sc-pseudotime

name	sc-pseudotime
description	Single-cell pseudotime and lineage inference after clustering, with DPT, Palantir, VIA, CellRank, or Slingshot plus post-hoc trajectory gene ranking.
version	0.5.0
author	OmicsClaw
license	MIT
tags	["singlecell","pseudotime","trajectory","dpt","palantir","via","cellrank","slingshot"]
metadata	{"omicsclaw":{"domain":"singlecell","allowed_extra_flags":["--method","--cluster-key","--use-rep","--root-cluster","--root-cell","--end-clusters","--n-neighbors","--n-pcs","--n-dcs","--n-genes","--corr-method","--palantir-knn","--palantir-n-components","--palantir-num-waypoints","--palantir-max-iterations","--palantir-seed","--via-knn","--via-seed","--cellrank-n-states","--cellrank-schur-components","--cellrank-frac-to-keep","--cellrank-use-velocity","--r-enhanced"],"param_hints":{"dpt":"[Truncated]","palantir":"[Truncated]","via":"[Truncated]","cellrank":"[Truncated]","slingshot_r":"[Truncated]","monocle3_r":"[Truncated]"},"saves_h5ad":true,"requires_preprocessed":true,"trigger_keywords":["pseudotime","trajectory","lineage","diffusion pseudotime","palantir","via","cellrank","monocle3","slingshot"]}}

Single-Cell Pseudotime

What This Skill Does

sc-pseudotime is the trajectory step after clustering. It takes a normalized, cluster-labeled AnnData object, picks a start state, infers a trajectory, then ranks genes associated with that trajectory.

This skill answers questions like:

• which cluster should be treated as the start of a biological transition
• how cells order along a continuous trajectory
• which genes change most strongly along that ordering
• whether the method also supports branch or fate information

What Should Usually Come Before It

• sc-preprocessing
• if needed, sc-batch-integration
• sc-clustering
• optionally sc-cell-annotation if the user wants to define the start state by biology instead of just cluster number

If the user only says “do pseudotime”, the first thing to explain is:

• pseudotime needs a biologically defensible start state
• pseudotime should usually use the same representation that drove clustering or integration

Matrix / State Requirements

• X must represent normalized_expression
• a cluster or label column must already exist in adata.obs
• at least one trajectory representation must exist; the current wrapper defaults to X_umap when it is already present, otherwise it falls back to integrated or PCA embeddings such as X_harmony, X_scvi, X_scanvi, X_scanorama, or X_pca
• layers["counts"] may still exist, but trajectory-gene ranking is performed on normalized adata.X

Public Methods

1. dpt
2. palantir
3. via
4. cellrank
5. slingshot_r
6. monocle3_r

Beginner-Friendly Method Summary

Method	Best first use	What it adds
dpt