Pseudotime Trajectory Viz

Pseudotime Trajectory Visualization

Visualize single-cell developmental trajectories showing cellular differentiation processes using pseudotime analysis.

When to Use

Key Features

Dependencies

Optional:

Example Usage

See ## Usage above for related details.

cd "20260318/scientific-skills/Data Analytics/pseudotime-trajectory-viz"
python -m py_compile scripts/main.py
python scripts/main.py --help

Example run plan: 1. Confirm the user input, output path, and any required config values. 2. Edit the in-file CONFIG block or documented parameters if the script uses fixed settings. 3. Run python scripts/main.py with the validated inputs. 4. Review the generated output and return the final artifact with any assumptions called out.

Implementation Details

See ## Workflow above for related details.

Quick Check

Use this command to verify that the packaged script entry point can be parsed before deeper execution.

python -m py_compile scripts/main.py

Audit-Ready Commands

Use these concrete commands for validation. They are intentionally self-contained and avoid placeholder paths.

python -m py_compile scripts/main.py
python scripts/main.py --help
python scripts/main.py --input "Audit validation sample with explicit symptoms, history, assessment, and next-step plan." --format json

Workflow

1. Confirm the user objective, required inputs, and non-negotiable constraints before doing detailed work. 2. Validate that the request matches the documented scope and stop early if the task would require unsupported assumptions. 3. Use the packaged script path or the documented reasoning path with only the inputs that are actually available. 4. Return a structured result that separates assumptions, deliverables, risks, and unresolved items. 5. If execution fails or inputs are incomplete, switch to the fallback path and state exactly what blocked full completion.

Function

Technical Difficulty

High - Requires understanding of single-cell analysis, dimensionality reduction, trajectory inference algorithms, and Python visualization libraries.

Usage

Basic trajectory analysis from AnnData file
python scripts/main.py --input data.h5ad --output ./results
Specify starting cells and lineage inference method
python scripts/main.py --input data.h5ad --start-cell stem_cell_cluster --method diffusion --output ./results
Visualize specific gene expression along trajectories
python scripts/main.py --input data.h5ad --genes SOX2,OCT4,NANOG --plot-genes --output ./results
Full analysis with custom parameters
python scripts/main.py --input data.h5ad \
    --embedding umap \
    --method slingshot \
    --start-cell-type progenitor \
    --n-lineages 3 \
    --genes MARKER1,MARKER2,MARKER3 \
    --output ./results \
    --format pdf

Parameters

| Parameter | Type | Default | Description | |-----------|------|---------|-------------| | --input | path | required | Input AnnData (.h5ad) file path | | --output | path | ./trajectory_output | Output directory for results | | --embedding | enum | umap | Embedding for visualization: umap, tsne, pca, diffmap | | --method | enum | diffusion | Trajectory inference: diffusion, slingshot, paga, palantir | | --start-cell | string | auto | Root cell ID or cluster name for trajectory origin | | --start-cell-type | string | - | Cell type annotation to use as starting point | | --n-lineages | int | auto | Number of expected lineage branches | | --cluster-key | string | leiden | AnnData obs key for cell clusters | | --cell-type-key | string | cell_type | AnnData obs key for cell type annotations | | --genes | string | - | Comma-separated gene names to plot along pseudotime | | --plot-genes | flag | false | Generate gene expression heatmaps along trajectories | | --plot-branch | flag | true | Show lineage branch probabilities | | --format | enum | png | Output format: png, pdf, svg | | --dpi | int | 300 | Figure resolution | | --n-pcs | int | 30 | Number of principal components for analysis | | --n-neighbors | int | 15 | Number of neighbors for graph construction | | --diffmap-components | int | 5 | Number of diffusion components to compute |

Input Format

Required AnnData (.h5ad) structure:

AnnData object with n_obs × n_vars = n_cells × n_genes
    obs: 'leiden', 'cell_type'  # Cluster and cell type annotations
    var: 'highly_variable'       # Highly variable gene marker
    obsm: 'X_umap', 'X_pca'      # Pre-computed embeddings (optional)
    layers: 'spliced', 'unspliced'  # For RNA velocity (optional)

Output Files

output_directory/
├── trajectory_plot.{format}          # Main trajectory visualization
├── pseudotime_distribution.{format}  # Pseudotime value distribution
├── lineage_tree.{format}             # Branching lineage structure
├── gene_expression_heatmap.{format}  # Gene dynamics heatmap (if --plot-genes)
├── gene_trends/
│   ├── {gene_name}_trend.{format}    # Individual gene expression trends
│   └── ...
├── pseudotime_values.csv             # Cell-level pseudotime values
├── lineage_assignments.csv           # Cell lineage assignments
└── analysis_report.json              # Analysis parameters and statistics

Output Format Example

analysis_report.json

{
  "analysis_date": "2026-02-06T06:00:00",
  "method": "diffusion",
  "n_cells": 5000,
  "n_lineages": 3,
  "root_cell": "cell_1234",
  "pseudotime_range": [0.0, 1.0],
  "lineages": {
    "lineage_1": {
      "cell_count": 1500,
      "terminal_state": "mature_type_A",
      "mean_pseudotime": 0.75
    },
    "lineage_2": {
      "cell_count": 1200,
      "terminal_state": "mature_type_B",
      "mean_pseudotime": 0.68
    }
  }
}

pseudotime_values.csv

cell_id,cluster,cell_type,pseudotime,lineage,branch_probability
cell_001,0,progenitor,0.05,lineage_1,0.95
cell_002,1,intermediate,0.42,lineage_1,0.88
...

Implementation Notes

1. Preprocessing: Assumes input data is already normalized and log-transformed 2. Root Detection: If start cell not specified, uses cell cycle or marker gene expression to infer progenitors 3. Diffusion Pseudotime: Default method using diffusion maps for robust trajectory inference 4. Palantir: Used for soft lineage assignments and fate probability estimation 5. Memory: Large datasets (>50k cells) may require 16GB+ RAM

Methods

Diffusion Pseudotime (DPT)

Slingshot

PAGA (Partition-based Graph Abstraction)

Palantir

Limitations

Safety & Best Practices

Example Workflow

Preprocess data with scanpy (before using this tool)
import scanpy as sc
adata = sc.read_h5ad('raw_data.h5ad')
sc.pp.normalize_total(adata)
sc.pp.log1p(adata)
sc.pp.highly_variable_genes(adata, n_top_genes=2000)
sc.pp.scale(adata)
sc.tl.pca(adata)
sc.pp.neighbors(adata)
sc.tl.umap(adata)
sc.tl.leiden(adata)
adata.write('data.h5ad')
Then run this skill
python scripts/main.py --input data.h5ad --start-cell-type progenitor

References

Version

Risk Assessment

| Risk Indicator | Assessment | Level | |----------------|------------|-------| | Code Execution | Python/R scripts executed locally | Medium | | Network Access | No external API calls | Low | | File System Access | Read input files, write output files | Medium | | Instruction Tampering | Standard prompt guidelines | Low | | Data Exposure | Output files saved to workspace | Low |

Security Checklist

Prerequisites

Python dependencies
pip install -r requirements.txt

Evaluation Criteria

Success Metrics

Test Cases

Lifecycle Status

Output Requirements

Every final response should make these items explicit when they are relevant:

Error Handling

Input Validation

This skill accepts requests that match the documented purpose of pseudotime-trajectory-viz and include enough context to complete the workflow safely.

Do not continue the workflow when the request is out of scope, missing a critical input, or would require unsupported assumptions. Instead respond:

> pseudotime-trajectory-viz only handles its documented workflow. Please provide the missing required inputs or switch to a more suitable skill.

Response Template

Use the following fixed structure for non-trivial requests:

1. Objective 2. Inputs Received 3. Assumptions 4. Workflow 5. Deliverable 6. Risks and Limits 7. Next Checks

If the request is simple, you may compress the structure, but still keep assumptions and limits explicit when they affect correctness.

Inputs to Collect

Output Contract

Validation and Safety Rules

Basic trajectory analysis from AnnData file
python scripts/main.py --input data.h5ad --output ./results
Specify starting cells and lineage inference method
python scripts/main.py --input data.h5ad --start-cell stem_cell_cluster --method diffusion --output ./results
Visualize specific gene expression along trajectories
python scripts/main.py --input data.h5ad --genes SOX2,OCT4,NANOG --plot-genes --output ./results
Full analysis with custom parameters
python scripts/main.py --input data.h5ad \
    --embedding umap \
    --method slingshot \
    --start-cell-type progenitor \
    --n-lineages 3 \
    --genes MARKER1,MARKER2,MARKER3 \
    --output ./results \
    --format pdf

Python dependencies
pip install -r requirements.txt