DELVE: feature selection for preserving biological trajectories in single-cell data

Jolene S Ranek; Wayne Stallaert; J Justin Milner; Margaret Redick; Samuel C Wolff; Adriana S Beltran; Natalie Stanley; Jeremy E Purvis

doi:10.1038/s41467-024-46773-z

DELVE: feature selection for preserving biological trajectories in single-cell data

Nat Commun. 2024 Mar 29;15(1):2765. doi: 10.1038/s41467-024-46773-z.

Authors

Jolene S Ranek^{1

2}, Wayne Stallaert³, J Justin Milner^{4

5}, Margaret Redick^{1

2}, Samuel C Wolff^{1

2}, Adriana S Beltran^{1

6}, Natalie Stanley^{7

8}, Jeremy E Purvis^{9

10}

Affiliations

¹ Department of Genetics, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.
² Computational Medicine Program, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.
³ Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, PA, USA.
⁴ Department of Microbiology and Immunology, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.
⁵ Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill School of Medicine, Chapel Hill, NC, USA.
⁶ Human Pluripotent Cell Core, University of North Carolina at Chapel Hill School of Medicine, Chapel Hill, NC, USA.
⁷ Computational Medicine Program, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA. [email protected].
⁸ Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA. [email protected].
⁹ Department of Genetics, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA. [email protected].
¹⁰ Computational Medicine Program, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA. [email protected].

Abstract

Single-cell technologies can measure the expression of thousands of molecular features in individual cells undergoing dynamic biological processes. While examining cells along a computationally-ordered pseudotime trajectory can reveal how changes in gene or protein expression impact cell fate, identifying such dynamic features is challenging due to the inherent noise in single-cell data. Here, we present DELVE, an unsupervised feature selection method for identifying a representative subset of molecular features which robustly recapitulate cellular trajectories. In contrast to previous work, DELVE uses a bottom-up approach to mitigate the effects of confounding sources of variation, and instead models cell states from dynamic gene or protein modules based on core regulatory complexes. Using simulations, single-cell RNA sequencing, and iterative immunofluorescence imaging data in the context of cell cycle and cellular differentiation, we demonstrate how DELVE selects features that better define cell-types and cell-type transitions. DELVE is available as an open-source python package: https://github.com/jranek/delve .

MeSH terms

Cell Cycle / genetics
Cell Differentiation
Gene Expression Profiling* / methods
Sequence Analysis, RNA / methods
Single-Cell Analysis / methods
Software*

Abstract

MeSH terms

Grants and funding