering, including both learning (training) and error estimation (testing). The theory is based on operators on random labeled point processes. It includes an error criterion in the context of random point sets and representation of the Bayes (optimal) cluster operator for a given random labeled point process. Training is illustrated using a nearest-neighbor approach, and trained cluster operators are compared to several classical clustering algorithms.     

生物信息学中基因芯片的特征选择技术综述

随着生物信息学这门新兴学科的兴起，基因芯片技术的研究已经受到越来越多研究者的重视。目前，人们对疾病的分类和诊断的水平已经有了进一步的提高．基于基因芯片的特征选择技术在其中起到了关键性的作用。本文主要对当前基于基因芯片的特征选择技术的研究现状和各种技术方法等进行了综述，并分别从特征基因的选择数、时间复杂度和分类正确率等方面对各个方法进行了分析比较，展望了特征选择技术在基因芯片研究中的未来研究方向。     

Genetic operators for combinatorial optimization in TSP and microarray gene ordering

This paper deals with some new operators of genetic algorithms and demonstrates their effectiveness to the traveling salesman problem (TSP) and microarray gene ordering. The new operators developed are nearest fragment operator based on the concept of nearest neighbor heuristic, and a modified version of order crossover operator. While these result in faster convergence of Genetic Algorithm (GAs) in finding the optimal order of genes in microarray and cities in TSP, the nearest fragment operator can augment the search space quickly and thus obtain much better results compared to other heuristics. Appropriate number of fragments for the nearest fragment operator and appropriate substring length in terms of the number of cities/genes for the modified order crossover operator are determined systematically. Gene order provided by the proposed method is seen to be superior to other related methods based on GAs, neural networks and clustering in terms of biological scores computed using categorization of the genes. Shubhra Sankar Ray is a Visiting Research Fellow at the Center for Soft Computing Research: A National Facility, Indian Statistical Institute, Kolkata, India. He received the M.Sc. in Electronic Science and M.Tech in Radiophysics & Electronics from University of Calcutta, Kolkata, India, in 2000 and 2002, respectively. Till March 2006, he had been a Senior Research Fellow of the Council of Scientific and Industrial Research (CSIR), New Delhi, India, working at Machine Intelligence Unit, Indian Statistical Institute, India. His research interests include bioinformatics, evolutionary computation, neural networks, and data mining. Sanghamitra Bandyopadhyay is an Associate Professor at Indian Statistical Institute, Calcutta, India. She did her Bachelors in Physics and Computer Science in 1988 and 1992 respectively. Subsequently, she did her Masters in Computer Science from Indian Institute of Technology (IIT), Kharagpur in 1994 and Ph.D in Computer Science from Indian Statistical Institute, Calcutta in 1998. She has worked in Los Alamos National Laboratory, Los Alamos, USA, in 1997, as a graduate research assistant, in the University of New South Wales, Sydney, Australia, in 1999, as a post doctoral fellow, in the Department of Computer Science and Engineering, University of Texas at Arlington, USA, in 2001 as a faculty and researcher, and in the Department of Computer Science and Engineering, University of Maryland Baltimore County, USA, in 2004 as a visiting research faculty. Dr. Bandyopadhyay is the first recipient of Dr. Shanker Dayal Sharma Gold Medal and Institute Silver Medal for being adjudged the best all round post graduate performer in IIT, Kharagpur in 1994. She has received the Indian National Science Academy (INSA) and the Indian Science Congress Association (ISCA) Young Scientist Awards in 2000, as well as the Indian National Academy of Engineering (INAE) Young Engineers' Award in 2002. She has published over ninety articles in international journals, conference and workshop proceedings, edited books and journal special issues and served as the Program Co-Chair of the 1st International Conference on Pattern Recognition and Machine Intelligence, 2005, Kolkata, India, and as the Tutorial Co-Chair, World Congress on Lateral Computing, 2004, Bangalore, India. She is on the editorial board of the International Journal on Computational Intelligence. Her research interests include Evolutionary and Soft Computation, Pattern Recognition, Data Mining, Bioinformatics, Parallel & Distributed Systems and VLSI. Sankar K. Pal (www.isical.ac.in/∼sankar) is the Director and Distinguished Scientist of the Indian Statistical Institute. He has founded the Machine Intelligence Unit, and the Center for Soft Computing Research: A National Facility in the Institute in Calcutta. He received a Ph.D. in Radio Physics and Electronics from the University of Calcutta in 1979, and another Ph.D. in Electrical Engineering along with DIC from Imperial College, University of London in 1982. He worked at the University of California, Berkeley and the University of Maryland, College Park in 1986-87; the NASA Johnson Space Center, Houston, Texas in 1990-92 & 1994; and in US Naval Research Laboratory, Washington DC in 2004. Since 1997 he has been serving as a Distinguished Visitor of IEEE Computer Society (USA) for the Asia-Pacific Region, and held seve ral visiting positions in Hong Kong and Australian universities. Prof. Pal is a Fellow of the IEEE, USA, Third World Academy of Sciences, Italy, International Association for Pattern recognition, USA, and all the four National Academies for Science/Engineering in India. He is a co-author of thirteen books and about three hundred research publications in the areas of Pattern Recognition and Machine Learning, Image Processing, Data Mining and Web Intelligence, Soft Computing, Neural Nets, Genetic Algorithms, Fuzzy Sets, Rough Sets, and Bioinformatics. He has received the 1990 S.S. Bhatnagar Prize (which is the most coveted award for a scientist in India), and many prestigious awards in India and abroad including the 1999 G.D. Birla Award, 1998 Om Bhasin Award, 1993 Jawaharlal Nehru Fellowship, 2000 Khwarizmi International Award from the Islamic Republic of Iran, 2000–2001 FICCI Award, 1993 Vikram Sarabhai Research Award, 1993 NASA Tech Brief Award (USA), 1994 IEEE Trans. Neural Networks Outstanding Paper Award (USA), 1995 NASA Patent Application Award (USA), 1997 IETE-R.L. Wadhwa Gold Medal, the 2001 INSA-S.H. Zaheer Medal, and 2005-06 P.C. Mahalanobis Birth Centenary Award (Gold Medal) for Lifetime Achievement . Prof. Pal is an Associate Editor of IEEE Trans. Pattern Analysis and Machine Intelligence, IEEE Trans. Neural Networks [1994–98, 2003–06], Pattern Recognition Letters, Neurocomputing (1995–2005), Applied Intelligence, Information Sciences, Fuzzy Sets and Systems, Fundamenta Informaticae, Int. J. Computational Intelligence and Applications, and Proc. INSA-A; a Member, Executive Advisory Editorial Board, IEEE Trans. Fuzzy Systems, Int. Journal on Image and Graphics, and Int. Journal of Approximate Reasoning; and a Guest Editor of IEEE Computer.     

Automated module for hybridization and staining of commercially produced nucleic acid microarrays

Nucleic acid microarrays are a rapidly expanding technology that enables the detection of pathogens at the genetic level. Currently, the processing of commercially produced microarrays requires cumbersome, expensive, and time-consuming benchtop equipment, which is not practical for point-of-care diagnostic applications. We demonstrate a portable module that can perform the hybridization, wash, and stain steps required for processing a nucleic acid microarray; and it performs these steps in a timeline significantly shorter than the standard commercial protocol. This device is automated, has a small footprint, and serves as a replacement for two commercial pieces of benchtop equipment. Furthermore, our device is designed to serve as a module in a portable biosensor that performs automated sample preparation and nucleic acid amplification. Results with Affymetrix GeneChips show that our device performs as well as non-portable equipment specifically manufactured to process these microarrays. J.S. Erickson and J.E. Hu contributed equally to this work.     

Species identification in food products using the bioMerieux FoodExpert-ID<Superscript>®</Superscript> system

Animal feeds and meat mixtures were analysed using the bioMerieux FoodExpert-ID^® system. The system utilises a reverse dot technique on a DNA microarray to allow the identification of over 30 species of fish, birds and mammals. DNA is amplified by PCR (polymerase chain reaction) then hybridised to the microarray chip. Using this technique, turkey and chicken were correctly identified in 100% of feed samples that contained these species above a level of 0.1%. Pig, lamb and cow could not be reliably detected below a level of 1% in feed samples. For meat mixtures, a level of 0.2% pork or chicken could be correctly identified when mixed with 50% beef or pork, respectively. When a baked or canned meat mixture was investigated, a level of 5% pork, beef or chicken could be correctly identified, following either process. The bioMerieux FoodExpert-ID^® system can therefore be used as a general screen to identify likely species present in a sample, the level of which can be confirmed using other methods.     

Microarray screening of differentially expressed genes in DCX transfected U87 cells before and after irradiation

Radiation therapy plays a critical role in the treatment of neurogliocytoma and it is known that doublecortin (DCX)-transfected U87 cells can inhibit tumor cell growth. Microarray analysis to screen for differentially expressed genes in DCX-transfected U87 cells before and after radiation uncovered DCX-related genes, the functions of DCX, and downstream genes in radiation therapy of neurogliocytoma. Stably transfected U87 cells were constructed (DCX-U87) and the differentially expressed genes were screened by microarray analysis to compare U87 cells with DCX-U87 cells in both non-irradiated and irradiated conditions. Cells were irradiated using 60Co γ-ray at a dose rate of 1.0 Gy/min. Mean values were subject to paired comparison analysis and genes with a p-value of less than 0.05 were analyzed. Differentially expressed genes can correlate with radiation sensitivity and DCX transfection. DCX and SPN proteins in DCX-U87 cells were detected by two groups of 0 and 10 Gy, but not the U87 cells, and their expression levels were higher in the 10 Gy group than in the 0 Gy group. The differential gene expression in DCX-U87 cells before and after radiation is helpful for future investigations into the mechanisms of radiation therapy in neurogliocytoma cells.