Protocol for assessing distances in pathway space for classifier feature sets from machine learning methods
As genes tend to be co-regulated as gene modules, feature selection in machine learning (ML) on gene expression data can be challenged by the complexity of gene regulation. Here, we present a protocol for reconciling differences in classifier features identified using different ML approaches. We describe steps for loading the PathwaySpace R package, preparing input for analysis, and creating density plots of gene sets. We then detail procedures for testing whether apparently distinct feature sets are related in pathway space. For complete details on the use and execution of this protocol, please refer to Ellrott et al.<sup>1</sup>.
Authors
- Jean C. Zenklusen (ORCID: https://orcid.org/0000-0002-9489-1873)
- Christopher C. Benz (ORCID: https://orcid.org/0000-0001-5479-4641)
- Vinicius S Chagas
- Peter W. Laird (ORCID: https://orcid.org/0000-0001-9117-3641)
- Joshua M. Stuart (ORCID: https://orcid.org/0000-0002-2171-565X)
- Andrew D. Cherniack (ORCID: https://orcid.org/0000-0003-0470-0111)
- Jordan Lee (ORCID: https://orcid.org/0000-0002-0983-0495)
- Kyle Ellrott (ORCID: https://orcid.org/0000-0002-6573-5900)
- Christopher K. Wong
- Christina Yau (ORCID: https://orcid.org/0000-0002-1937-0859)
- Bahar Tercan (ORCID: https://orcid.org/0000-0002-5332-264X)
- Jasleen Grewal (ORCID: https://orcid.org/0000-0001-7213-5930)
- Steven J.M. Jones (ORCID: https://orcid.org/0000-0003-3394-2208)
- B. Karlberg
- A. Gordon Robertson
- Victor H Apolonio
Institutions
- Broad Institute (US)
- Universidade Tecnológica Federal do Paraná (BR)
- Van Andel Institute (US)
- Buck Institute for Research on Aging (US)
- Oregon Health & Science University (US)
- University of California, Santa Cruz (US)
- Institute for Systems Biology (US)
- Dana-Farber Cancer Institute (US)
- Canada's Michael Smith Genome Sciences Centre (CA)
- National Cancer Institute (US)
- Universidade Federal do Paraná (BR)
Publication Details
- Journal
- STAR Protocols
- Published
- 2025-03-18
- DOI
- https://doi.org/10.1016/j.xpro.2025.103681
- Primary Topic
- Machine Learning in Bioinformatics
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
- Fundação Araucária
- National Institutes of Health
- National Cancer Institute