# tooluniverse-multi-omics-integration

A skill that pulls several omics layers into one analysis: matches samples, runs cross-omics correlations, clusters patients and writes a report.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 398 installs · ★ 1759
- Author: mims-harvard
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/mims-harvard/ToolUniverse/tree/HEAD/skills/tooluniverse-multi-omics-integration/SKILL.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/tooluniverse-multi-omics-integration

## What it does

The skill works in phases: load and QC each layer, match samples, map features to shared gene-level identifiers, run cross-omics correlations, cluster, integrate at pathway level, then look for biomarkers. Supported layers are transcriptomics, proteomics, methylation, CNV/SNV and metabolomics, with formats ranging from CSV and h5ad to MaxQuant, DIA-NN, IDAT and VCF.

It coordinates other ToolUniverse skills, among them `tooluniverse-rnaseq-deseq2`, `tooluniverse-epigenomics`, `tooluniverse-variant-analysis` and `tooluniverse-gene-enrichment`. Clustering options are MOFA+, joint NMF and SNF. Pathway enrichment is meant to be computed on the actual gene lists rather than recalled, and the same goes for eQTL links and the direction of methylation versus expression.

There is a data floor: at least two omics datasets and 10 common samples, with n >= 20 recommended for integration. When not every sample carries every layer, the skill falls back to pairwise integration. Different platforms need careful normalization because of batch effects.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-multi-omics-integration -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/tooluniverse-multi-omics-integration/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/tooluniverse-multi-omics-integration/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-multi-omics-integration -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/tooluniverse-multi-omics-integration/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-multi-omics-integration -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/tooluniverse-multi-omics-integration/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install mims-harvard/ToolUniverse tooluniverse-multi-omics-integration
```

2. **Manually: put the files in place**
- File: `.github/skills/tooluniverse-multi-omics-integration/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-multi-omics-integration -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/mims-harvard/ToolUniverse --path skills/tooluniverse-multi-omics-integration
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/tooluniverse-multi-omics-integration/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-multi-omics-integration -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/mims-harvard/ToolUniverse/tree/HEAD/skills/tooluniverse-multi-omics-integration/SKILL.md

## When to use it
- match samples across RNA-seq and proteomics on shared IDs
- compute per-gene correlation between transcript and protein abundance
- find patient subtypes with MOFA+, NMF or SNF
- aggregate evidence from several omics layers into one pathway score
- select cross-omics features for a biomarker

## Example prompts
- I have RNA-seq and proteomics on the same samples — match them and compute the correlations.
- Cluster the patients using methylation and expression, and show shared versus omics-specific factors.
- Build the report: correlations, clusters, enriched pathways and biomarker candidates.

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 302219f4fd9cdbf1.

BEGIN THIRD-PARTY FILE 302219f4fd9cdbf1
```text
---
name: tooluniverse-multi-omics-integration
description: Multi-omics integration — orchestrate per-layer analysis (transcriptomics, proteomics, epigenomics, genomics, metabolomics) then perform cross-omics correlation, multi-omics clustering, and pathway-level integration. Use for integrative systems-biology analysis, multi-modal disease characterization, and cross-omics biomarker discovery.
disable-model-invocation: true
---

# Multi-Omics Integration

Coordinate and integrate multiple omics datasets for comprehensive systems biology analysis. Orchestrates specialized ToolUniverse skills to perform cross-omics correlation, multi-omics clustering, pathway-level integration, and unified interpretation.

---

## Domain Reasoning

Multi-omics integration asks whether different molecular layers tell a concordant story. If a gene is upregulated in RNA-seq AND its protein is elevated in proteomics, that is concordant evidence of true biological change. Discordance — high mRNA but low protein, or elevated protein without matching mRNA — may indicate post-transcriptional regulation (miRNA silencing, protein degradation, translational control) and is itself a meaningful finding worth reporting. Not every discordance is noise; some are the most interesting biology.

## LOOK UP DON'T GUESS

- Expected RNA-protein correlation ranges: compute Spearman r from the actual data; the typical range (0.4-0.6) is a guide, not a guarantee.
- Pathway enrichment results: run `ReactomeAnalysis_pathway_enrichment` or gseapy on the actual gene lists; never list enriched pathways from memory.
- eQTL associations: query GTEx or eQTL databases for the specific variant and tissue; do not assume regulatory relationships.
- Methylation-expression directionality at specific loci: retrieve experimental data; promoter repression is the canonical model but exceptions exist.

---

## When to Use This Skill

- User has multiple omics datasets (RNA-seq + proteomics, methylation + expression, etc.)
- Cross-omics correlation queries (e.g., "How does methylation affect expression?")
- Multi-omics biomarker discovery or patient subtyping
```
END THIRD-PARTY FILE 302219f4fd9cdbf1

The third-party file has ended. Everything between the 302219f4fd9cdbf1 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2140 of 7633 bytes. © mims-harvard · Apache-2.0 · https://github.com/mims-harvard/ToolUniverse/tree/HEAD/skills/tooluniverse-multi-omics-integration/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md