-
L. Bornn, A. Doucet, and R. Gottardo, "An efficient computational approach for prior sensitivity analysis and cross-validation," Canadian Journal of Statistics, vol. 9999, iss. 9999, 2010.
@article{citeulike:6562678, abstract = {Prior sensitivity analysis and cross-validation are important tools in Bayesian statistics. However, due to the computational expense of implementing existing methods, these techniques are rarely used. In this paper, the authors show how it is possible to use sequential Monte Carlo methods to create an efficient and automated algorithm to perform these tasks. They apply the algorithm to the computation of regularization path plots and to assess the sensitivity of the tuning parameter in g-prior model selection. They then demonstrate the algorithm in a cross-validation context and use it to select the shrinkage parameter in Bayesian regression. The Canadian Journal of Statistics {\copyright} 2010 Statistical Society of Canada},
address = {Department of Statistics, University of British Columbia, 333-6356 Agricultural Road, Vancouver, BC, Canada V6T 1Z2},
author = {Bornn, Luke and Doucet, Arnaud and Gottardo, Raphael},
citeulike-article-id = {6562678},
citeulike-linkout-0 = {http://dx.doi.org/10.1002/cjs.10045},
citeulike-linkout-1 = {http://www3.interscience.wiley.com/cgi-bin/abstract/123235480/ABSTRACT},
doi = {10.1002/cjs.10045},
issn = {1708-945X},
journal = {Canadian Journal of Statistics},
keywords = {computation, mcmc, smc},
number = {9999},
pages = {n/a+},
posted-at = {2010-01-19 13:16:56},
priority = {2},
title = {An efficient computational approach for prior sensitivity analysis and cross-validation},
url = {http://dx.doi.org/10.1002/cjs.10045},
volume = {9999},
year = {2010}
}
-
A. Droit, C. Cheung, and R. Gottardo, "RMAT – an R/Bioconductor package for analyzing ChIP-chip experiments," Bioinformatics, vol. 26, iss. 5, pp. 678-679, 2010.
@article{citeulike:6600462, abstract = {Summary: Chromatin immunoprecipitation combined with DNA microarrays (ChIP-chip) has evolved as a popular technique to study DNA-protein binding or post-translational chromatin/histone modifications at the genomic level. However, the raw microarray intensities generate a massive amount of data, creating a need for efficient analysis algorithms and statistical methods to identify enriched regions. Results: We present a fast, free and powerful, open source R package, rMAT, that allows the identification of regions enriched for transcription factor binding sites in ChIP-chip experiments on Affymetrix tiling arrays. Availability: The R-package rMAT is available from the Bioconductor web site at http://bioconductor.org and runs on Linux, MAC OS and MS-Windows. rMAT is distributed under the terms of the Artistic Licence 2.0. Contact: arnaud.droit@ircm.qc.ca; raphael.gottardo@ircm.qc.ca Supplementary information: Supplementary data are available at Bioinformatics online. 10.1093/bioinformatics/btq023},
author = {Droit, Arnaud and Cheung, Charles and Gottardo, Raphael},
citeulike-article-id = {6600462},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btq023},
citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/26/5/678},
citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/20089513},
citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=20089513},
day = {1},
doi = {10.1093/bioinformatics/btq023},
issn = {1367-4811},
journal = {Bioinformatics},
keywords = {bioinformatics, chip, tiling-arrays},
month = {March},
number = {5},
pages = {678--679},
posted-at = {2010-01-28 17:41:34},
priority = {2},
title = {rMAT - an R/Bioconductor package for analyzing ChIP-chip experiments},
url = {http://dx.doi.org/10.1093/bioinformatics/btq023},
volume = {26},
year = {2010}
}
-
R. Gottardo and A. E. Raftery, "Bayesian robust variable and transformation selection: A unified approach," Canadian Journal of Statistics, vol. 37, iss. 2, pp. 1-20, 2009.
@article{citeulike:3466536,
author = {Gottardo, R. and Raftery, A. E.},
citeulike-article-id = {3466536},
citeulike-linkout-0 = {http://www.rglab.org/download/bayesianvsandt\_cjs.pdf},
journal = {Canadian Journal of Statistics},
keywords = {bayesian, box-cox, mcmc, transformation, variable-selection},
number = {2},
pages = {1--20},
posted-at = {2008-10-30 19:14:19},
priority = {2},
title = {Bayesian robust variable and transformation selection: A unified approach},
url = {http://www.rglab.org/download/bayesianvsandt\_cjs.pdf},
volume = {37},
year = {2009}
}
-
K. Lo, F. Hahne, R. R. Brinkman, and R. Gottardo, "FlowClust: a Bioconductor package for automated gating of flow cytometry data.," BMC bioinformatics, vol. 10, p. 145, 2009.
@article{citeulike:4520045, abstract = {Background: As a high-throughput technology that offers rapid quantification of multidimensional characteristics for millions of cells, flow cytometry (FCM) is widely used in health research, medical diagnosis and treatment, and vaccine development. Nevertheless, there is an increasing concern about the lack of appropriate software tools to provide an automated analysis platform to parallelize the high-throughput data-generation platform. Currently, to a large extent, FCM data analysis relies on the manual selection of sequential regions in 2-D graphical projections to extract the cell populations of interest. This is a time-consuming task that ignores the high-dimensionality of FCM data. Results: In view of the aforementioned issues, we have developed an R package called flowClust to automate FCM analysis. flowClust implements a robust model-based clustering approach based on multivariate t mixture models with the Box-Cox transformation. The package provides the functionality to identify cell populations whilst simultaneously handling the commonly encountered issues of outlier identification and data transformation. It offers various tools to summarize and visualize a wealth of features of the clustering results. In addition, to ensure its convenience of use, flowClust has been adapted for the current FCM data format, and integrated with existing Bioconductor packages dedicated to FCM analysis. Conclusion: flowClust addresses the issue of a dearth of software that helps automate FCM analysis with a sound theoretical foundation. It tends to give reproducible results, and helps reduce the significant subjectivity and human time cost encountered in FCM analysis. The package contributes to the cytometry community by offering an efficient, automated analysis platform which facilitates the active, ongoing technological advancement.},
author = {Lo, Kenneth and Hahne, Florian and Brinkman, Ryan R. and Gottardo, Raphael},
citeulike-article-id = {4520045},
citeulike-linkout-0 = {http://dx.doi.org/10.1186/1471-2105-10-145},
citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/19442304},
citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=19442304},
day = {14},
doi = {10.1186/1471-2105-10-145},
issn = {1471-2105},
journal = {BMC bioinformatics},
keywords = {bioinformatics, clustering, flow-cytometry, mixture-model, statistics},
month = {May},
pages = {145+},
posted-at = {2009-05-18 02:10:07},
priority = {2},
title = {flowClust: a Bioconductor package for automated gating of flow cytometry data.},
url = {http://dx.doi.org/10.1186/1471-2105-10-145},
volume = {10},
year = {2009}
}
-
G. Finak, A. Bashashati, R. Brinkman, and R. Gottardo, "Merging mixture components for cell population identification in flow cytometry.," Advances in bioinformatics, 2009.
@article{citeulike:6562670, abstract = {We present a framework for the identification of cell subpopulations in flow cytometry data based on merging mixture components using the flowClust methodology. We show that the cluster merging algorithm under our framework improves model fit and provides a better estimate of the number of distinct cell subpopulations than either Gaussian mixture models or flowClust, especially for complicated flow cytometry data distributions. Our framework allows the automated selection of the number of distinct cell subpopulations and we are able to identify cases where the algorithm fails, thus making it suitable for application in a high throughput FCM analysis pipeline. Furthermore, we demonstrate a method for summarizing complex merged cell subpopulations in a simple manner that integrates with the existing flowClust framework and enables downstream data analysis. We demonstrate the performance of our framework on simulated and real FCM data. The software is available in the flowMerge package through the Bioconductor project.},
author = {Finak, Greg and Bashashati, Ali and Brinkman, Ryan and Gottardo, Rapha\"{e}l},
citeulike-article-id = {6562670},
citeulike-linkout-0 = {http://dx.doi.org/10.1155/2009/247646},
citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/20049161},
citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=20049161},
doi = {10.1155/2009/247646},
issn = {1687-8035},
journal = {Advances in bioinformatics},
keywords = {bioinformatics, flow-cytometry, mixture-models},
posted-at = {2010-01-19 13:13:19},
priority = {2},
title = {Merging mixture components for cell population identification in flow cytometry.},
url = {http://dx.doi.org/10.1155/2009/247646},
year = {2009}
}
-
V. T. Chu, R. Gottardo, A. E. Raftery, R. E. Bumgarner, and K. Y. Yeung, "MeV+R: using MeV as a graphical user interface for Bioconductor applications in microarray analysis," Genome Biology, vol. 9, p. 118, 2008.
@article{citeulike:3044031,
author = {Chu, Vu T. and Gottardo, Raphael and Raftery, Adrian E. and Bumgarner, Roger E. and Yeung, Ka Y.},
citeulike-article-id = {3044031},
citeulike-linkout-0 = {http://dx.doi.org/10.1186/gb-2008-9-7-r118},
citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/18652698},
citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=18652698},
day = {24},
doi = {10.1186/gb-2008-9-7-r118},
issn = {1465-6906},
journal = {Genome Biology},
keywords = {mevr},
month = {July},
pages = {R118+},
posted-at = {2008-10-30 18:35:11},
priority = {2},
title = {MeV+R: using MeV as a graphical user interface for Bioconductor applications in microarray analysis},
url = {http://dx.doi.org/10.1186/gb-2008-9-7-r118},
volume = {9},
year = {2008}
}
-
R. Gottardo and A. E. Raftery, "Markov chain monte carlo with mixtures of singular distributions," Journal of Computational and Graphical Statistics, vol. 17, iss. 4, pp. 917-943, 2008.
@article{citeulike:3466532,
author = {Gottardo, R. and Raftery, A. E.},
citeulike-article-id = {3466532},
citeulike-linkout-0 = {http://pubs.amstat.org/doi/abs/10.1198/106186008X386102},
journal = {Journal of Computational and Graphical Statistics},
keywords = {bayesian, computation},
month = {December},
number = {4},
pages = {917--943},
posted-at = {2008-10-30 19:12:15},
priority = {2},
title = {Markov chain monte carlo with mixtures of singular distributions},
url = {http://pubs.amstat.org/doi/abs/10.1198/106186008X386102},
volume = {17},
year = {2008}
}
-
K. Lo, R. R. Brinkman, and R. Gottardo, "Automated gating of flow cytometry data via robust model-based clustering.," Cytometry. Part A : the journal of the International Society for Analytical Cytology, vol. 73, iss. 4, pp. 321-332, 2008.
@article{citeulike:3466477, abstract = {The capability of flow cytometry to offer rapid quantification of multidimensional characteristics for millions of cells has made this technology indispensable for health research, medical diagnosis, and treatment. However, the lack of statistical and bioinformatics tools to parallel recent high-throughput technological advancements has hindered this technology from reaching its full potential. We propose a flexible statistical model-based clustering approach for identifying cell populations in flow cytometry data based on t-mixture models with a Box-Cox transformation. This approach generalizes the popular Gaussian mixture models to account for outliers and allow for nonelliptical clusters. We describe an Expectation-Maximization (EM) algorithm to simultaneously handle parameter estimation and transformation selection. Using two publicly available datasets, we demonstrate that our proposed methodology provides enough flexibility and robustness to mimic manual gating results performed by an expert researcher. In addition, we present results from a simulation study, which show that this new clustering framework gives better results in terms of robustness to model misspecification and estimation of the number of clusters, compared to the popular mixture models. The proposed clustering methodology is well adapted to automated analysis of flow cytometry data. It tends to give more reproducible results, and helps reduce the significant subjectivity and human time cost encountered in manual gating analysis.},
author = {Lo, K. and Brinkman, R. R. and Gottardo, R.},
citeulike-article-id = {3466477},
citeulike-linkout-0 = {http://dx.doi.org/10.1002/cyto.a.20531},
citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/18307272},
citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=18307272},
doi = {10.1002/cyto.a.20531},
issn = {1552-4930},
journal = {Cytometry. Part A : the journal of the International Society for Analytical Cytology},
keywords = {flowclust},
month = {April},
number = {4},
pages = {321--332},
posted-at = {2008-10-30 18:36:17},
priority = {2},
title = {Automated gating of flow cytometry data via robust model-based clustering.},
url = {http://dx.doi.org/10.1002/cyto.a.20531},
volume = {73},
year = {2008}
}
-
R. Gottardo, W. Li, E. W. Johnson, and S. X. Liu, "A Flexible and Powerful Bayesian Hierarchical Model for ChIP-Chip Experiments," Biometrics, vol. 64, iss. 12, pp. 468-478, 2008.
@article{citeulike:2358259, abstract = {Summary. Chromatin-immunoprecipitation microarrays (ChIP-chip) that enable researchers to identify regions of a given genome that are bound by specific DNA-binding proteins present new challenges for statistical analysis due to the large number of probes, the high noise-to-signal ratio, and the spatial dependence between probes. We propose a method called BAC (Bayesian analysis of ChIP-chip) to detect transcription factor bound regions, which incorporate the dependence between probes while making little assumptions about the bound regions (e.g., length). BAC is robust to probe outliers with an exchangeable prior for the variances, which allows different variances for the probes but still shrink extreme empirical variances. Parameter estimation is carried out using Markov chain Monte Carlo and inference is based on the joint distribution of the parameters. Bound regions are detected using posterior probabilities computed from the joint posterior distribution of neighboring probes. We show that these posterior probabilities are well calibrated and can be used to obtain an estimate of the false discovery rate. The method is illustrated using two publicly available ChIP-chip data sets containing 18 experimentally validated regions. We compare our method to four other baseline and commonly used techniques, namely, the Wilcoxon's rank sum test, TileMap, HGMM, and MAT. We found BAC and HGMM to perform best at detecting validated regions. However, HGMM appears to be very sensitive to probe outliers compared to BAC. In addition, we present a simulation study, which shows that BAC is more powerful than the other four techniques under various simulation scenarios while being robust to model misspecification.},
author = {Gottardo, Raphael and Li, Wei and Johnson, Evan W. and Liu, Shirley X.},
citeulike-article-id = {2358259},
citeulike-linkout-0 = {http://www.blackwell-synergy.com/doi/abs/10.1111/j.1541-0420.2007.00899.x},
citeulike-linkout-1 = {http://dx.doi.org/10.1111/j.1541-0420.2007.00899.x},
citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/17888037},
citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=17888037},
doi = {10.1111/j.1541-0420.2007.00899.x},
journal = {Biometrics},
keywords = {bac},
number = {12},
pages = {468--478},
posted-at = {2008-10-30 18:36:54},
priority = {2},
title = {A Flexible and Powerful Bayesian Hierarchical Model for ChIP-Chip Experiments},
url = {http://dx.doi.org/10.1111/j.1541-0420.2007.00899.x},
volume = {64},
year = {2008}
}
-
R. Gottardo, A. E. Raftery, K. Y. Yeung, and R. E. Bumgarner, "Quality Control and Robust Estimation for cDNA Microarrays With Replicates," Journal of the American Statistical Association, vol. 101, iss. 473, pp. 30-40, 2006.
@article{citeulike:510453,
author = {Gottardo, Raphael and Raftery, Adrian E. and Yeung, Ka Y. and Bumgarner, Roger E.},
citeulike-article-id = {510453},
citeulike-linkout-0 = {http://dx.doi.org/10.1198/016214505000001096},
citeulike-linkout-1 = {http://www.ingentaconnect.com/content/asa/jasa/2006/00000101/00000473/art00004},
doi = {10.1198/016214505000001096},
issn = {0162-1459},
journal = {Journal of the American Statistical Association},
keywords = {rama},
month = {March},
number = {473},
pages = {30--40},
posted-at = {2008-10-30 19:01:57},
priority = {2},
publisher = {American Statistical Association},
title = {Quality Control and Robust Estimation for cDNA Microarrays With Replicates},
url = {http://dx.doi.org/10.1198/016214505000001096},
volume = {101},
year = {2006}
}
-
E. W. Johnson, W. Li, C. A. Meyer, R. Gottardo, J. S. Carroll, M. Brown, and S. X. Liu, "Model-based analysis of tiling-arrays for ChIP-chip," Proceedings of the National Academy of Sciences, vol. 103, iss. 33, pp. 12457-12462, 2006.
@article{citeulike:1120020, abstract = {10.1073/pnas.0601180103 We propose a fast and powerful analysis algorithm, titled Model-based Analysis of Tiling-arrays (MAT), to reliably detect regions enriched by transcription factor chromatin immunoprecipitation (ChIP) on Affymetrix tiling arrays (ChIP-chip). MAT models the baseline probe behavior by considering probe sequence and copy number on each array. It standardizes the probe value through the probe model, eliminating the need for sample normalization. MAT uses an innovative function to score regions for ChIP enrichment, which allows robust value and false discovery rate calculations. MAT can detect ChIP regions from a single ChIP sample, multiple ChIP samples, or multiple ChIP samples with controls with increasing accuracy. The single-array ChIP region detection feature minimizes the time and monetary costs for laboratories newly adopting ChIP-chip to test their protocols and antibodies and allows established ChIP-chip laboratories to identify samples with questionable quality that might contaminate their data. MAT is developed in open-source Python and is available at . The general framework presented here can be extended to other oligonucleotide microarrays and tiling array platforms.},
address = {Department of Biostatistics and Computational Biology, Dana-Farber Cancer Institute, 44 Binney Street, Boston, MA 02115, USA.},
author = {Johnson, W. Evan and Li, Wei and Meyer, Clifford A. and Gottardo, Raphael and Carroll, Jason S. and Brown, Myles and Liu, X. Shirley},
citeulike-article-id = {1120020},
citeulike-linkout-0 = {http://dx.doi.org/10.1073/pnas.0601180103},
citeulike-linkout-1 = {http://www.pnas.org/content/103/33/12457.full.abstract},
citeulike-linkout-2 = {http://www.pnas.org/content/103/33/12457.full.full.pdf},
citeulike-linkout-3 = {http://www.pnas.org/cgi/content/abstract/103/33/12457},
citeulike-linkout-4 = {http://view.ncbi.nlm.nih.gov/pubmed/16895995},
citeulike-linkout-5 = {http://www.hubmed.org/display.cgi?uids=16895995},
day = {15},
doi = {10.1073/pnas.0601180103},
issn = {0027-8424},
journal = {Proceedings of the National Academy of Sciences},
keywords = {mat},
month = {August},
number = {33},
pages = {12457--12462},
posted-at = {2008-10-30 18:38:37},
priority = {2},
title = {Model-based analysis of tiling-arrays for ChIP-chip},
url = {http://dx.doi.org/10.1073/pnas.0601180103},
volume = {103},
year = {2006}
}
-
K. Lo and R. Gottardo, "Flexible empirical Bayes models for differential gene expression.," Bioinformatics, 2006.
@article{citeulike:1023363, abstract = {MOTIVATION: Inference about differential expression is a typical objective when analyzing gene expression data. Recently, Bayesian hierarchical models have become increasingly popular for this type of problem. The two most common hierarchical models are the hierarchical Gamma-Gamma (GG) and Lognormal-Normal (LNN) models. However, to facilitate inference, some unrealistic assumptions have been made. One such assumption is that of a common coefficient of variation across genes, which can adversely affect the resulting inference. RESULTS: In this paper, we extend both the GG and LNN modeling frameworks to allow for gene-specific variances and propose EM based algorithms for parameter estimation. The proposed methodology is evaluated on three experimental datasets: one cDNA microarray experiment and two Affymetrix spike-in experiments. The two extended models significantly reduce the false positive rate while keeping a high sensitivity when compared to the originals. Finally, using a simulation study we show that the new frameworks are also more robust to model misspecification. AVAILABILITY: The R code for implementing the proposed methodology can be downloaded at http://www.stat.ubc.ca/\~{}c.lo/FEBarrays. SUPPLEMENTARY INFORMATION: The supplementary material is available at http://www.stat.ubc.ca/\~{}c.lo/FEBarrays/supp.pdf.},
address = {Department of Statistics, University of British Columbia, 333-6356 Agricultural Road, Vancouver, BC, V6T 1Z2.},
author = {Lo, Kenneth and Gottardo, Raphael},
citeulike-article-id = {1023363},
citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/17138586},
citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=17138586},
day = {30},
issn = {1460-2059},
journal = {Bioinformatics},
keywords = {febarrays},
month = {November},
posted-at = {2008-10-30 18:38:11},
priority = {2},
title = {Flexible empirical Bayes models for differential gene expression.},
url = {http://view.ncbi.nlm.nih.gov/pubmed/17138586},
year = {2006}
}
-
Gottardo, Raphael, Raftery, E. Adrian, Y. Yeung, Ka, Bumgarner, and E. Roger, "Bayesian Robust Inference for Differential Gene Expression in Microarrays with Multiple Samples," Biometrics, vol. 62, iss. 1, pp. 10-18, 2006.
@article{citeulike:552735,
author = {Gottardo and Raphael and Raftery and Adrian, E. and Yeung, Yee and Ka and Bumgarner and Roger, E.},
citeulike-article-id = {552735},
citeulike-linkout-0 = {http://dx.doi.org/10.1111/j.1541-0420.2005.00397.x},
citeulike-linkout-1 = {http://www.ingentaconnect.com/content/bpl/biom/2006/00000062/00000001/art00002},
citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/16542223},
citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=16542223},
doi = {10.1111/j.1541-0420.2005.00397.x},
issn = {0006-341X},
journal = {Biometrics},
keywords = {bridge},
month = {March},
number = {1},
pages = {10--18},
posted-at = {2008-10-30 18:39:25},
priority = {2},
publisher = {Blackwell Publishing},
title = {Bayesian Robust Inference for Differential Gene Expression in Microarrays with Multiple Samples},
url = {http://dx.doi.org/10.1111/j.1541-0420.2005.00397.x},
volume = {62},
year = {2006}
}
-
R. Gottardo, J. Besag, M. Stephens, and A. Murua, "Probabilistic segmentation and intensity estimation for microarray images.," Biostatistics (Oxford, England), vol. 7, iss. 1, pp. 85-99, 2006.
@article{citeulike:3466480, abstract = {We describe a probabilistic approach to simultaneous image segmentation and intensity estimation for complementary DNA microarray experiments. The approach overcomes several limitations of existing methods. In particular, it (a) uses a flexible Markov random field approach to segmentation that allows for a wider range of spot shapes than existing methods, including relatively common 'doughnut-shaped' spots; (b) models the image directly as background plus hybridization intensity, and estimates the two quantities simultaneously, avoiding the common logical error that estimates of foreground may be less than those of the corresponding background if the two are estimated separately; and (c) uses a probabilistic modeling approach to simultaneously perform segmentation and intensity estimation, and to compute spot quality measures. We describe two approaches to parameter estimation: a fast algorithm, based on the expectation-maximization and the iterated conditional modes algorithms, and a fully Bayesian framework. These approaches produce comparable results, and both appear to offer some advantages over other methods. We use an HIV experiment to compare our approach to two commercial software products: Spot and Arrayvision.},
author = {Gottardo, R. and Besag, J. and Stephens, M. and Murua, A.},
citeulike-article-id = {3466480},
citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/16049139},
citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=16049139},
issn = {1465-4644},
journal = {Biostatistics (Oxford, England)},
keywords = {prism},
month = {January},
number = {1},
pages = {85--99},
posted-at = {2008-10-30 18:39:48},
priority = {2},
title = {Probabilistic segmentation and intensity estimation for microarray images.},
url = {http://view.ncbi.nlm.nih.gov/pubmed/16049139},
volume = {7},
year = {2006}
}
-
J. F. Challacombe, A. Rechtsteiner, R. Gottardo, L. M. Rocha, E. P. Browne, T. Shenk, M. R. Altherr, and T. S. Brettin, "Evaluation of the host transcriptional response to human cytomegalovirus infection.," Physiological genomics, vol. 18, iss. 1, pp. 51-62, 2004.
@article{citeulike:3466481, abstract = {Gene expression data from human cytomegalovirus (HCMV)-infected cells were analyzed using DNA-Chip Analyzer (dChip) followed by singular value decomposition (SVD) and compared with a previous analysis of the same data that employed GeneChip software and a fold change filtering approach. dChip and SVD analysis revealed two clusters of coexpressed human genes responding differently to HCMV infection: one containing some genes identified previously, and another that was largely unique to this analysis. Annotating these genes, we identified several functional categories important to host cell responses to HCMV infection. These categories included genes involved in transcriptional regulation, oncogenesis, and cell cycle regulation, which were more prevalent in cluster 1, and genes involved in immune system regulation, signal transduction, and cell adhesion, which were more prevalent in cluster 2. Within these categories, we found genes involved in the host response to HCMV infection (mainly in cluster 1), as well as genes targeted by HCMV's immune evasion strategies (mainly in cluster 2). As the second group of genes identified by the dChip and SVD approach was statistically and biologically significant, our results point out the advantages of using different methods to analyze gene expression data.},
author = {Challacombe, J. F. and Rechtsteiner, A. and Gottardo, R. and Rocha, L. M. and Browne, E. P. and Shenk, T. and Altherr, M. R. and Brettin, T. S.},
citeulike-article-id = {3466481},
citeulike-linkout-0 = {http://dx.doi.org/10.1152/physiolgenomics.00155.2003},
citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/15069167},
citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=15069167},
day = {17},
doi = {10.1152/physiolgenomics.00155.2003},
issn = {1531-2267},
journal = {Physiological genomics},
keywords = {challacombe},
month = {June},
number = {1},
pages = {51--62},
posted-at = {2008-10-30 18:40:27},
priority = {2},
title = {Evaluation of the host transcriptional response to human cytomegalovirus infection.},
url = {http://dx.doi.org/10.1152/physiolgenomics.00155.2003},
volume = {18},
year = {2004}
}
-
G. Xie, C. A. Bonner, T. Brettin, R. Gottardo, N. O. Keyhani, and R. A. Jensen, "Lateral gene transfer and ancient paralogy of operons containing redundant copies of tryptophan-pathway genes in Xylella species and in heterocystous cyanobacteria.," Genome biology, vol. 4, iss. 2, 2003.
@article{citeulike:3466485, abstract = {BACKGROUND: Tryptophan-pathway genes that exist within an apparent operon-like organization were evaluated as examples of multi-genic genomic regions that contain phylogenetically incongruous genes and coexist with genes outside the operon that are congruous. A seven-gene cluster in Xylella fastidiosa includes genes encoding the two subunits of anthranilate synthase, an aryl-CoA synthetase, and trpR. A second gene block, present in the Anabaena/Nostoc lineage, but not in other cyanobacteria, contains a near-complete tryptophan operon nested within an apparent supraoperon containing other aromatic-pathway genes. RESULTS: The gene block in X. fastidiosa exhibits a sharply delineated low-GC content. This, as well as bias of codon usage and 3:1 dinucleotide analysis, strongly implicates lateral gene transfer (LGT). In contrast, parametric studies and protein tree phylogenies did not support the origination of the Anabaena/Nostoc gene block by LGT. CONCLUSIONS: Judging from the apparent minimal amelioration, the low-GC gene block in X. fastidiosa probably originated by LGT at a relatively recent time. The surprising inability to pinpoint a donor lineage still leaves room for alternative, albeit less likely, explanations other than LGT. On the other hand, the large Anabaena/Nostoc gene block does not seem to have arisen by LGT. We suggest that the contemporary Anabaena/Nostoc array of divergent paralogs represents an ancient ancestral state of paralog divergence, with extensive streamlining by gene loss occurring in the lineage of descent representing other (unicellular) cyanobacteria.},
author = {Xie, G. and Bonner, C. A. and Brettin, T. and Gottardo, R. and Keyhani, N. O. and Jensen, R. A.},
citeulike-article-id = {3466485},
citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/12620124},
citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=12620124},
issn = {1465-6914},
journal = {Genome biology},
keywords = {xie},
number = {2},
posted-at = {2008-10-30 18:43:52},
priority = {2},
title = {Lateral gene transfer and ancient paralogy of operons containing redundant copies of tryptophan-pathway genes in Xylella species and in heterocystous cyanobacteria.},
url = {http://view.ncbi.nlm.nih.gov/pubmed/12620124},
volume = {4},
year = {2003}
}
-
R. Gottardo, J. A. Pannucci, C. R. Kuske, and T. Brettin, "Statistical analysis of microarray data: a Bayesian approach.," Biostatistics (Oxford, England), vol. 4, iss. 4, pp. 597-620, 2003.
@article{citeulike:3466484, abstract = {The potential of microarray data is enormous. It allows us to monitor the expression of thousands of genes simultaneously. A common task with microarray is to determine which genes are differentially expressed between two samples obtained under two different conditions. Recently, several statistical methods have been proposed to perform such a task when there are replicate samples under each condition. Two major problems arise with microarray data. The first one is that the number of replicates is very small (usually 2-10), leading to noisy point estimates. As a consequence, traditional statistics that are based on the means and standard deviations, e.g. t-statistic, are not suitable. The second problem is that the number of genes is usually very large (approximately 10,000), and one is faced with an extreme multiple testing problem. Most multiple testing adjustments are relatively conservative, especially when the number of replicates is small. In this paper we present an empirical Bayes analysis that handles both problems very well. Using different parametrizations, we develop four statistics that can be used to test hypotheses about the means and/or variances of the gene expression levels in both one- and two-sample problems. The methods are illustrated using experimental data with prior knowledge. In addition, we present the result of a simulation comparing our methods to well-known statistics and multiple testing adjustments.},
author = {Gottardo, R. and Pannucci, J. A. and Kuske, C. R. and Brettin, T.},
citeulike-article-id = {3466484},
citeulike-linkout-0 = {http://dx.doi.org/10.1093/biostatistics/4.4.597},
citeulike-linkout-1 = {http://biostatistics.oxfordjournals.org/cgi/content/abstract/4/4/597},
citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/14557114},
citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=14557114},
doi = {10.1093/biostatistics/4.4.597},
issn = {1465-4644},
journal = {Biostatistics (Oxford, England)},
keywords = {sam},
month = {October},
number = {4},
pages = {597--620},
posted-at = {2008-10-30 18:43:16},
priority = {2},
title = {Statistical analysis of microarray data: a Bayesian approach.},
url = {http://dx.doi.org/10.1093/biostatistics/4.4.597},
volume = {4},
year = {2003}
}
X. Zhang, G. Robertson, M. Krzywinski, K. Ning, A. Droit, S. Jones, and R. Gottardo, "PICS: Probabilistic Inference for ChIP-seq," arXiv, 0903.3206, 2009.