Agent skills
bio-single-cell-markers-annota...

Agent skill

bio-single-cell-markers-annotation

Find marker genes and annotate cell types in single-cell RNA-seq using Seurat (R) and Scanpy (Python). Use for differential expression between clusters, identifying cluster-specific markers, scoring gene sets, and assigning cell type labels. Use when finding marker genes and annotating clusters.

View SKILL.md on GitHub Repository

Stars 2,009

Forks 275

Install this agent skill to your Project

npx add-skill https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/bio-single-cell-markers-annotation

SKILL.md

Version Compatibility

Reference examples tested with: DESeq2 1.42+, pandas 2.2+, scanpy 1.10+

Before using code patterns, verify installed versions match. If versions differ:

Python: pip show <package> then help(module.function) to check signatures
R: packageVersion('<pkg>') then ?function_name to verify parameters

If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying.

Marker Genes and Cell Type Annotation

Find differentially expressed genes between clusters and annotate cell types.

Scanpy (Python)

Goal: Identify cluster-specific marker genes, score gene sets, and annotate cell types using Scanpy.

Approach: Perform differential expression testing between clusters with Wilcoxon rank-sum, visualize markers with dot plots and heatmaps, and assign cell type labels manually.

"Find marker genes for each cluster" → Test each cluster against all others for differentially expressed genes and rank by statistical significance and fold change.

Required Imports

python

import scanpy as sc
import pandas as pd

Find Markers for All Clusters

python

# Find marker genes for each cluster vs all others
sc.tl.rank_genes_groups(adata, groupby='leiden', method='wilcoxon')

# View top markers
sc.pl.rank_genes_groups(adata, n_genes=10, sharey=False)

# Get results as DataFrame
markers = sc.get.rank_genes_groups_df(adata, group=None)
print(markers.head(20))

Marker Detection Methods

python

# Wilcoxon rank-sum test (default, recommended)
sc.tl.rank_genes_groups(adata, groupby='leiden', method='wilcoxon')

# t-test
sc.tl.rank_genes_groups(adata, groupby='leiden', method='t-test')

# Logistic regression
sc.tl.rank_genes_groups(adata, groupby='leiden', method='logreg')

Filter Markers

python

# Get markers with filters
markers = sc.get.rank_genes_groups_df(adata, group='0')
significant = markers[(markers['pvals_adj'] < 0.05) & (markers['logfoldchanges'] > 1)]
print(f'Cluster 0 significant markers: {len(significant)}')

# Filter all groups
sc.tl.filter_rank_genes_groups(adata, min_fold_change=1.5, min_in_group_fraction=0.25)

Compare Specific Clusters

python

# Find markers between two specific clusters
sc.tl.rank_genes_groups(adata, groupby='leiden', groups=['0'], reference='1', method='wilcoxon')
sc.pl.rank_genes_groups(adata, n_genes=10)

Visualize Marker Expression

python

# Dot plot of top markers per cluster
markers_to_plot = ['CD3D', 'CD8A', 'MS4A1', 'CD14', 'FCGR3A', 'NKG7']
sc.pl.dotplot(adata, var_names=markers_to_plot, groupby='leiden')

# Stacked violin
sc.pl.stacked_violin(adata, var_names=markers_to_plot, groupby='leiden')

# Heatmap
sc.pl.rank_genes_groups_heatmap(adata, n_genes=5, groupby='leiden')

# Matrix plot
sc.pl.matrixplot(adata, var_names=markers_to_plot, groupby='leiden')

Gene Set Scoring

python

# Score cells for gene set expression
t_cell_genes = ['CD3D', 'CD3E', 'CD4', 'CD8A', 'CD8B']
sc.tl.score_genes(adata, gene_list=t_cell_genes, score_name='T_cell_score')

# Visualize score
sc.pl.umap(adata, color='T_cell_score')

Cell Cycle Scoring

python

# Score cell cycle phases
s_genes = ['MCM5', 'PCNA', 'TYMS', 'FEN1', 'MCM2']  # S phase genes
g2m_genes = ['HMGB2', 'CDK1', 'NUSAP1', 'UBE2C', 'BIRC5']  # G2/M genes

sc.tl.score_genes_cell_cycle(adata, s_genes=s_genes, g2m_genes=g2m_genes)
sc.pl.umap(adata, color=['S_score', 'G2M_score', 'phase'])

Manual Cell Type Annotation

python

# Create annotation dictionary
cluster_annotations = {
    '0': 'CD4 T cells',
    '1': 'CD14 Monocytes',
    '2': 'B cells',
    '3': 'CD8 T cells',
    '4': 'NK cells',
    '5': 'FCGR3A Monocytes'
}

# Add annotations
adata.obs['cell_type'] = adata.obs['leiden'].map(cluster_annotations)

# Visualize
sc.pl.umap(adata, color='cell_type')

Export Markers

python

# Export all markers to CSV
markers = sc.get.rank_genes_groups_df(adata, group=None)
markers.to_csv('all_markers.csv', index=False)

# Export top markers per cluster
top_markers = markers.groupby('group').head(20)
top_markers.to_csv('top_markers.csv', index=False)

Seurat (R)

Goal: Identify cluster-specific marker genes, score gene modules, and annotate cell types using Seurat.

Approach: Run FindAllMarkers with Wilcoxon or MAST tests, visualize with FeaturePlot/DotPlot/DoHeatmap, and rename cluster identities with cell type labels.

Required Libraries

library(Seurat)
library(dplyr)

Find All Markers

# Find markers for all clusters
all_markers <- FindAllMarkers(seurat_obj, only.pos = TRUE, min.pct = 0.25, logfc.threshold = 0.25)

# View top markers per cluster
top_markers <- all_markers %>%
    group_by(cluster) %>%
    slice_max(n = 5, order_by = avg_log2FC)
print(top_markers)

Find Markers for Specific Cluster

# Markers for cluster 0 vs all others
cluster0_markers <- FindMarkers(seurat_obj, ident.1 = 0, min.pct = 0.25)
head(cluster0_markers)

Compare Two Clusters

# Find markers between two specific clusters
markers_0_vs_1 <- FindMarkers(seurat_obj, ident.1 = 0, ident.2 = 1, min.pct = 0.25)
head(markers_0_vs_1)

Marker Detection Methods

# Wilcoxon (default, fast)
markers <- FindMarkers(seurat_obj, ident.1 = 0, test.use = 'wilcox')

# MAST (recommended for DE)
markers <- FindMarkers(seurat_obj, ident.1 = 0, test.use = 'MAST')

# DESeq2
markers <- FindMarkers(seurat_obj, ident.1 = 0, test.use = 'DESeq2')

# Logistic regression
markers <- FindMarkers(seurat_obj, ident.1 = 0, test.use = 'LR')

Visualize Markers

# Feature plot on UMAP
FeaturePlot(seurat_obj, features = c('CD3D', 'MS4A1', 'CD14', 'NKG7'))

# Violin plot
VlnPlot(seurat_obj, features = c('CD3D', 'MS4A1', 'CD14'))

# Dot plot
markers_to_plot <- c('CD3D', 'CD8A', 'MS4A1', 'CD14', 'FCGR3A', 'NKG7')
DotPlot(seurat_obj, features = markers_to_plot) + RotatedAxis()

# Heatmap
top10 <- all_markers %>%
    group_by(cluster) %>%
    top_n(n = 10, wt = avg_log2FC)
DoHeatmap(seurat_obj, features = top10$gene)

Gene Module Scoring

# Score cells for gene set
t_cell_genes <- list(c('CD3D', 'CD3E', 'CD4', 'CD8A', 'CD8B'))
seurat_obj <- AddModuleScore(seurat_obj, features = t_cell_genes, name = 'T_cell_score')

# Visualize
FeaturePlot(seurat_obj, features = 'T_cell_score1')

Cell Cycle Scoring

# Built-in cell cycle genes
s.genes <- cc.genes$s.genes
g2m.genes <- cc.genes$g2m.genes

seurat_obj <- CellCycleScoring(seurat_obj, s.features = s.genes, g2m.features = g2m.genes)
DimPlot(seurat_obj, group.by = 'Phase')

Manual Cell Type Annotation

# Rename cluster identities
new_cluster_ids <- c(
    '0' = 'CD4 T cells',
    '1' = 'CD14 Monocytes',
    '2' = 'B cells',
    '3' = 'CD8 T cells',
    '4' = 'NK cells',
    '5' = 'FCGR3A Monocytes'
)

seurat_obj <- RenameIdents(seurat_obj, new_cluster_ids)
DimPlot(seurat_obj, reduction = 'umap', label = TRUE)

# Store in metadata
seurat_obj$cell_type <- Idents(seurat_obj)

Export Markers

# Export to CSV
write.csv(all_markers, file = 'all_markers.csv', row.names = FALSE)

# Export top markers
write.csv(top_markers, file = 'top_markers.csv', row.names = FALSE)

Common PBMC Markers

Cell Type	Markers
CD4 T cells	CD3D, CD4, IL7R
CD8 T cells	CD3D, CD8A, CD8B
B cells	MS4A1, CD79A, CD19
NK cells	NKG7, GNLY, NCAM1
CD14 Monocytes	CD14, LYZ, S100A8
FCGR3A Monocytes	FCGR3A, MS4A7
Dendritic cells	FCER1A, CST3
Platelets	PPBP, PF4

Method Comparison

Task	Scanpy	Seurat
All markers	`rank_genes_groups()`	`FindAllMarkers()`
Specific cluster	`rank_genes_groups(groups=['0'])`	`FindMarkers(ident.1=0)`
Two clusters	`rank_genes_groups(reference='1')`	`FindMarkers(ident.1=0, ident.2=1)`
Gene scoring	`score_genes()`	`AddModuleScore()`
Dot plot	`sc.pl.dotplot()`	`DotPlot()`

Related Skills

clustering - Must cluster before finding markers
preprocessing - Data must be normalized
data-io - Export annotated data

Maintainer

FreedomIntelligence Core maintainer

Source details

Full Name: FreedomIntelligence/OpenClaw-Medical-Skills
Branch: main
Path in repo: skills/bio-single-cell-markers-annotation
Topics: claude-code skills openclaw awesome clawhub openclaw-skills medical nanoclaw

Featured Tools

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

FreedomIntelligence/OpenClaw-Medical-Skills

vcf-annotator

Annotate VCF variants with VEP, ClinVar, gnomAD frequencies, and ancestry-aware context. Generates prioritised variant reports.

2,009 275

Explore

FreedomIntelligence/OpenClaw-Medical-Skills

chemist-analyst

Analyzes events through chemistry lens using molecular structure, reaction mechanisms, thermodynamics, kinetics, and analytical techniques (spectroscopy, chromatography, mass spectrometry). Provides insights on chemical processes, material properties, reaction pathways, synthesis, and analytical methods. Use when: Chemical reactions, material analysis, synthesis planning, process optimization, environmental chemistry. Evaluates: Molecular structure, reaction mechanisms, yield, selectivity, safety, environmental impact.

2,009 275

Explore

FreedomIntelligence/OpenClaw-Medical-Skills

bio-alignment-io

Read, write, and convert multiple sequence alignment files using Biopython Bio.AlignIO. Supports Clustal, PHYLIP, Stockholm, FASTA, Nexus, and other alignment formats for phylogenetics and conservation analysis. Use when reading, writing, or converting alignment file formats.

2,009 275

Explore

FreedomIntelligence/OpenClaw-Medical-Skills

sleep-analyzer

分析睡眠数据、识别睡眠模式、评估睡眠质量，并提供个性化睡眠改善建议。支持与其他健康数据的关联分析。

2,009 275

Explore

FreedomIntelligence/OpenClaw-Medical-Skills

metabolomics-workbench-database

Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery.

2,009 275

Explore

FreedomIntelligence/OpenClaw-Medical-Skills

bio-hi-c-analysis-matrix-operations

Balance, normalize, and transform Hi-C contact matrices using cooler and cooltools. Apply iterative correction (ICE), compute expected values, and generate observed/expected matrices. Use when normalizing or transforming Hi-C matrices.

2,009 275

Explore

Didn't find tool you were looking for?

Search AI Tools

Install this agent skill to your Project

SKILL.md

Version Compatibility

Marker Genes and Cell Type Annotation

Scanpy (Python)

Required Imports

Find Markers for All Clusters

Marker Detection Methods

Filter Markers

Compare Specific Clusters

Visualize Marker Expression

Gene Set Scoring

Cell Cycle Scoring

Manual Cell Type Annotation

Export Markers

Seurat (R)

Required Libraries

Find All Markers

Find Markers for Specific Cluster

Compare Two Clusters

Marker Detection Methods

Visualize Markers

Gene Module Scoring

Cell Cycle Scoring

Manual Cell Type Annotation

Export Markers

Common PBMC Markers

Method Comparison

Related Skills

Recommended Agent Skills

vcf-annotator

chemist-analyst

bio-alignment-io

sleep-analyzer

metabolomics-workbench-database

bio-hi-c-analysis-matrix-operations