Improving feature ranking for biomarker discovery in proteomics mass spectrometry data using genetic programming.
Soha AhmedMengjie ZhangLifeng PengPublished in: Connect. Sci. (2014)
Keyphrases
- mass spectrometry data
- biomarker discovery
- feature ranking
- cancer classification
- gene selection
- high throughput
- mass spectrometry
- pattern classification
- random forest
- feature selection
- high dimensionality
- microarray
- microarray datasets
- microarray data
- fold cross validation
- feature subset selection
- gene expression data
- support vector machine
- early detection
- neural network
- feature subset
- support vector
- machine learning
- training data
- data analysis
- selected features
- classification models
- prediction accuracy
- missing values