At this week's R clinic Frank Harrell will unveil the new rms (Regression Modeling Strategies) package that is a replacement for the R Design package.  He will demonstrate the differences with Design, especially related to enhanced graphics for displaying effects in regression models.  Frank will also discuss the implementation of quantile regression in rms.

Any R user no matter what level of experience has had trouble finding the package or the function to do what you want to do and then figuring out how to use it.  The sos package in R just made that a lot easier. First, fire up R, then install the sos package (don't omit the quotes): install.packages("sos") It'll ask you to choose a mirror.  Choose the closest one.

Revolutions blog recently posted a link to R code by Joshua Reich with self-contained examples of using machine learning techniques in R, including various clustering methods (k-means, nearest neighbor, and kernel), recursive partitioning (CART), principle components analysis, linear discriminant analysis, and support vector machines.  This post also links to some slides that go over the basics of machine learning.

Vanderbilt ACCRE users with PCs only... If you use ACCRE to run multi-processor jobs you'll be glad to know that they now allow you to map your home directory to your local desktop using Samba (so you can access your files through My Computer as you normally would with local files).

In the last post I showed you how to point to a file in windows and get the full path copied to your clipboard.  I wanted to come up with something similar for a Linux environment.  This is helpful on Vampire/ACCRE because you have to fully qualify the path to every file you use when you submit jobs with PBS scripts.

I wish I would have discovered this long ago.  Loading data into R or MySQL requires you to specify the full path to the file.  If you do this on a Windows machine there are two annoyances.  First, if you save something to your desktop the path to your desktop is really long.  Second, windows by default uses backslashes "\" in the file path, while R or other software requires forward slashes "/".

A quick announcement about a formatting fix here - you can now print posts from GGD a little more cleanly.  When you print it should no longer include the title and sidebar, so most posts should now only use a page or two.Getting Genetics Done by Stephen Turner is licensed under a Creative Commons Attribution (CC BY) License.

Here are citations for the articles discussed at our most recent meeting (August 28). I have also appended a link to Nature Reviews: Genetics new series, Fundamental concepts in genetics, at the end. Our next meeting is scheduled for September 11.~JuliaGurwitz D, Fortier I, Lunshof JE, Knoppers BM. Research ethics: Children and population biobanks. Science . 2009 Aug 14; 325(5942):818-9 Hastings PJ, Lupski JR, Rosenberg SM, Ira G.

I tip my hat to Will for showing me this little command line trick. PLINK's output looks nice when you print it to the screen, but it can be a pain to load the output into excel or a MySQL database because all the fields are separated by a variable number of spaces. This little command line trick will convert a variable-space delimited PLINK output file to a comma delimited file.You need to be on a Linux/Unix machine to do this.

http://www.harvardscience.harvard.edu/blog/how-dachshund-lost-its-legsGetting Genetics Done by Stephen Turner is licensed under a Creative Commons Attribution (CC BY) License.

While not directly related to genetics, this is an excellent example of well-designed data representation. The New York Times reports the results of a survey of average time spent on various activities through the day by different groups of people. The graphic is essentially a stacked density plot with time (24 hours) on the X-axis.