omicverse-bulk-metabol-multivariate

Name: omicverse-bulk-metabol-multivariate
Availability: InStock
Author: omicverse

Discriminate two metabolomics groups and select biomarkers from preprocessed AnnData.

13|2|Updated Apr 5, 2026

Search Tags:#metabolomics #vip #biomarker #roc #nested-cv #pls-da #opls-da

Ready to run

npx skills add https://github.com/omicverse/omicverse-skills --skill omicverse-bulk-metabol-multivariate

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: omicverse-bulk-metabol-multivariate
Source: https://github.com/omicverse/omicverse-skills/tree/main/src/omicverse_skills/skills/bulk-metabol-multivariate
Command: npx skills add https://github.com/omicverse/omicverse-skills --skill omicverse-bulk-metabol-multivariate

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

This Skill helps you compare two metabolomics groups, separate real biological signal from noise, and identify the features most likely to serve as reliable biomarkers.

Core Features & Use Cases

Multivariate discrimination with PLS-DA and OPLS-DA for preprocessed metabolomics AnnData objects.
Feature prioritization with VIP ranking and S-plot inspection to support biomarker triage.
Validation workflows for per-metabolite ROC AUC, bootstrap confidence intervals, and nested cross-validation biomarker panels with a permutation null.
Example use case: analyze a cachexia versus control dataset, compare model quality, rank the top metabolites, and build a compact biomarker panel for reporting.

Quick Start

Ask the assistant to run the metabolomics multivariate workflow on a preprocessed AnnData object, compare PLS-DA and OPLS-DA, rank VIP features, and validate a biomarker panel with nested cross-validation.

Frequently Asked Questions about omicverse-bulk-metabol-multivariate

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I rank metabolomic biomarkers using PLS-DA and OPLS-DA?▼

You can discriminate two metabolomics groups and select biomarkers by applying PLS-DA and OPLS-DA models to preprocessed AnnData, using VIP ranking and S-plot inspection to prioritize the most discriminative features.

What is the best way to validate a metabolomics biomarker panel?▼

Validating a metabolomics biomarker panel requires nested cross-validation with a permutation null, per-metabolite ROC AUC calculations, and bootstrap confidence intervals to ensure reportable panel performance.

Do I need log-transformed or Pareto-scaled data for metabolomics multivariate analysis?▼

Yes, this multivariate analysis requires log-transformed or Pareto-scaled metabolomics inputs in AnnData format, and your dataset must contain exactly two groups with explicit cross-validation settings configured.

Can I use S-plot inspection to triage metabolites for a biomarker panel?▼

Yes, you can use S-plot inspection alongside VIP ranking to triage metabolites, separating real biological signal from noise to identify features most likely to serve as reliable biomarkers.

Why does my metabolomics biomarker model require permutation testing?▼

Permutation testing is required during nested cross-validation to generate a null distribution, ensuring the biomarker panel's reported performance is statistically robust rather than overfitted to the data.