Data & ReproSingle-Cell & Spatial OmicsFreedomIntelligence/OpenClaw-Medical-SkillsData & Reproduction

bio-single-cell-batch-integration

Maintainer FreedomIntelligence · Last updated April 1, 2026

Integrate multiple scRNA-seq samples/batches using Harmony, scVI, Seurat anchors, and fastMNN. Remove technical variation while preserving biological differences. Use when integrating multiple scRNA-seq batches or datasets.

OpenClawNanoClawAnalysisReproductionbio-single-cell-batch-integration🧬 bioinformatics (gptomics bio-* suite)bioinformatics — single-cell & spatial omicsintegrate

Original source

FreedomIntelligence/OpenClaw-Medical-Skills

https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/bio-single-cell-batch-integration

Maintainer: FreedomIntelligence
License: MIT
Last updated: April 1, 2026

Skill Snapshot

Key Details From SKILL.md

2 min

Key Notes

Integrate multiple scRNA-seq datasets to remove batch effects while preserving biological variation.
merged <- merge(sample1, y = list(sample2, sample3), add.cell.ids = c('S1', 'S2', 'S3')).

Source Doc

Excerpt From SKILL.md

Tool Comparison

Tool	Speed	Scalability	Best For
Harmony	Fast	Good	Quick integration, most use cases
scVI	Moderate	Excellent	Large datasets, deep learning
Seurat CCA/RPCA	Moderate	Good	Conserved biology across batches
fastMNN	Fast	Good	MNN-based correction

Harmony (R/Python)

Goal: Remove batch effects from merged scRNA-seq datasets using Harmony's iterative correction of PCA embeddings.

Approach: Run PCA on merged data, iteratively adjust embeddings to mix batches while preserving biological variation, and use corrected embeddings for downstream analysis.

"Integrate my batches" → Merge samples, preprocess jointly, correct technical variation in the embedding space, and cluster on corrected coordinates.

R with Seurat

library(Seurat)
library(harmony)

Use cases

Use when integrating multiple scRNA-seq batches or datasets.

Not for

Do not rely on this catalog entry alone for installation or maintenance details.

Upstream Related Skills

single-cell/preprocessing - QC before integration
single-cell/clustering - Clustering after integration
single-cell/cell-annotation - Annotation after integration
single-cell/multimodal-integration - Multi-omic integration (different from batch)

Related skills

Back to directory

Data & ReproSingle-Cell & Spatial Omics

Arboreto

Arboreto is a computational library for inferring gene regulatory networks (GRNs) from gene expression data using paralleli.

Claude CodeOpenClawAnalysis

K-Dense-AI/claude-scientific-skillsView

Data & ReproSingle-Cell & Spatial Omics

bio-imaging-mass-cytometry-cell-segmentation

Cell segmentation from multiplexed tissue images. Covers deep learning (Cellpose, Mesmer) and classical approaches for nuclear and whole-cel…

OpenClawNanoClawAnalysis

FreedomIntelligence/OpenClaw-Medical-SkillsView

Data & ReproSingle-Cell & Spatial Omics

bio-read-qc-umi-processing

Extract, process, and deduplicate reads using Unique Molecular Identifiers (UMIs) with umi_tools. Use when library prep includes UMIs and ac…

OpenClawNanoClawAnalysis

FreedomIntelligence/OpenClaw-Medical-SkillsView

Data & ReproSingle-Cell & Spatial Omics

bio-single-cell-cell-annotation

Automated cell type annotation using reference-based methods including CellTypist, scPred, SingleR, and Azimuth for consistent, reproducible…

OpenClawNanoClawAnalysis

FreedomIntelligence/OpenClaw-Medical-SkillsView