International Journal of Data Mining and Bioinformatics http://www.inderscience.com/browse/index.php?journalID=189&year=2011&vol=5&issue=5 Inderscience Publishers Ltd en-uk International Journal of Data Mining and Bioinformatics 1748-5673 1748-5681 © 2011 Inderscience Publishers Ltd editor@inderscience.com https://www.inderscience.com/images/files/coverImgs/ijdmb_scoverijdmb.jpg http://www.inderscience.com/browse/index.php?journalID=189&year=2011&vol=5&issue=5 http://www.inderscience.com/link.php?id=43029 Transcribed regions can be determined by aligning Expressed Sequence Tags (ESTs) with genome sequences. The kernel of this strategy is to effectively distinguish true EST alignments from spurious ones. In this study, three measures including Direction Check, Identity Check and Terminal Check were introduced to more effectively eliminate spurious EST alignments. On the basis of these introduced measures and other widely used measures, a computational tool, named ESTCleanser, has been developed to identify true EST alignments for obtaining reliable transcribed regions. The performance of ESTCleanser has been evaluated on the well-annotated human ENCyclopedia of DNA Elements (ENCODE) regions using human ESTs in the dbEST database. The evaluation results show that the accuracy of ESTCleanser at exon and intron levels is more remarkably enhanced than that of UCSC-spliced EST alignments. This work would be helpful to EST-based researches on finding new genes, complementing genome annotation, recognising alternative splicing events and Single Nucleotide Polymorphisms (SNPs), etc. Identification of true EST alignments for recognising transcribed regions
Chuang Ma; Jia Wang; Lun Li; Mo-Jie Duan; Yan-Hong Zhou
International Journal of Data Mining and Bioinformatics, Vol. 5, No. 5 (2011) pp. 465 - 484
Transcribed regions can be determined by aligning Expressed Sequence Tags (ESTs) with genome sequences. The kernel of this strategy is to effectively distinguish true EST alignments from spurious ones. In this study, three measures including Direction Check, Identity Check and Terminal Check were introduced to more effectively eliminate spurious EST alignments. On the basis of these introduced measures and other widely used measures, a computational tool, named ESTCleanser, has been developed to identify true EST alignments for obtaining reliable transcribed regions. The performance of ESTCleanser has been evaluated on the well-annotated human ENCyclopedia of DNA Elements (ENCODE) regions using human ESTs in the dbEST database. The evaluation results show that the accuracy of ESTCleanser at exon and intron levels is more remarkably enhanced than that of UCSC-spliced EST alignments. This work would be helpful to EST-based researches on finding new genes, complementing genome annotation, recognising alternative splicing events and Single Nucleotide Polymorphisms (SNPs), etc.

]]> 10.1504/IJDMB.2011.043029 International Journal of Data Mining and Bioinformatics, Vol. 5, No. 5 (2011) pp. 465 - 484 Chuang Ma; Jia Wang; Lun Li; Mo-Jie Duan; Yan-Hong Zhou Hubei Bioinformatics and Molecular Imaging Key Laboratory, Huazhong University of Science and Technology, Wuhan 430074, China. ' Hubei Bioinformatics and Molecular Imaging Key Laboratory, Huazhong University of Science and Technology, Wuhan 430074, China. ' Hubei Bioinformatics and Molecular Imaging Key Laboratory, Huazhong University of Science and Technology, Wuhan 430074, China. ' Hubei Bioinformatics and Molecular Imaging Key Laboratory, Huazhong University of Science and Technology, Wuhan 430074, China. ' Hubei Bioinformatics and Molecular Imaging Key Laboratory, Huazhong University of Science and Technology, Wuhan 430074, China expressed sequence tag EST alignment genome sequence protein coding genes transcribed regions measure filtering criteria genome annotation alternative splicing computational genomics data mining bioinformatics. 2011-10-12T23:20:50-05:00 5 5 465 484 2011-10-12T23:20:50-05:00 http://www.inderscience.com/link.php?id=43030 Gene-expression data are now widely available and used for a wide range of clinical and diagnostic purposes. A key challenge is to select a few significant marker genes for biological studies. While it is feasible to find important genes from a single gene-expression data set, it is often more meaningful to compare the results from different but related data sets together, especially for multiple gene-expression data sets arising from different studies of a common organism or phenotype. In this paper, we present a novel framework to exploit the commonalities across different data sets by jointly learning from different data sets simultaneously through multi-task feature learning. By identifying a common subspace of genes, we can help biologists find important marker genes that span different evolutionary periods in the life cycle of cancer development. The genes thus found are more stable and more significant. Our experimental results demonstrate that more accurate models can be built using multiple data sets based on fewer labelled examples. To the best of our knowledge, we are among the first to introduce multi-task learning in the bioinformatics community to solve the lack of data problem. Multi-platform gene-expression mining and marker gene analysis
Qian Xu; Hong Xue; Qiang Yang
International Journal of Data Mining and Bioinformatics, Vol. 5, No. 5 (2011) pp. 485 - 503
Gene-expression data are now widely available and used for a wide range of clinical and diagnostic purposes. A key challenge is to select a few significant marker genes for biological studies. While it is feasible to find important genes from a single gene-expression data set, it is often more meaningful to compare the results from different but related data sets together, especially for multiple gene-expression data sets arising from different studies of a common organism or phenotype. In this paper, we present a novel framework to exploit the commonalities across different data sets by jointly learning from different data sets simultaneously through multi-task feature learning. By identifying a common subspace of genes, we can help biologists find important marker genes that span different evolutionary periods in the life cycle of cancer development. The genes thus found are more stable and more significant. Our experimental results demonstrate that more accurate models can be built using multiple data sets based on fewer labelled examples. To the best of our knowledge, we are among the first to introduce multi-task learning in the bioinformatics community to solve the lack of data problem.

]]> 10.1504/IJDMB.2011.043030 International Journal of Data Mining and Bioinformatics, Vol. 5, No. 5 (2011) pp. 485 - 503 Qian Xu; Hong Xue; Qiang Yang Bioengineering Programme, Hong Kong University of Science and Technology, Clearwater Bay, Kowloon, Hong Kong. ' Department of Biochemistry, Hong Kong University of Science and Technology, Clearwater Bay, Kowloon, Hong Kong. ' Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clearwater Bay, Kowloon, Hong Kong data mining bioinformatics gene expression data analysis multi-task learning gene expression mining marker gene analysis feature learning. 2011-10-12T23:20:50-05:00 5 5 485 503 2011-10-12T23:20:50-05:00 http://www.inderscience.com/link.php?id=43032 The objective of this study is to develop an accurate and robust classification ensemble method suitable for microarray data with noises. We proposed an algorithm, pattern match (PM)-bagging, which performs well in accuracy and is robust to noise variables and noise observations. From the experiments with real data set, the performance of the proposed method is found quite comparable and not much degraded even when the data set has noise variables or noise observations, while some other ensemble methods showed degradations of performance. A bias and variance decomposition showed that the success of the proposed method is due to an effective reduction of both bias and variance. Robust classification ensemble method for microarray data
Dongjun Chung; Hyunjoong Kim
International Journal of Data Mining and Bioinformatics, Vol. 5, No. 5 (2011) pp. 504 - 518
The objective of this study is to develop an accurate and robust classification ensemble method suitable for microarray data with noises. We proposed an algorithm, pattern match (PM)-bagging, which performs well in accuracy and is robust to noise variables and noise observations. From the experiments with real data set, the performance of the proposed method is found quite comparable and not much degraded even when the data set has noise variables or noise observations, while some other ensemble methods showed degradations of performance. A bias and variance decomposition showed that the success of the proposed method is due to an effective reduction of both bias and variance.

]]> 10.1504/IJDMB.2011.043032 International Journal of Data Mining and Bioinformatics, Vol. 5, No. 5 (2011) pp. 504 - 518 Dongjun Chung; Hyunjoong Kim Department of Statistics, University of Wisconsin-Madison, WI 53706, USA. ' Department of Applied Statistics, Yonsei University, Seoul 120-749, Korea classification ensemble microarray data robustness data mining bioinformatics decision trees noise variables noise observations. 2011-10-12T23:20:50-05:00 5 5 504 518 2011-10-12T23:20:50-05:00 http://www.inderscience.com/link.php?id=43031 MicroRNAs (miRNAs) are potential biomarkers in the diagnosis of human disease. In this study, a novel concept, the miRNA network biomarker, was proposed for the selection of biomarkers. Each miRNA network biomarker contains miRNA targets, as well as Transcription Factors (TFs), that affect the miRNA expression. The obtained biomarkers were applied to classifying expression data sets in different progression stages from chronic gastritis to gastric cancer. Furthermore, these biomarkers could accurately (94%) discriminate gastric cancer samples from normal samples in another data set. Angiogenesis-related pathways and genes were found to be enriched in these network biomarkers. Computational identification of potential microRNA network biomarkers for the progression stages of gastric cancer
Le Lu; Yanda Li; Shao Li
International Journal of Data Mining and Bioinformatics, Vol. 5, No. 5 (2011) pp. 519 - 531
MicroRNAs (miRNAs) are potential biomarkers in the diagnosis of human disease. In this study, a novel concept, the miRNA network biomarker, was proposed for the selection of biomarkers. Each miRNA network biomarker contains miRNA targets, as well as Transcription Factors (TFs), that affect the miRNA expression. The obtained biomarkers were applied to classifying expression data sets in different progression stages from chronic gastritis to gastric cancer. Furthermore, these biomarkers could accurately (94%) discriminate gastric cancer samples from normal samples in another data set. Angiogenesis-related pathways and genes were found to be enriched in these network biomarkers.

]]> 10.1504/IJDMB.2011.043031 International Journal of Data Mining and Bioinformatics, Vol. 5, No. 5 (2011) pp. 519 - 531 Le Lu; Yanda Li; Shao Li MOE Key Laboratory of Bioinformatics and Bioinformatics Division, TNLIST/Department of Automation, Tsinghua University, Beijing 100084, China. ' MOE Key Laboratory of Bioinformatics and Bioinformatics Division, TNLIST/Department of Automation, Tsinghua University, Beijing 100084, China. ' MOE Key Laboratory of Bioinformatics and Bioinformatics Division, TNLIST/Department of Automation, Tsinghua University, Beijing 100084, China microRNA biomarkers transcription factors TSS transcription start site miRNA targets angiogenesis gastric cancer chronic gastritis TFBS transcription factor binding sites bioinformatics. 2011-10-12T23:20:50-05:00 5 5 519 531 2011-10-12T23:20:50-05:00 http://www.inderscience.com/link.php?id=43034 MentalSquares (MSQs) an equilibrium-based dimensional approach is presented for the classification and diagnostic analysis of psychological conditions with Bipolar Disorders (BPDs) as an example. While a Support Vector Machine (SVM) is defined in Hilbert space. A MSQ can be considered as a generic SVM for improved classification. Different from the traditional categorical model of BPDs, the generic approach focuses on the balance of two poles of mental equilibrium. Preliminary results show that this new approach has a number of advantages over existing models. The generic model is analytically illustrated with public domain clinical examples and well-known empirical clinical knowledge. Its clinical and computerised operability is illustrated. Its potential of being a practical method for the classification and analysis of neurobiological patterns and drug effects is discussed. MentalSquares: A generic bipolar Support Vector Machine for psychiatric disorder classification, diagnostic analysis and neurobiological data mining
Wen-Ran Zhang; Anand K. Pandurangi; Karl E. Peace; Yan-Qing Zhang; Zhongming Zhao
International Journal of Data Mining and Bioinformatics, Vol. 5, No. 5 (2011) pp. 532 - 557
MentalSquares (MSQs) an equilibrium-based dimensional approach is presented for the classification and diagnostic analysis of psychological conditions with Bipolar Disorders (BPDs) as an example. While a Support Vector Machine (SVM) is defined in Hilbert space. A MSQ can be considered as a generic SVM for improved classification. Different from the traditional categorical model of BPDs, the generic approach focuses on the balance of two poles of mental equilibrium. Preliminary results show that this new approach has a number of advantages over existing models. The generic model is analytically illustrated with public domain clinical examples and well-known empirical clinical knowledge. Its clinical and computerised operability is illustrated. Its potential of being a practical method for the classification and analysis of neurobiological patterns and drug effects is discussed.

]]> 10.1504/IJDMB.2011.043034 International Journal of Data Mining and Bioinformatics, Vol. 5, No. 5 (2011) pp. 532 - 557 Wen-Ran Zhang; Anand K. Pandurangi; Karl E. Peace; Yan-Qing Zhang; Zhongming Zhao Computer Science Department, Georgia Southern University, Statesboro, GA 30460, USA. ' Department of Psychiatry, Virginia Commonwealth University, Richmond, VA 23298, USA. ' Jiann-Ping Hsu College of Public Health, Georgia Southern University, Statesboro, GA 30460, USA. ' Computer Science Department, Georgia State University, Atlanta, GA 30302, USA. ' Vanderbilt University Medical Center, Departments of Biomedical Informatics, Psychiatry, and Cancer Biology, Nashville, Tennessee 37232, USA computational neuroscience computational psychiatry dimensional approach unified bipolar disorder classification exploratory neurobiological data mining YinYang bipolar SVMs support vector machines diagnosis. neurobiology psychiatric disorders bioinformatics neurobiological patterns drug effects. 2011-10-12T23:20:50-05:00 5 5 532 557 2011-10-12T23:20:50-05:00 http://www.inderscience.com/link.php?id=43033 The great amount of biological information provides scientists with an incomparable framework for testing the results of new algorithms. Several tools have been developed for analysing gene-enrichment and most of them are Gene Ontology-based tools. We developed a Kyoto Encyclopedia of Genes and Genomes (Kegg)-based tool that provides a friendly graphical environment for analysing gene-enrichment. The tool integrates two statistical corrections and simultaneously analysing the information about many groups of genes in both visual and textual manner. We tested the usefulness of our approach on a previous analysis (Huttenshower et al.). Furthermore, our tool is freely available (http://www.upo.es/eps/bigs/cargene.html). CarGene: Characterisation of sets of genes based on metabolic pathways analysis
Jesus S. Aguilar-Ruiz; Domingo S. Rodriguez-Baena; Norberto Diaz-Diaz; Isabel A. Nepomuceno-Chamorro
International Journal of Data Mining and Bioinformatics, Vol. 5, No. 5 (2011) pp. 558 - 573
The great amount of biological information provides scientists with an incomparable framework for testing the results of new algorithms. Several tools have been developed for analysing gene-enrichment and most of them are Gene Ontology-based tools. We developed a Kyoto Encyclopedia of Genes and Genomes (Kegg)-based tool that provides a friendly graphical environment for analysing gene-enrichment. The tool integrates two statistical corrections and simultaneously analysing the information about many groups of genes in both visual and textual manner. We tested the usefulness of our approach on a previous analysis (Huttenshower et al.). Furthermore, our tool is freely available (http://www.upo.es/eps/bigs/cargene.html).

]]> 10.1504/IJDMB.2011.043033 International Journal of Data Mining and Bioinformatics, Vol. 5, No. 5 (2011) pp. 558 - 573 Jesus S. Aguilar-Ruiz; Domingo S. Rodriguez-Baena; Norberto Diaz-Diaz; Isabel A. Nepomuceno-Chamorro School of Engineering, Pablo de Olavide University, 41013 Seville, Spain. ' School of Engineering, Pablo de Olavide University, 41013 Seville, Spain. ' School of Engineering, Pablo de Olavide University, 41013 Seville, Spain. ' Computer Science Department, University of Seville, 41012 Seville, Spain clustering biclustering Kegg biological validation metabolic pathways gene enrichment bioinformatics Kyoto Encyclopedia of Genes and Genomes. 2011-10-12T23:20:50-05:00 5 5 558 573 2011-10-12T23:20:50-05:00 http://www.inderscience.com/link.php?id=43035 The partial nucleotide sequence of putative Trypanosoma brucei rhodesiense oligosaccharyl transferase gene was previously reported. Here, we describe the determination of its full-length nucleotide sequence by Inverse PCR (IPCR), subsequent biological sequence analysis and transmembrane topology modelling. The full-length DNA sequence has an Open Reading Frame (ORF) of 2406 bp and encodes a polypeptide of 801 amino acid residues. Protein and DNA sequence analyses revealed that homologues within the genome of other kinetoplastid and various origins exist. Protein topology analysis predicted that Trypanosoma brucei rhodesiense putative oligosaccharyl transferase clone II (TbOST II) is a transmembrane protein with transmembrane helices in probably an N(cytosol)-C(cytosol) orientation. Data from the GenBank database assembly and sequence analyses in general clearly state that TbOST II is the STT3 subunit of OST in T.b. rhodesiense that necessitates further characterisation and functional studies with RNAi. TbOST II sequence had been deposited in the GenBank (accession number GU245937). Complete coding sequence, sequence analysis and transmembrane topology modelling of Trypanosoma brucei rhodesiense Putative Oligosaccharyl transferase (TbOST II)
Waren N. Baticados; Noboru Inoue; Chihiro Sugimoto; Hideyuki Nagasawa; Abigail M. Baticados
International Journal of Data Mining and Bioinformatics, Vol. 5, No. 5 (2011) pp. 574 - 592
The partial nucleotide sequence of putative Trypanosoma brucei rhodesiense oligosaccharyl transferase gene was previously reported. Here, we describe the determination of its full-length nucleotide sequence by Inverse PCR (IPCR), subsequent biological sequence analysis and transmembrane topology modelling. The full-length DNA sequence has an Open Reading Frame (ORF) of 2406 bp and encodes a polypeptide of 801 amino acid residues. Protein and DNA sequence analyses revealed that homologues within the genome of other kinetoplastid and various origins exist. Protein topology analysis predicted that Trypanosoma brucei rhodesiense putative oligosaccharyl transferase clone II (TbOST II) is a transmembrane protein with transmembrane helices in probably an N(cytosol)-C(cytosol) orientation. Data from the GenBank database assembly and sequence analyses in general clearly state that TbOST II is the STT3 subunit of OST in T.b. rhodesiense that necessitates further characterisation and functional studies with RNAi. TbOST II sequence had been deposited in the GenBank (accession number GU245937).

]]> 10.1504/IJDMB.2011.043035 International Journal of Data Mining and Bioinformatics, Vol. 5, No. 5 (2011) pp. 574 - 592 Waren N. Baticados; Noboru Inoue; Chihiro Sugimoto; Hideyuki Nagasawa; Abigail M. Baticados Department of Veterinary Paraclinical Sciences, College of Veterinary Medicine, University of the Philippines Los Banos, Laguna 4031, Philippines ' National Research Center for Protozoan Diseases, Obihiro University of Agriculture and Veterinary Medicine, Hokkaido 080-8555, Japan. ' Research Center for Zoonosis Control, Hokkaido University N18-W9, Kita-ku, Sapporo, Hokkaido 060-0818, Japan. ' National Research Center for Protozoan Diseases, Obihiro University of Agriculture and Veterinary Medicine, Hokkaido 080-8555, Japan. ' Department of Veterinary Paraclinical Sciences, College of Veterinary Medicine, University of the Philippines Los Banos, Laguna 4031, Philippines Trypanosoma brucei rhodesiense oligosaccharyl transferase N-glycosylation STT3 subunit inverse PCR coding sequences sequence analysis transmembrane topology modelling DNA sequencing. 2011-10-12T23:20:50-05:00 5 5 574 592 2011-10-12T23:20:50-05:00