Protocol to explain support vector machine predictions via exact Shapley value computation.

Journal: STAR protocols
PMID:

Abstract

Shapley values from cooperative game theory are adapted for explaining machine learning predictions. For large feature sets used in machine learning, Shapley values are approximated. We present a protocol for two techniques for explaining support vector machine predictions with exact Shapley value computation. We detail the application of these algorithms and provide ready-to-use Python scripts and custom code. The final output of the protocol includes quantitative feature analysis and mapping of important features for visualization. For complete details on the use and execution of this protocol, please refer to Feldmann and Bajorath and Mastropietro et al..

Authors

  • Andrea Mastropietro
    Department of Computer, Control and Management Engineering Antonio Ruberti (DIAG) Sapienza University of Rome, 00185 Rome, Italy; Department of Life Science Informatics and Data Science, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universität, Friedrich-Hirzebruch-Allee 5/6, 53115 Bonn, Germany. Electronic address: mastropietro@diag.uniroma1.it.
  • Jürgen Bajorath
    Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universität, Dahlmannstr. 2, D-53113 Bonn, Germany.