Identification and quantitation of clinically relevant microbes in patient samples: Comparison of three k-mer based classifiers for speed, accuracy, and sensitivity.
George S. WattsJames E. Thornton Jr.Ken Youens-ClarkAlise J. PonseroMarvin J. SlepianEmmanuel MenashiCharles HuWuquan DengDavid G. ArmstrongSpenser ReedLee D. CranmerBonnie L. HurwitzPublished in: PLoS Comput. Biol. (2019)
Keyphrases
- clinically relevant
- confusion matrices
- confusion matrix
- training samples
- processing speed
- high accuracy
- optimum path forest
- training set
- test set
- sensitivity analysis
- improving classification accuracy
- execution speed
- roc curve
- data sets
- prediction accuracy
- training data
- classification accuracy
- error rate
- ensemble pruning
- computational cost
- individual classifiers
- fold cross validation
- decision trees
- high speed
- data samples
- small sample
- naive bayes
- roc analysis
- unseen data
- higher classification accuracy
- support vector
- highest accuracy
- test sample
- machine learning algorithms
- training examples
- feature space
- class labels
- health care
- classification rate
- multi class
- linear classifiers