[BiO BB] bioclusters

[J.W. Bizzaro]

Michi Kami wrote:
>
> In case anyone isn't aware of it and would be interested - John
> Koza from Stanford has a 1000-Pentium Beowulf cluster set up. 
> (As my 3-year old says, "that's a big puppy!")  He has a write-up,
> and links to it, at http://www.xent.com/FoRK-archive/july99/0591.html
> His area is genetic algorithms (mine also, while bridging
> into bioinformatics), and the system runs Linux. 

I've been considering starting a mailing list, and later posting some HOWTO's,
for building computer clusters (e.g., Beowulf) for bioinformatics.  There are
at least two issues that make "bioclusters" unique, requiring discussions
outside of those for traditional clusters: (1) some bioinformatics programs
have special hardware requirements (e.g., "embarrassingly parallel" vs.
parallel or serial), and (2) bioinformaticians/ists may want to find and help
each other with locating or porting bioinformatics software to these clusters
(e.g., where can one get a parallel version of BLAST?).

I know some people who'd like to learn more (or anything) about building
bioclusters, but we need some people with experience willing to give advise. 
It would be silly to have 200 people on a list with no one able to answer a
single question.  If you are able to help, please contact me at
jeff at bioinformatics.org.

Also, if anyone knows of an existing discussion forum with educational
resources like what I'm proposing, please let us know.  Maybe we don't want to
reinvent the wheel.

Cheers.
Jeff
-- 
J.W. Bizzaro                                jeff at bioinformatics.org
Director, Bioinformatics.org        http://bioinformatics.org/~jeff
"As we enjoy great advantages from the inventions of others, we
should be glad of an opportunity to serve others by any invention
of ours; and this we should do freely and generously."
                   -- Benjamin Franklin
--