trajectory-pseudotime

Infer cell developmental trajectories and pseudotime ordering from gene expression data.

3|Updated Apr 3, 2026
One-click install
npx skills add https://github.com/chenyhvvvv/STAT-agent --skill trajectory-pseudotime
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trajectory-pseudotime
Source: https://github.com/chenyhvvvv/STAT-agent/tree/main/stat_agent/skills/trajectory-palantir-dpt
Command: npx skills add https://github.com/chenyhvvvv/STAT-agent --skill trajectory-pseudotime

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Infer developmental trajectories and pseudotime ordering from gene expression data, enabling researchers to map lineage relationships and differentiation dynamics.

Core Features & Use Cases

  • Palantir-based trajectory analysis with diffusion maps, entropy, and fate probabilities.
  • DPT (Diffusion Pseudotime) for lightweight, fast trajectory estimation.
  • Root-cell guidance and both linear and branching trajectory workflows; outputs stored in adata.obs and adata.uns.

Quick Start

Load your slice data, choose a root cell type, and run Palantir or DPT to compute pseudotime.

Frequently Asked Questions about trajectory-pseudotime

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I infer cellular trajectories and pseudotime from single-cell gene expression data?

To infer cellular trajectories and pseudotime, this skill applies Palantir and DPT algorithms to single-slice gene expression datasets, outputting pseudotime ordering, entropy, and fate probabilities to map lineage relationships.

What is the difference between Palantir and DPT for trajectory analysis?

Palantir provides detailed trajectory analysis using diffusion maps, entropy, and fate probabilities for branching trajectories, whereas DPT offers a lightweight, fast diffusion pseudotime estimation for simpler linear trajectory workflows.

Do I need to preprocess my single-cell data with Scanpy before trajectory analysis?

Yes, preprocessing single-cell data with Scanpy is required before running trajectory analysis. The skill relies on preprocessed gene expression data to accurately compute pseudotime, entropy, and fate probabilities.

Can I specify a root cell type to guide pseudotime ordering?

Yes, you can guide pseudotime ordering by providing an optional root-cell hint or cell-type label. This helps direct the trajectory inference when calculating pseudotime and fate probabilities in your single-slice dataset.

Where are trajectory and pseudotime results stored after running Palantir or DPT?

After running Palantir or DPT, trajectory and pseudotime results are stored directly in adata.obs and adata.uns, making them immediately available for downstream visualization and analysis of cellular differentiation dynamics.

Does this trajectory analysis support branching lineages or only linear progressions?

This trajectory analysis supports both branching and linear trajectories. Palantir handles branching lineages by calculating fate probabilities for different cell states, while DPT provides fast pseudotime estimation for linear progressions.