What are the key fields in genetics/proteomics/metabolomics that use deep computes to aid research?
For those fields identified above, what are the key algorithms used? SVM, Bayesian, spectral, clustering, search, matching, etc.
And for those algorithms, what are the key databases that function as the source and targets of the research?
For bioinformatics/biomedical researchers, we have an opportunity to collaborate and provide them with $500k worth of gear to test some new parallel algorithms. The data set sizes we are targeting are 1-10Tbytes and the computes we are targeting are 10-100PetaFlops. Roughly a 100PetaFlops is the compute power of a 100 processor cluster computing for a day.