Use of machine learning algorithms to classify binary protein sequences as highly-designable or poorly-designable.
Myron PetoAndrzej KloczkowskiVasant G. HonavarRobert L. JerniganPublished in: BMC Bioinform. (2008)
Keyphrases
- machine learning algorithms
- protein sequences
- benchmark data sets
- computational biology
- machine learning
- learning algorithm
- machine learning methods
- decision trees
- amino acids
- protein classification
- protein structure
- random forests
- learning tasks
- machine learning approaches
- learning problems
- remote homology detection
- secondary structure
- amino acid sequences
- protein structure prediction
- machine learning models
- predictive accuracy
- sequence analysis
- biological sequences
- standard machine learning algorithms
- protein structure and function
- protein function
- multiple alignment
- protein secondary structure
- learning models
- support vector
- sequence databases
- data mining
- supervised learning
- feature selection
- protein structural