@article{howard_hu_babaoglu_chandra_borghi_tan_he_winter-sederoff_gassmann_veronese_et al._2013, title={High-Throughput RNA Sequencing of Pseudomonas-Infected Arabidopsis Reveals Hidden Transcriptome Complexity and Novel Splice Variants}, volume={8}, ISSN={["1932-6203"]}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84885077606&partnerID=MN8TOARS}, DOI={10.1371/journal.pone.0074183}, abstractNote={We report the results of a genome-wide analysis of transcription in Arabidopsis thaliana after treatment with Pseudomonas syringae pathovar tomato. Our time course RNA-Seq experiment uses over 500 million read pairs to provide a detailed characterization of the response to infection in both susceptible and resistant hosts. The set of observed differentially expressed genes is consistent with previous studies, confirming and extending existing findings about genes likely to play an important role in the defense response to Pseudomonas syringae. The high coverage of the Arabidopsis transcriptome resulted in the discovery of a surprisingly large number of alternative splicing (AS) events – more than 44% of multi-exon genes showed evidence for novel AS in at least one of the probed conditions. This demonstrates that the Arabidopsis transcriptome annotation is still highly incomplete, and that AS events are more abundant than expected. To further refine our predictions, we identified genes with statistically significant changes in the ratios of alternative isoforms between treatments. This set includes several genes previously known to be alternatively spliced or expressed during the defense response, and it may serve as a pool of candidate genes for regulated alternative splicing with possible biological relevance for the defense response against invasive pathogens.}, number={10}, journal={PLOS ONE}, author={Howard, Brian E. and Hu, Qiwen and Babaoglu, Ahmet Can and Chandra, Manan and Borghi, Monica and Tan, Xiaoping and He, Luyan and Winter-Sederoff, Heike and Gassmann, Walter and Veronese, Paola and et al.}, year={2013}, month={Oct} } @article{howard_heber_2010, title={Towards reliable isoform quantification using RNA-SEQ data}, volume={11}, ISSN={["1471-2105"]}, DOI={10.1186/1471-2105-11-s3-s6}, abstractNote={In eukaryotes, alternative splicing often generates multiple splice variants from a single gene. Here we explore the use of RNA sequencing (RNA-Seq) datasets to address the isoform quantification problem. Given a set of known splice variants, the goal is to estimate the relative abundance of the individual variants.Our method employs a linear models framework to estimate the ratios of known isoforms in a sample. A key feature of our method is that it takes into account the non-uniformity of RNA-Seq read positions along the targeted transcripts.Preliminary tests indicate that the model performs well on both simulated and real data. In two publicly available RNA-Seq datasets, we identified several alternatively-spliced genes with switch-like, on/off expression properties, as well as a number of other genes that varied more subtly in isoform expression. In many cases, genes exhibiting differential expression of alternatively spliced transcripts were not differentially expressed at the gene level.Given that changes in isoform expression level frequently involve a continuum of isoform ratios, rather than all-or-nothing expression, and that they are often independent of general gene expression changes, we anticipate that our research will contribute to revealing a so far uninvestigated layer of the transcriptome. We believe that, in the future, researchers will prioritize genes for functional analysis based not only on observed changes in gene expression levels, but also on changes in alternative splicing.}, journal={BMC BIOINFORMATICS}, author={Howard, Brian E. and Heber, Steffen}, year={2010} } @article{howard_sick_heber_2009, title={Unsupervised assessment of microarray data quality using a Gaussian mixture model}, volume={10}, ISSN={["1471-2105"]}, DOI={10.1186/1471-2105-10-191}, abstractNote={Quality assessment of microarray data is an important and often challenging aspect of gene expression analysis. This task frequently involves the examination of a variety of summary statistics and diagnostic plots. The interpretation of these diagnostics is often subjective, and generally requires careful expert scrutiny. We show how an unsupervised classification technique based on the Expectation-Maximization (EM) algorithm and the naïve Bayes model can be used to automate microarray quality assessment. The method is flexible and can be easily adapted to accommodate alternate quality statistics and platforms. We evaluate our approach using Affymetrix 3' gene expression and exon arrays and compare the performance of this method to a similar supervised approach. This research illustrates the efficacy of an unsupervised classification approach for the purpose of automated microarray data quality assessment. Since our approach requires only unannotated training data, it is easy to customize and to keep up-to-date as technology evolves. In contrast to other "black box" classification systems, this method also allows for intuitive explanations.}, journal={BMC BIOINFORMATICS}, author={Howard, Brian E. and Sick, Beate and Heber, Steffen}, year={2009}, month={Jun} } @article{frahm_howard_heber_muddiman_2006, title={Accessible proteomics space and its implications for peak capacity for zero-, one- and two-dimensional separations coupled with FT-ICR and TOF mass spectrometry}, volume={41}, ISSN={["1096-9888"]}, DOI={10.1002/jms.1024}, abstractNote={AbstractThe number and wide dynamic range of components found in biological matrixes present several challenges for global proteomics. In this perspective, we will examine the potential of zero‐dimensional (0D), one‐dimensional (1D), and two‐dimensional (2D) separations coupled with Fourier‐transform ion cyclotron resonance (FT‐ICR) and time‐of‐flight (TOF) mass spectrometry (MS) for the analysis of complex mixtures. We describe and further develop previous reports on the space occupied by peptides, to calculate the theoretical peak capacity available to each separations‐mass spectrometry method examined. Briefly, the peak capacity attainable by each of the mass analyzers was determined from the mass resolving power (RP) and the m/z space occupied by peptides considered from the mass distribution of tryptic peptides from National Center for Biotechnology Information's (NCBI's) nonredundant database. Our results indicate that reverse‐phase‐nanoHPLC (RP‐nHPLC) separation coupled with FT‐ICR MS offers an order of magnitude improvement in peak capacity over RP‐nHPLC separation coupled with TOF MS. The addition of an orthogonal separation method, strong cation exchange (SCX), for 2D LC‐MS demonstrates an additional 10‐fold improvement in peak capacity over 1D LC‐MS methods. Peak capacity calculations for 0D LC, two different 1D RP‐HPLC methods, and 2D LC (with various numbers of SCX fractions) for both RP‐HPLC methods coupled to FT‐ICR and TOF MS are examined in detail. Peak capacity production rates, which take into account the total analysis time, are also considered for each of the methods. Furthermore, the significance of the space occupied by peptides is discussed. Copyright © 2006 John Wiley & Sons, Ltd.}, number={3}, journal={JOURNAL OF MASS SPECTROMETRY}, author={Frahm, JL and Howard, BE and Heber, S and Muddiman, DC}, year={2006}, month={Mar}, pages={281–288} }