###### 2011

###### Here are the abstracts from the conference: http://www.warwick.ac.uk/statsdept/user-2011/abstract_booklet.pdf (it may take a while to load the big pdf!)

There are some useful and cutting edge abstracts from the R community.

*Using R to Empower A New Plant Biology*: iPlant provides a cyberinfrastructure that allows researchers in the plant science community to collaborate and share and integrate data and algorithms. Furthermore, by providing access to High Performance Computing resources it permits the generation and analysis of very large datasets as well as the usage of computationally intensive algorithms. Given the growing importance of R in virtually every field of biology and bioinformatics, iPlant's cyberinfrastructure has been enriched by an interface to facilitate the development, execution and distribution of R scripts. https://gucumatz.iplantcollaborative.org/idp/Authn/UserPassword (they also use the cloud: https://atmo.iplantcollaborative.org/login/)

*Arbitrary Accurate Computation with R*: Package 'Rmpfr': The R package Rmpfr allows to use arbitrary high precision numbers instead of R's double precision numbers in many R computations and functions. http://cran.r-project.org/web/packages/Rmpfr/vignettes/Maechler_useR_2011-abstr.pdf

*EMA - A R Package for Easy Microarray data analysis*: The increasing number of methodologies and tools currently available to analyse gene expression microarray data can be confusing for non specialist users. Based on the experience of biostatisticians of Institut Curie, we propose both a clear analysis strategy and a selection of tools to investigate microarray gene expression data. The most usual and relevant existing R functions were discussed, validated and gathered in an easy-to-use R package (EMA) devoted to gene expression microarray analysis. http://cran.r-project.org/web/packages/EMA/vignettes/EMA_vignette.pdf

*cloudnumbers.com*: Your calculation cloud for R': (http://cloudnumbers.com/)

*Using the Google Visualisation API with R*: (http://www.ssg.uab.edu/wiki/x/TIzu) (Neat motion charts!)

*Adding direct labels to plots*: http://directlabels.r-forge.r-project.org/

*Rstudio: IDE for R*: I have been using this in my workflow and find it quite stable and useful (http://rstudio.org/).

*GPU Computing in R*: Discusses ROpenCL package(http://cran.r-project.org/web/packages/OpenCL/index.html)

*R2wd: Writing MS-Word Documents from R*: R2wd is a package for creating new and modifying existing MS-Word documents. It allows to outline the document structure (title, headings, sections), insert text content, R graphs in metafile and bitmap formats, R dataframes as Word tables, mathematical formulas written in a LaTeX like style, and to apply Word themes to the document. (http://cran.r-project.org/web/packages/R2wd/R2wd.pdf

*Efficient data analysis workflow in R*(look for the abstract in the pdf)

*Investigate clusters if co-expressed and co-located genets at a genomic scale using cocoMAP*

*survAUC:Estimators of Prediction Accuracy for Time-to-Event Data*: (http://cran.at.r-project.org/web/packages/survAUC/index.html)

*Web 2.0 for R scripts & workflows: Tiki & PluginR*: This Wiki Plugin provides an interface to run R scripts through web pages (https://doc.tiki.org/PluginR)

*compareGroups package*: In many studies, such as epidemiological ones, it is needed to compare characteristics between groups of individuals or disease status. Usually these comparisons are presented in the form of tables (also called Bivariate Tables) of descriptive statistics where rows are characteristics, and each column is a group / status. Usually the number of characteristics is large, and thus construction of these tables is laborious. To build them in an easy, quick and efficient way, we created the compareGroups package 1. Here we present package improvements and extensions

*Easy interactive ggplots*: http://cran.r-project.org/web/packages/gWidgets/vignettes/gWidgets.pdf

*Microbenchmark*: A package to accurately benchmark R expressions (http://cran.r-project.org/web/packages/microbenchmark/index.html)

We present the R package microbenchmark. It provides functions to accurately measure the execution time of R expressions. This enables the user to benchmark and compare different implementation strategies for performance critical functions, whose execution time may be small, but which will be executed many times in his program. In contrast to the often used system.time and replicate combination, our package offers the following advantages: firstly it attempts to use the most accurate method of measuring time made available by the underlying operating system, secondly it estimates to overhead of the timing routines and subtracts it from all measurements automatically and lastly it provides utility functions to quickly compare the timing results for different expressions.

Labels