Adopting the MapReduce framework to pre-train 1-D and 2-D protein structure predictors with large protein datasets.
Jesse EickholtSuman KarkiPublished in: BIBM (2014)
Keyphrases
- protein structure
- protein sequences
- molecular biology
- protein structure prediction
- protein function
- amino acid sequences
- contact map
- amino acids
- secondary structure
- mapreduce framework
- protein tertiary structure
- cloud computing
- protein structural
- large scale data sets
- protein families
- knowledge discovery
- data sets
- solvent accessibility
- database
- protein folding
- support vector
- nuclear magnetic resonance
- contact maps