检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Meng, Jia Zhang, Jianqiu Chen, Yidong Huang, Yufei Univ Texas San Antonio Dept Elect & Comp Engn San Antonio TX 78249 USA UT Hlth Sci Ctr San Antonio Dept Epidemiol & Biostat San Antonio TX USA UT Hlth Sci Ctr San Antonio Greehey Childrens Canc Res Inst San Antonio TX USA

ISBN: (纸本)9781424483075

The problem of uncovering transcriptional regulation by transcription factors (TFs) based on microarray data is considered. A novel Bayesian sparse correlated rectified factor model (BSCRFM) coupled with its ICM solution is proposed. BSCRFM models the unknown TF protein level activity, the correlated regulations between TFs, and the sparse nature of TF regulated genes and it admits prior knowledge from existing database regarding TF regulated target genes. An efficient Iterated Conditional Modes (ICM) algorithm is developed, and a maximum a posterior (MAP) solution is calculated from multiple ICM results to avoid the local maximum problem, a context-specific transcriptional regulatory network specific to the experimental condition of the microarray data can then be obtained. The proposed model's ICM algorithm and MAP solution are evaluated on the simulated systems and results demonstrated the validity and effectiveness of the proposed approach. The proposed model is also applied to the breast cancer microarray data and a TF regulated network is obtained.

关键词： BSCRFM model Bayes methods Bayesian sparse correlated rectified factor model bioinformatics cellular biophysics iterated conditional modes maximum a posterior solution microarray data protein proteins transcriptional regulatory network

来源：评论

学校读者我要写书评

暂无评论

A THREE-STAGE METHOD TO SELECT INFORMATIVE GENES FOR CANCER CLASSIFICATION

A THREE-STAGE METHOD TO SELECT INFORMATIVE GENES FOR CANCER ...

引用

40th ISCIE International Symposium on Stochastic Systems Theory and Its Applications

作者： Mohamad, Mohd Saberi Omatu, Sigeru Yoshioka, Michifumi Deris, Safaai Osaka Prefecture Univ Grad Sch Engn Dept Comp Sci & Intelligent Syst Osaka 5998531 Japan Univ Teknol Malaysia Dept Software Engn Fac Comp Sci & Informat Syst Skudai 81310 Johore Malaysia

microarray technology has provided biologists with the ability to measure the expression levels of thousands of genes in a single experiment. One of the urgent issues in the use of microarray data is the selection of a small subset of genes from the thousands of genes in the data that contributes to a disease. This selection process is difficult due to many irrelevant genes, noisy genes, and the availability of the small number of Samples compared to the huge number Of genes (high-dimensional data). In this study, we propose a three-stage gene selection method to select a small subset of informative genes that is most relevant for the cancer classification. It has three stages: 1) pre-selecting genes using a filter method to produce a subset of genes;2) optimising the gene Subset using a multi-objective hybrid method to yield near-optimal gene Subsets;3) analysing the frequency of appearance of each gene in the different near-optimal gene subsets to produce a small subset of informative genes. The experimental results show that our proposed method is capable in selecting the small subset to obtain better classification accuracies than other related previous works as well as five methods experimented in this work. Additionally, a list of informative genes in the final gene subsets is also presented for biological usage.

关键词： A three-stage method Gene selection Hybrid approach microarray data

来源：评论

学校读者我要写书评

暂无评论

Binary-Organoid Particle Swarm Optimisation for Inferring Genetic Networks

Binary-Organoid Particle Swarm Optimisation for Inferring Ge...

引用

2010 IEEE World Congress on Computational Intelligence

作者： Chanthaphavong, Santi S. Chetty, Madhu Monash Univ Gippsland Sch Informat Technol Fac Informat Technol Churchill 3842 Australia

ISBN: (纸本)9781424481262

A holistic understanding of genetic interactions is crucial in the analysis of complex biological systems. However, due to the dimensionality problem (less samples and large number of genes) of microarray data, obtaining an optimal gene regulatory network is not only difficult but also computationally expensive. In this paper, a Bayesian model for the genetic interactions using the Minimum Description Length as a scoring metric is proposed. For fast optimisation of the network structure, we propose a novel Swarm Intelligence algorithm called Binary-Organoid Particle Swarm (BORG-Swarm). In BORG-Swarm we introduce the concepts of probability threshold vector and particle drift to update particle positions. Experimental studies are carried out using real-life yeast cell cycle dataset. Results indicate that existing binary swarms fail to converge and suffer from long runtimes. In constrast, BORG-Swarm's fast convergence towards the global optimum becomes apparent from results of extensive simulations.

关键词： BORG-swarm algorithm Bayes methods Bayesian model artificial intelligence binary-organoid particle swarm optimisation biology computing complex biological system data handling dimensionality problem genetic algorithms genetic interaction genetic network genetics microarray data minimum description length network structure optimal gene regulatory network particle drift particle swarm optimisation probability probability threshold vector real-life yeast cell cycle dataset scoring metric swarm intelligence algorithm

来源：评论

学校读者我要写书评

暂无评论

Time Series Gene Expression data Classification via L₁-norm Temporal SVM

引用

5th International Conference on Pattern Recognition in Bioinformatics

作者： Orsenigo, Carlotta Vercellis, Carlo Politecn Milan Dept Management Econ & Ind Engn I-20156 Milan Italy

ISBN: (纸本)9783642160004

Machine learning methods have been successfully applied to the phenotype classification of many diseases based on static gene expression measurements. More recently microarray data have been collected over time, making available datasets composed by time series of expression gene profiles. In this paper we propose a new method for time series classification, based on a temporal extension of L-1-norm support vector machines, that uses dynamic time warping distance for measuring time series similarity. This results in a mixed-integer optimization model which is solved by a sequential approximation algorithm. Computational tests performed on two benchmark datasets indicate the effectiveness of the proposed method compared to other techniques, and the general usefulness of the approaches based on dynamic time warping for labeling time series gene expression data.

关键词： Time series classification microarray data L-1-norm support vector machines dynamic time warping

来源：评论

学校读者我要写书评

暂无评论

Analysis of Module of Co-regulated Genes by Integrating Information from Sequence and microarray

Analysis of Module of Co-regulated Genes by Integrating Info...

引用

4th International Conference on Bioinformatics and Biomedical Engineering (iCBBE)

作者： Qiang Bo Wang Zheng-Zhi Natl Univ Def Technol Coll Mechatron Engn & Automat Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9781424447138

The researches of module of co-regulated genes act as important role in research of gene regulatory networks. Present analysis of module of co-regulated genes generally have 2 problems: The first one is that the co-expressed genes are generally clustered as the co-regulated genes, but recent studies show that only 50% genes are co-regulated when their Spearman correlative coefficients are bigger than 0.84, so the co-regulated genes need to be refined from cluster of co-expressed genes;the other problem is that the common transcription factor (TF) is usually unknown, this makes obstacle in quantitative analysis on regulation relationships between TF and target genes. This paper presents a method for analysis of module about co-regulated genes by integrating information from sequences and microarray data. Firstly we cluster the genes by the similarity of expression profiles;then the co-regulated genes are refined by analysis of transcription factor binding sites (TFBS) in their promoter regions;the expression level of the gene corresponding to the common transcription factor can be estimated by Viterbi decoding based on Hidden Markov Model (HMM), whose parameters are learned by Baum-Welch algorithm. By consulting the related articles of experiments and standard database, the correctness and effectiveness of our method are validated.

关键词： Module of co-regulated genes Sequence of Gene microarray data Co-regulated Genes Transcription Factor Binding Sites

来源：评论

学校读者我要写书评

暂无评论

Local likelihood regression in generalized linear single-index models with applications to microarray data

引用

COMPUTATIONAL STATISTICS & data ANALYSIS 2006年第3期51卷 2091-2113页

作者： Lambert-Lacroix, Sophie Peyre, Julie IMAG LMC F-38041 Grenoble 9 France

Searching for an effective dimension reduction space is an important problem in regression, especially for high-dimensional data such as microarray data. A major characteristic of microarray data consists in the small number of observations n and a very large number of genes p. This "large p, small n" paradigm makes the discriminant analysis for classification difficult. In order to offset this dimensionality problem a solution consists in reducing the dimension. Supervised classification is understood as a regression problem with a small number of observations and a large number of covariates. A new approach for dimension reduction is proposed. This is based on a semi-parametric approach which uses local likelihood estimates for single-index generalized linear models. The asymptotic properties of this procedure are considered and its asymptotic performances are illustrated by simulations. Applications of this method when applied to binary and multiclass classification of the three real data sets Colon, Leukemia and SRBCT are presented. (c) 2006 Elsevier B.V. All rights reserved.

关键词： dimension reduction generalized linear models generalized linear single-index models local likelihood estimates nonparametric regression microarray data

来源：评论

学校读者我要写书评

暂无评论

A robust procedure for Gaussian graphical model search from microarray data with p larger than n

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2006年第12期7卷 2621-2650页

作者： Castelo, Robert Roverato, Alberto Univ Pompeu Fabra Dept Ciencies Expt & Salut E-08003 Barcelona Spain Univ Bologna Dipartimento Sci Stat I-40126 Bologna Italy

Learning of large-scale networks of interactions from microarray data is an important and challenging problem in bioinformatics. A widely used approach is to assume that the available data constitute a random sample from a multivariate distribution belonging to a Gaussian graphical model. As a consequence, the prime objects of inference are full-order partial correlations which are partial correlations between two variables given the remaining ones. In the context of microarray data the number of variables exceed the sample size and this precludes the application of traditional structure learning procedures because a sampling version of full-order partial correlations does not exist. In this paper we consider limited-order partial correlations, these are partial correlations computed on marginal distributions of manageable size, and provide a set of rules that allow one to assess the usefulness of these quantities to derive the independence structure of the underlying Gaussian graphical model. Furthermore, we introduce a novel structure learning procedure based on a quantity, obtained from limited-order partial correlations, that we call the non-rejection rate. The applicability and usefulness of the procedure are demonstrated by both simulated and real data.

关键词： Gaussian distribution gene network graphical model microarray data non-rejection rate partial correlation small-sample inference

来源：评论

学校读者我要写书评

暂无评论

A novel ensemble machine learning for robust microarray data classification

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2006年第6期36卷 553-573页

作者： Peng, Yonghong Univ Bradford Dept Comp Bradford BD7 1DP W Yorkshire England

microarray data analysis and classification has demonstrated convincingly that it provides an effective methodology for the effective diagnosis of diseases and cancers. Although much research has been performed on applying machine learning techniques for microarray data classification during the past years, it has been shown that conventional machine learning techniques have intrinsic drawbacks in achieving accurate and robust classifications. This paper presents a novel ensemble machine learning approach for the development of robust microarray data classification. Different from the conventional ensemble learning techniques, the approach presented begins with generating a pool of candidate base classifiers based on the gene sub-sampling and then the selection of a sub-set of appropriate base classifiers to construct the classification committee based on classifier clustering. Experimental results have demonstrated that the classifiers constructed by the proposed method outperforms not only the classifiers generated by the conventional machine learning but also the classifiers generated by two widely used conventional ensemble learning methods (bagging and boosting). (c) 2005 Elsevier Ltd. All rights reserved.

关键词： microarray data machine learning ensemble learning classification

来源：评论

学校读者我要写书评

暂无评论

PathEx: a novel multi factors based datasets selector web tool

引用

BMC BIOINFORMATICS 2010年第1期11卷 1-9页

作者： Bareke, Eric Pierre, Michael Gaigneaux, Anthoula De Meulder, Bertrand Depiereux, Sophie Habra, Naji Depiereux, Eric Univ Namur FUNDP Mol Biol Res Unit URBM Namur Belgium Univ Namur FUNDP Res Ctr Informat Syst Engn PReCISE Namur Belgium

Background: microarray experiments have become very popular in life science research. However, if such experiments are only considered independently, the possibilities for analysis and interpretation of many life science phenomena are reduced. The accumulation of publicly available data provides biomedical researchers with a valuable opportunity to either discover new phenomena or improve the interpretation and validation of other phenomena that partially understood or well known. This can only be achieved by intelligently exploiting this rich mine of information. Description: Considering that technologies like microarrays remain prohibitively expensive for researchers with limited means to order their own experimental chips, it would be beneficial to re-use previously published microarray data. For certain researchers interested in finding gene groups (requiring many replicates), there is a great need for tools to help them to select appropriate datasets for analysis. These tools may be effective, if and only if, they are able to re-use previously deposited experiments or to create new experiments not initially envisioned by the depositors. However, the generation of new experiments requires that all published microarray data be completely annotated, which is not currently the case. Thus, we propose the PathEx approach. Conclusion: This paper presents PathEx, a human-focused web solution built around a two-component system: one database component, enriched with relevant biological information (expression array, omics data, literature) from different sources, and another component comprising sophisticated web interfaces that allow users to perform complex dataset building queries on the contents integrated into the PathEx database.

关键词： microarray data Sample File Content Logic Publish microarray data Chip Definition Files

来源：评论

学校读者我要写书评

暂无评论

Quenching of microbial samples for increased reliability of microarray data

引用

JOURNAL OF MICROBIOLOGICAL METHODS 2006年第2期64卷 207-216页

作者： Pieterse, B Jellema, RH van der Werf, MJ TNO NL-3700 AJ Zeist Netherlands Wageningen Ctr Food Sci NL-6700 AN Wageningen Netherlands

Messenger RNA levels change on a minutes scale due to both degradation and de novo transcription. Consequently, alterations in the transcript profiles that are not representative for the condition of interest are easily introduced during sample harvesting and work-up. In order to avoid these unwanted changes we have validated a -45 degrees C methanol-based quenching method for obtaining reliable and reproducible 'snapshot' samples of Lactobacillus plantarum cells for transcriptome analyses. Transcript profiles of cells harvested with the quenching method were compared with transcript profiles of cells that were harvested according to two different commonly applied protocols. Significant differences between the transcript profiles of cells harvested by the different methods from the same steady-state culture were observed. In total. 42 genes or operons were identified from which the transcript levels were altered when the cells were not immediately quenched upon harvesting. Among these, several have previously been associated with cold-shock response. Furthermore, the reproducibility of transcript profiles improved, as indicated by the fact that the variation in the data sets obtained from the quenched cells was smaller than in the data sets obtained from the cells that were harvested under non-quenched conditions. (c) 2005 Elsevier B.V. All rights reserved.

关键词： quenching microbial samples microarray data

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：