Skip to main content

Table 6 Misclassified proteins from the benchmark dataset by machine learning algorithms

From: A novel strategy for classifying the output from an in silicovaccine discovery pipeline for eukaryotic pathogens using machine learning algorithms

Algorithm

Incorrect YES classifications

Incorrect NO classifications

Adaptive boosting

 

Q27298

k-Nearest Neighbour

B6K9N1

B0LUH4

B9Q0C2

P84343

 

Q9U483

Naive Bayes Classifier

B9PK71

 

Neural Networks

  

Random Forest

 

Q27298

B9PRX5

Support Vector Machines

 

Q27298

B9QH60

  

B9PRX5

  1. Protein identifiers e.g. Q27298 are UniProt IDs. Refer to Additional file 1 for a description of the protein and its relevance as a vaccine candidate.