Supervised discovery of interpretable gene programs from single-cell data

• Verfasst von: Kunes, Russell Z. [VerfasserIn]
• Verfasst von: Walle, Thomas [VerfasserIn]
• Verfasst von: Land, Max [VerfasserIn]
• Verfasst von: Nawy, Tal [VerfasserIn]
• Verfasst von: Pe’er, Dana [VerfasserIn]
• Titel: Supervised discovery of interpretable gene programs from single-cell data
• Verf.angabe: Russell Z. Kunes, Thomas Walle, Max Land, Tal Nawy & Dana Pe’er
• Jahr: 2024
• Umfang: 40 S.
• Fussnoten: Online veröffentlicht: 21. September 2023 ; Gesehen am 24.02.2025
• Titel Quelle: Enthalten in: Nature biotechnology
• Ort Quelle: New York, NY : Springer Nature, 1996
• Jahr Quelle: 2024
• Band/Heft Quelle: 42(2024), 7 vom: Sept., Seite 1084-1095
• ISSN Quelle: 1546-1696
• DOI: doi:10.1038/s41587-023-01940-3
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 191842618X

Abstract

Abstract - - Factor analysis decomposes single-cell gene expression data into a minimal set of gene programs that correspond to processes executed by cells in a sample. However, matrix factorization methods are prone to technical artifacts and poor factor interpretability. We address these concerns with Spectra, an algorithm that combines user-provided gene programs with the detection of novel programs that together best explain expression covariation. Spectra incorporates existing gene sets and cell-type labels as prior biological information, explicitly models cell type and represents input gene sets as a gene-gene knowledge graph using a penalty function to guide factorization toward the input graph. We show that Spectra outperforms existing approaches in challenging tumor immune contexts, as it finds factors that change under immune checkpoint therapy, disentangles the highly correlated features of CD8 - + - T cell tumor reactivity and exhaustion, finds a program that explains continuous macrophage state changes under therapy and identifies cell-type-specific immune metabolic programs.