Protocol to explain support vector machine predictions via exact Shapley value computation
Summary: 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 Shaple...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-06-01
|
| Series: | STAR Protocols |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666166724001758 |
| _version_ | 1797213318366101504 |
|---|---|
| author | Andrea Mastropietro Jürgen Bajorath |
| author_facet | Andrea Mastropietro Jürgen Bajorath |
| author_sort | Andrea Mastropietro |
| collection | DOAJ |
| description | Summary: 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 Bajorath1 and Mastropietro et al.2 : Publisher’s note: Undertaking any experimental protocol requires adherence to local institutional guidelines for laboratory safety and ethics. |
| first_indexed | 2024-04-24T10:56:22Z |
| format | Article |
| id | doaj.art-6cb2a314e5e54833934045de7b05a70c |
| institution | Directory Open Access Journal |
| issn | 2666-1667 |
| language | English |
| last_indexed | 2024-04-24T10:56:22Z |
| publishDate | 2024-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | STAR Protocols |
| spelling | doaj.art-6cb2a314e5e54833934045de7b05a70c2024-04-12T04:46:02ZengElsevierSTAR Protocols2666-16672024-06-0152103010Protocol to explain support vector machine predictions via exact Shapley value computationAndrea Mastropietro0Jürgen Bajorath1Deparment of Computer, Control and Management Engineering “Antonio Ruberti”, Sapienza University of Rome, Via Ariosto 25, 00185 Rome, Italy; Corresponding authorDepartment 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; Lamarr Institute for Machine Learning and Artificial Intelligence, Friedrich-Hirzebruch-Allee 5/6, 53115 Bonn, Germany; Corresponding authorSummary: 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 Bajorath1 and Mastropietro et al.2 : Publisher’s note: Undertaking any experimental protocol requires adherence to local institutional guidelines for laboratory safety and ethics.http://www.sciencedirect.com/science/article/pii/S2666166724001758BioinformaticsChemistryComputer sciences |
| spellingShingle | Andrea Mastropietro Jürgen Bajorath Protocol to explain support vector machine predictions via exact Shapley value computation STAR Protocols Bioinformatics Chemistry Computer sciences |
| title | Protocol to explain support vector machine predictions via exact Shapley value computation |
| title_full | Protocol to explain support vector machine predictions via exact Shapley value computation |
| title_fullStr | Protocol to explain support vector machine predictions via exact Shapley value computation |
| title_full_unstemmed | Protocol to explain support vector machine predictions via exact Shapley value computation |
| title_short | Protocol to explain support vector machine predictions via exact Shapley value computation |
| title_sort | protocol to explain support vector machine predictions via exact shapley value computation |
| topic | Bioinformatics Chemistry Computer sciences |
| url | http://www.sciencedirect.com/science/article/pii/S2666166724001758 |
| work_keys_str_mv | AT andreamastropietro protocoltoexplainsupportvectormachinepredictionsviaexactshapleyvaluecomputation AT jurgenbajorath protocoltoexplainsupportvectormachinepredictionsviaexactshapleyvaluecomputation |