Preface
I How sclet Thinks: State, Provenance, and Navigation
1 State-Aware Analysis Contract
2 Automation & Provenance Logs
II From Data to Discovery: Analysis Mainlines
3 Data Ingress and Object Interoperability
- 3.1 Seurat and SCE Conversion
- 3.2 AnnData (h5ad)
4 Recommended usage
- 4.1 For end users
- 4.2 For pipeline authors
5 Developer design notes
6 Core Single-Cell Workflow
7 Integration and Batch Correction
8 Cell Identity and Reference Mapping
9 Cell Fate and Dynamic Processes
10 Program, Regulon, and Mechanistic Interpretation
11 Differential Analysis and Functional Interpretation
12 Cell-Cell Communication and Microenvironment Interaction
13 State Priority and Perturbation Sensitivity
14 Spatial Context and Niche Analysis
15 Multimodal Expansion
III Specialized Techniques and Reference
16 Enhanced Visualization
17 Fate probability on embedding
18 Terminal state assignments
19 Lineage driver trends
20 Velocity latent time
21 Metacells with SuperCell
- 21.1 RunSuperCell
- 21.2 Estimate SuperCell Purity
22 Milo: Differential Abundance
23 Phenotype Association
- 23.1 A practical pattern
- 23.2 What gets recorded
24 Interactive Data Exploration
- 24.1 Launch Explorer
- 24.2 Customization
25 SVP: Gene Set Activity in Spatial and Single-Cell Data
26 AI Copilot & Evidence Governance
- 26.1 sclet_copilot: An AI That Understands Your Objects
- 26.2 AuditAnalysisChain: Cross-Chain Error Control
References

sclet: A Lightweight Toolkit for Single-Cell Data Analysis

17 Fate probability on embedding

plot_fate_probability(sce, fate = 1, reduction = “UMAP”)