Introduction

The MHCBench is an interface developed for evaluating the Major Histocompatibility Complex (MHC) binding peptide prediction algorithms. It allows the users to compare the performance of the old/new prediction methods in terms of the threshold dependent and independent parameters. The MHCBench offers a collection of defined data sets. The users can download these sets and can evaluate their own algorithms. The evaluations can be compared with other prediction methods evaluated using the same data sets. The server can be extended to include new methods for different MHC allele and new data sets.
Overall, the MHCBench is an effort to benchmark the prediction methods in terms of the data sets and the evaluation parameters

Services available

• Curated and defined data sets for evaluation.
• Evaluation parameters for an unbiased comparrison.
  • Threshold Independent Parameters.
  • Threshold Dependent Parameters.
• Evaluation of new algorithms using
  • The available data sets.
  • The user defined data set.
• Extandability.
  • Submit new data sets.
  • Submit new methods/algorithms