Characterizing efficient feature selection for single-cell expression analysis

• Published in: Briefings in bioinformatics Vol. 25; no. 4
• Main Authors: Cho, Juok, Baik, Bukyung, Nguyen, Hai C T, Park, Daeui, Nam, Dougu
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 23.05.2024; Oxford Publishing Limited (England)
• Subjects: Algorithms; Benchmarks; Cluster Analysis; Clustering; Computational Biology - methods; Criteria; Discordance; Gene expression; Gene Expression Profiling - methods; Genes; Humans; Problem Solving Protocol; RNA-Seq - methods; Scientific visualization; Sequence Analysis, RNA - methods; Single-Cell Analysis - methods; Trajectory analysis; single-cell RNA-sequencing; trajectory analysis; clustering; feature selection

Abstract Unsupervised feature selection is a critical step for efficient and accurate analysis of single-cell RNA-seq data. Previous benchmarks used two different criteria to compare feature selection methods: (i) proportion of ground-truth marker genes included in the selected features and (ii) acc...