scDesign3

scDesign3 generates realistic single-cell and spatial omics data, including various cell states, experimental designs, and feature modalities, by learning interpretable parameters from real data.

Key Features:

• Unified probabilistic model: scDesign3 uses a unified probabilistic model for single-cell and spatial omics data.
• Biological parameter inference: scDesign3 infers biologically meaningful parameters from real data.
• Goodness-of-fit assessment: scDesign3 assesses the goodness-of-fit of inferred cell clusters, trajectories, and spatial locations.
• In silico control generation: scDesign3 generates in silico negative and positive controls for benchmarking computational tools.

Scientific Applications:

• Single-cell omics simulation: scDesign3 generates realistic single-cell omics data across various cell states and feature modalities.
• Spatial omics simulation: scDesign3 generates realistic spatial omics data with spatial locations.
• Computational tool benchmarking: scDesign3 provides in silico negative and positive controls for benchmarking computational tools.

Methodology:

scDesign3 learns interpretable parameters from real data using a unified probabilistic model for single-cell and spatial omics data.