An interpretable machine learning pipeline based on transcriptomics predicts phenotypes of lupus patients.

Autor:	Leventhal EL; AMPEL BioSolutions LLC, and the RILITE Research Institute, Charlottesville, VA 22902, USA., Daamen AR; AMPEL BioSolutions LLC, and the RILITE Research Institute, Charlottesville, VA 22902, USA., Grammer AC; AMPEL BioSolutions LLC, and the RILITE Research Institute, Charlottesville, VA 22902, USA., Lipsky PE; AMPEL BioSolutions LLC, and the RILITE Research Institute, Charlottesville, VA 22902, USA.
Jazyk:	angličtina
Zdroj:	IScience [iScience] 2023 Sep 25; Vol. 26 (10), pp. 108042. Date of Electronic Publication: 2023 Sep 25 (Print Publication: 2023).
DOI:	10.1016/j.isci.2023.108042
Abstrakt:	Machine learning (ML) has the potential to identify subsets of patients with distinct phenotypes from gene expression data. However, phenotype prediction using ML has often relied on identifying important genes without a systems biology context. To address this, we created an interpretable ML approach based on blood transcriptomics to predict phenotype in systemic lupus erythematosus (SLE), a heterogeneous autoimmune disease. We employed a sequential grouped feature importance algorithm to assess the performance of gene sets, including immune and metabolic pathways and cell types, known to be abnormal in SLE in predicting disease activity and organ involvement. Gene sets related to interferon, tumor necrosis factor, the mitoribosome, and T cell activation were the best predictors of phenotype with excellent performance. These results suggest potential relationships between the molecular pathways identified in each model and manifestations of SLE. This ML approach to phenotype prediction can be applied to other diseases and tissues. Competing Interests: The authors declare that they have no conflict of interest. (© 2023 The Author(s).)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu