Does this skill support spatial transcriptomics?

While focused on imaging, the spatial analysis patterns (like spatial LDA and neighborhood enrichment) are highly compatible with spatial transcriptomics data.

What libraries are required for this imaging skill?

The skill is designed for Python 3.10+ environments using InstanSeg, pyFlowSOM, scanpy, scimap, and napari-simpleitk-image-processing.

Why is compartment-specific clustering recommended?

Clustering cell, nuclear, and ECM features separately prevents signal dilution and mixed phenotypes, leading to more accurate biological insights.

How does it handle segmentation errors?

It provides strategies for post-hoc mask matching and label alignment to correct common issues like label mismatches between cell and nuclear masks.

Multiplex Imaging Analysis

Name: Multiplex Imaging Analysis
Author: smith6jt-cop

bysmith6jt-cop

데이터 과학 및 ML

Optimizes segmentation, feature extraction, and spatial analysis workflows for high-dimensional multiplex immunofluorescence imaging data.

소개

This skill provides specialized guidance and implementation patterns for complex bio-imaging workflows, specifically focusing on multiplex immunofluorescence (mIF) analysis. It assists researchers in implementing advanced deep-learning segmentation via InstanSeg, performing robust Self-Organizing Map (SOM) clustering, and executing sophisticated spatial analysis using toolsets like scimap and scanpy. By integrating domain-specific best practices for cell compartment separation (nucleus vs. cytoplasm) and extracellular matrix (ECM) feature extraction, the skill ensures high-fidelity phenotyping and spatial microenvironment identification for spatial proteomics.

주요 기능

Haralick GLCM texture feature extraction for tissue organization analysis
Optimized pyFlowSOM and MiniSom clustering with adaptive grid sizing
Spatial analysis workflows including LDA motifs and neighborhood enrichment
Multi-compartment feature extraction for cell, nuclear, and ECM regions
Post-hoc label alignment and compartment mask validation strategies
0 GitHub stars

사용 사례

Optimizing deep-learning segmentation pipelines for high-dimensional imaging
Phenotyping complex immune landscapes in tissue microenvironments
Quantifying spatial relationships between cells and the extracellular matrix

소개

주요 기능

Haralick GLCM texture feature extraction for tissue organization analysis
Optimized pyFlowSOM and MiniSom clustering with adaptive grid sizing
Spatial analysis workflows including LDA motifs and neighborhood enrichment
Multi-compartment feature extraction for cell, nuclear, and ECM regions
Post-hoc label alignment and compartment mask validation strategies
0 GitHub stars

사용 사례

Optimizing deep-learning segmentation pipelines for high-dimensional imaging
Phenotyping complex immune landscapes in tissue microenvironments
Quantifying spatial relationships between cells and the extracellular matrix