svmTrain {MSiP}

svmTrain

Description

The labeled feature matrix can be used as input for Support Vector Machines (SVM) classifier. The classifier then assigns each bait-prey pair a confidence score, indicating the level of support for that pair of proteins to interact. Hyperparameter optimization can also be performed to select a set of parameters that maximizes the model's performance. This function also computes the areas under the precision-recall (PR) and ROC curve to evaluate the performance of the classifier.

Usage

svmTrain(
  dtInput,
  impute = TRUE,
  p = 0.3,
  parameterTuning = TRUE,
  cost = seq(from = 2, to = 10, by = 2),
  gamma = seq(from = 0.01, to = 0.1, by = 0.02),
  kernel = "radial",
  ncross = 10,
  pr.plot = TRUE,
  roc.plot = TRUE
)

Arguments

dtInput

Data frame containing instances with class labels

impute

Logical value, indicating whether to impute missing values

p

The percentage of data that goes to training; defaults to 0.3

parameterTuning

Logical value; indicating whether to tune SVM hyper parameters

cost

Cost of constraints violation

gamma

Parameter needed for all kernels except linear

kernel

Kernel type: 'linear', 'polynomial', 'sigmoid', or 'radial'; defaults to 'radial'

ncross

K-fold cross validation on the training data is performed to assess the quality of the model; defaults to 10

pr.plot

Logical value, indicating whether to plot precision-recall (PR) curve

roc.plot

Logical value, indicating whether to plot ROC curve

Value

Data frame containing a classification results for all instances in the data set, where positive confidence score corresponds to the level of support for the pair of proteins to be true positive, whereas negative score corresponds to the level of support for the pair of proteins to be true negative.

Author(s)

Matineh Rahmatbakhsh, [e-mail]

Examples

data(testdfClassifier)
predidcted_SVM <-
svmTrain(testdfClassifier,impute = FALSE,p = 0.3,parameterTuning = FALSE,
cost = seq(from = 2, to = 10, by = 2),
gamma = seq(from = 0.01, to = 0.10, by = 0.02),
kernel = "radial",ncross = 10,
pr.plot = FALSE, roc.plot = TRUE)
head(predidcted_SVM)