数据与复现生物信息与基因组学FreedomIntelligence/OpenClaw-Medical-Skills数据与复现

bio-flow-cytometry-clustering-phenotyping

维护者 FreedomIntelligence · 最近更新 2026年4月1日

Unsupervised clustering and cell type identification for flow/mass cytometry. Covers FlowSOM, Phenograph, and CATALYST workflows. Use when discovering cell populations in high-dimensional cytometry data without predefined gates.

OpenClawNanoClaw分析处理复现实验bio-flow-cytometry-clustering-phenotyping🧬 bioinformatics (gptomics bio-* suite)bioinformatics — immunoinformatics & flow cytometryunsupervised

原始来源

FreedomIntelligence/OpenClaw-Medical-Skills

https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/bio-flow-cytometry-clustering-phenotyping

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

2 min

核心说明

R：FlowSOM：：FlowSOM() ，用于 self-organizing map 聚类。
R：CATALYST：：cluster() ，支持 Phenograph 或 FlowSOM。
Cluster my cytometry data to find cell types" → Discover cell populations in high-dimensional flow/mass cytometry data ，使用 unsupervised 聚类 without predefined gates. R：FlowSOM：：FlowSOM() ，用于 self-organizing map 聚类 R：CATALYST：：cluster() ，支持 Phenograph 或 FlowSOM。
expr <- exprs(fcs) marker_cols <- grep('CD|HLA'，colnames(fcs)，value = TRUE)。

原始文档

SKILL.md 摘录

FlowSOM Clustering

Goal: Cluster cytometry events into cell populations using self-organizing maps.

Approach: Build a FlowSOM grid on marker channels, then extract metacluster assignments per cell.

library(FlowSOM)

## Build SOM

fsom <- FlowSOM(fcs,
                colsToUse = marker_cols,
                xdim = 10, ydim = 10,
                nClus = 20,
                seed = 42)

## Get cluster assignments

clusters <- GetMetaclusters(fsom)