trajectory-analysis

Reconstruct cell-state transitions and developmental trajectories from single-cell RNA-seq AnnData objects.

13|5|Updated May 4, 2026
One-click install
npx skills add https://github.com/awslabs/hcls-agent-skills --skill trajectory-analysis
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trajectory-analysis
Source: https://github.com/awslabs/hcls-agent-skills/tree/main/skills/trajectory-analysis
Command: npx skills add https://github.com/awslabs/hcls-agent-skills --skill trajectory-analysis

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires scvelo, cellrank, scanpy, numpy, and includes references (resource) components.

What problem does it solve?

This skill solves the complexity of inferring developmental paths and cell fate probabilities from single-cell RNA sequencing data, which is often hindered by noisy data and the need for specialized kinetic modeling.

Core Features & Use Cases

  • Trajectory Inference: Computes diffusion pseudotime and PAGA graphs to map cell-state transitions.
  • RNA Velocity & Fate Mapping: Uses scVelo and CellRank to predict future cell states and terminal differentiation outcomes.
  • Use Case: A researcher can use this to determine the differentiation trajectory of stem cells into mature lineages by analyzing spliced and unspliced mRNA ratios.

Quick Start

Use the trajectory-analysis skill to compute the diffusion pseudotime and visualize the cell lineage tree for the provided AnnData object.

Frequently Asked Questions about trajectory-analysis

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

FAQPage Schema
How do I reconstruct cell-state transitions from scRNA-seq data?

You can reconstruct cell-state transitions from scRNA-seq data by computing diffusion pseudotime and PAGA graphs on preprocessed AnnData objects to map continuous developmental trajectories.

How does RNA velocity predict cell fate probabilities in single-cell datasets?

RNA velocity predicts cell fate by analyzing spliced and unspliced mRNA ratios in scRNA-seq data, using scVelo and CellRank to model future cell states and terminal differentiation outcomes.

Do I need spliced and unspliced count layers to map single-cell trajectories?

Spliced and unspliced count layers are required for velocity-based trajectory mapping, but methods like diffusion pseudotime and PAGA only need preprocessed AnnData objects containing normalized expression data.

Can I use scanpy and cellrank together for single-cell trajectory inference?

Yes, this skill integrates scanpy and cellrank to compute trajectory inference, leveraging Markov-chain based fate mapping and diffusion pseudotime to visualize cell lineage trees.

What is the best way to determine stem cell differentiation trajectories into mature lineages?

The best way to determine stem cell differentiation trajectories is by applying RNA velocity and fate mapping to analyze kinetic mRNA ratios and infer terminal differentiation outcomes.

Why does my trajectory analysis require a preprocessed AnnData object?

Trajectory analysis requires a preprocessed AnnData object because the underlying methods depend on normalized expression data to accurately compute continuous cell-state transitions and developmental paths.