Exploring the role of normalization and feature selection in microbiome disease classification pipelines
Overall, feature selection pipelines improved model focus and robustness via a massive reduction of the feature space. mRMR and LASSO emerged as the most effective methods across datasets.
Authors
- Francisco Ortuño (ORCID: https://orcid.org/0000-0001-7424-1753)
- Luis Javier Herrera (ORCID: https://orcid.org/0000-0003-3220-9389)
- Ignacio Rojas Ruiz
- Ignacio Garach Vélez
Institutions
- Universidad de Granada (ES)
Publication Details
- Journal
- GigaScience
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1093/gigascience/giaf096
- Citations
- 1
- Primary Topic
- Gene expression and cancer classification
- Type
- article
- Field-Weighted Citation Impact
- 0.81
Funders
- European Commission
- Ministerio de Ciencia e Innovación
- Universidad de Granada
- Consejería de Conocimiento, Investigación y Universidad, Junta de Andalucía
- Agencia Estatal de Investigación