skills.rest
Starlitnightly
StarlitnightlyCOMMUNITY
Explore all skills by this author →
GitHub

Single-trajectory analysis

Reproduce and extend single-trajectory analysis workflows across PAGA, Palantir, VIA, and scVelo.

1.2k|145|Updated Mar 22, 2021
Search Tags:#bioinformatics#Palantir#single-cell trajectory#RNA velocity#pseudotime#omicverse#PAGA#cell differentiation#VIA
One-click install
npx skills add https://github.com/Starlitnightly/omicverse --skill single-trajectory-analysis
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Single-trajectory analysis
Source: https://github.com/Starlitnightly/omicverse/tree/main/.claude/skills/single-trajectory
Command: npx skills add https://github.com/Starlitnightly/omicverse --skill single-trajectory-analysis

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires omicverse, scanpy, scvelo, palantir, via, cytotrace, numpy, pandas, matplotlib, and includes references (resource) components.

What problem does it solves? Inferring and visualizing developmental trajectories from single-cell data is crucial for understanding cell differentiation, but it involves complex algorithms like PAGA, Palantir, and RNA velocity. This Skill provides a comprehensive guide to these trajectory analysis workflows, simplifying the process of uncovering cellular fate.

Core Features & Use Cases

  • Graph-Based Trajectory Inference: Infer cell lineage trajectories using PAGA, Palantir, and VIA.
  • RNA Velocity Coupling: Integrate RNA velocity to refine lineage directionality and pseudotime.
  • Fate Scoring: Quantify differentiation potential, branch probabilities, and fate bias.
  • Downstream Analysis: Integrate CytoTRACE differentiation potential and aggregate metacell trajectories for robustness.
  • Use Case: Analyze a single-cell dataset of T-cell development, infer trajectories using VIA, integrate RNA velocity for directional insights, and then quantify the differentiation potential of different T-cell subsets.

Quick Start

Perform trajectory analysis on my single-cell data using VIA, integrate RNA velocity, and visualize the pseudotime and lineage paths.

Frequently Asked Questions about Single-trajectory analysis

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

FAQPage Schema
How do I infer cell developmental trajectories from single-cell RNA-seq data?▼

Trajectory inference reconstructs cellular developmental paths by applying graph-based algorithms like PAGA, Palantir, or VIA to single-cell data. These methods build cell-state networks, identify root and terminal states, and compute pseudotime to order cells along differentiation paths, revealing lineage branching and fate decisions.

Can I integrate RNA velocity to determine cell differentiation direction?▼

Yes. RNA velocity from scVelo estimates directional momentum by comparing unspliced and spliced mRNA abundance, refining trajectory directionality and pseudotime accuracy. Coupling velocity with PAGA, Palantir, or VIA strengthens lineage inference and improves branch probability estimates in developmental workflows.

What's the workflow for analyzing T-cell differentiation using trajectory methods?▼

Preprocess T-cell scRNA-seq data through quality control, normalization, and HVG selection. Compute neighbors and embeddings, apply VIA or PAGA to infer trajectories, specify root and terminal T-cell states, integrate RNA velocity, then quantify fate probabilities and differentiation potential using CytoTRACE to characterize developmental branch bias.

How do I validate trajectory results across different inference methods?▼

Cross-method validation compares pseudotime, branch probabilities, and fate scores from PAGA, Palantir, and VIA on the same dataset. Consistency across methods confirms lineage topology and differentiation patterns, while discrepancies highlight algorithmic sensitivity and guide method selection for immune-cell or other specialized datasets.

Do I need batch correction before inferring trajectories from multi-sample single-cell data?▼

Yes. Batch correction during preprocessing ensures robust trajectory inference by removing technical variation before computing neighbors and embeddings. This step is critical for pooled immune-cell datasets or other multi-condition scRNA-seq studies to prevent batch effects from distorting lineage topology and pseudotime calculations.

What downstream analyses can I perform after trajectory inference?▼

After trajectory inference, export pseudotime and branch probabilities for gene expression dynamics, integrate fate-scoring metrics like CytoTRACE differentiation potential, aggregate metacell trajectories for robustness, and visualize lineage-specific gene programs to support functional annotation of developmental transitions.

Related Skills

Explore More Education & Research Skills→
ovachieverovachiever
52

scanpy

Analyze scRNA-seq data with Scanpy workflows for QC through trajectory inference.

Community
Advanced
chenyhvvvvchenyhvvvv
3

trajectory-pseudotime

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

Community
Advanced
omicverseomicverse
32

single-trajectory-analysis

Infer developmental trajectories and compute RNA velocity on single-cell AnnData objects.

Official
Advanced
StarlitnightlyStarlitnightly
13

omicverse-single-cell-trajectory-inference

Infer trajectories and summarize lineages on cluster-ready AnnData objects.

Community
Intermediate