Data Mining & Protein Structures

[Simon Andrews]

Louis Hom wrote:
> 
> I'm curious about efforts to use data mining and machine learning
> approaches to shed light on the rules governing protein folding;  I was
> wondering if anyone had particular references/online documents that they'd
> suggest I read.  I should probably mention that I'm a biochemist venturing
> into CS and not a computer scientist venturing into biochemistry.  I'm
> aware of threading methods, but I hoping for something involving perhaps
> even a more naive approach.

I'd take a look at the ROSETTA program from David Baker, the most
successful ab initio folding program, and sounds like the sort of thing
you're after;

Simons, K.T., Bonneau, R., Ruczinski, I., Baker, D. (1999). Ab initio
Protein Structure Prediction of CASP III Targets Using ROSETTA. Proteins
3,
171-176.

http://depts.washington.edu/bakerpg/casp4/casp4.html


You could also look at the FRAGFOLD program from David Jones which takes
a similar approach. (He's just moved to Brunel, and his homepage is not
back yet, but you can read the CASP4 summary).

http://PredictionCenter.llnl.gov/casp4/abstracts/casp4-abstracts-ab.html#1


Hope this helps

TTFN

Simon.