AR
数据与复现
Arboreto
Arboreto is a computational library for inferring gene regulatory networks (GRNs) from gene expression data using parall…
K-Dense-AI/claude-scientific-skills查看
数据与复现
BI
bio-single-cell-batch-integration
维护者 FreedomIntelligence · 最近更新 2026年4月1日
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.
原始来源
FreedomIntelligence/OpenClaw-Medical-Skills
https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/bio-single-cell-batch-integration
- 维护者
- FreedomIntelligence
- 许可
- MIT
- 最近更新
- 2026年4月1日
技能摘要
来自 SKILL.md 的关键信息
核心说明
- 整合 multiple scRNA-seq 数据集s to remove batch effects while preserving biological variation。
- merged <- merge(sample1，y = list(sample2，sample3)，add.cell.ids = c('S1'，'S2'，'S3'))。
原始文档
SKILL.md 摘录
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)
适用场景
- 适合在integrating multiple scRNA-seq batches 或 数据集s时使用。
不适用场景
- Do not rely on this catalog entry alone ，用于 installation 或 maintenance details。
上游相关技能
- 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)
相关技能
相关技能
Cell segmentation from multiplexed tissue images. Covers deep learning (Cellpose, Mesmer) and classical approaches for n…
FreedomIntelligence/OpenClaw-Medical-Skills查看
BI
Extract, process, and deduplicate reads using Unique Molecular Identifiers (UMIs) with umi_tools. Use when library prep…
FreedomIntelligence/OpenClaw-Medical-Skills查看
Automated cell type annotation using reference-based methods including CellTypist, scPred, SingleR, and Azimuth for cons…
FreedomIntelligence/OpenClaw-Medical-Skills查看