multi-omics-integration

Files (3)

• SKILL.md
• run.cpython-313.pyc · scripts/__pycache__/
• run.py · scripts/

SKILL.md (first lines)

---
name: tooluniverse-multi-omics-integration
description: Integrate and analyze multiple omics datasets (transcriptomics, proteomics, epigenomics, genomics, metabolomics) for systems biology and precision medicine. Performs cross-omics correlation, multi-omics clustering (MOFA+, NMF), pathway-level integration, and sample matching. Coordinates ToolUniverse skills for expression data (RNA-seq), epigenomics (methylation, ChIP-seq), variants (SNVs, CNVs), protein interactions, and pathway enrichment. Use when analyzing multi-omics datasets, performing integrative analysis, discovering multi-omics biomarkers, studying disease mechanisms across molecular layers, or conducting systems biology research that requires coordinated analysis of transcriptome, genome, epigenome, proteome, and metabolome data.
---

# Multi-Omics Integration

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

## When to Use This Skill

**Triggers**:
- User has multiple omics datasets (RNA-seq + proteomics, methylation + expression, etc.)
- Requests for integrative multi-omics analysis
- Cross-omics correlation queries (e.g., "How does methylation affect expression?")
- Multi-omics biomarker discovery
- Systems biology questions requiring multiple molecular layers
- Precision medicine applications with multi-omics patient data
- Questions about molecular mechanisms across omics types

**Example Questions This Skill Solves**:
1. "Integrate RNA-seq and proteomics data to find genes with concordant changes"
2. "How does promoter methylation correlate with gene expression?"
3. "Perform multi-omics clustering to identify patient subtypes"
4. "Which pathways are dysregulated across transcriptome, proteome, and metabolome?"
5. "Find multi-omics biomarkers for disease classification"
6. "Correlate CNV with gene expression to identify dosage effects"
7. "Integrate GWAS variants, eQTLs, and expression data"
8. "Perform MOFA+ analysis on multi-omics cancer data"

---

## Core Capabilities

| Capability | Description |
|-----------|-------------|
| **Data Integration** | Match samples across omics, handle missing data, normalize scales |
| **Cross-Omics Correlation** | Correlate features across molecular layers (gene expression vs protein, methylation vs expression) |
| **Multi-Omics Clustering** | MOFA+, NMF, joint clustering to identify omics-driven subtypes |
| **Pathway Integration** | Combine omics evidence at pathway level for unified biological interpretation |
| **Biomarker Discovery** | Identify multi-omics signatures with improved predictive power |
| **Skill Coordination** | Orchestrate RNA-seq, epigenomics, variant-analysis, protein-interactions, gene-enrichment skills |
| **Visualization** | Circos plots, integrated heatmaps, network visualizations |
| **Reporting** | Unified multi-omics reports with cross-layer insights |

---

## Workflow Overview

```
Input: Multiple Omics Datasets
    |
    v
Phase 1: Data Loading & QC
    |-- Load RNA-seq (expression matrix)
    |-- Load proteomics (protein abundance)
    |-- Load methylation (beta values or M-values)
    |-- Load variants (CNV, SNV from VCF)
    |-- Load metabolomics (metabolite abundance)
    |-- Quality control per omics type
    |
    v
Phase 2: Sample Matching
    |-- Match samples across omics by ID
    |-- Identify common samples
    |-- Handle batch effects
    |-- Normalize sample identifiers
    |
    v
Phase 3: Feature Mapping
    |-- Map features to common identifier space (genes, proteins, metabolites)
    |-- Link CpG sites to genes (promoter, gene body)
    |-- Map variants to genes
    |-- Create unified feature matrix
    |
    v
Phase 4: Cross-Omics Correlation
    |-- Gene expression vs protein abundance (translation efficiency)
    |-- Promoter methylation vs expression (epigenetic regulation)
    |-- CNV vs expression (dosage effect)
    |-- eQTL variants vs expression (genetic regulation)
    |-- Metabolite vs enzyme expression (metabolic flux)
    |
    v
Phase 5: Multi-Omics Clustering
    |-- MOFA+ (Multi-Omics Factor Analysis) for latent factors
    |-- NMF (Non-negative Matrix Factorization) for patient subtypes
    |-- Joint clustering across omics
    |-- Identify omics-specific vs shared variation
    |
    v
Phase 6: Pathway-Level Integration
    |-- Aggregate omics to pathway level
    |-- Score pathway dysregulation (combined evidence)
    |-- Use ToolUniverse enrichment tools (Reactome, KEGG, GO)
    |-- Identify driver pathways across omics
    |
    v
Phase 7: Biomarker Discovery
    |-- Feature selection across omics
    |-- Multi-omics signatures for classification
    |-- Cross-validation and performance
    |-- Interpretation and biological validation
    |
    v
Phase 8: Generate Integrated Report
    |-- Summary statistics per omics
    |-- Cross-omics correlation results
    |-- Multi-omics clusters and subtypes
    |-- Top dysregulated pathways
    |-- Multi-omics biomarkers
    |-- Biological interpretation
```

---

## Phase Details

### Phase 1: Data Loading & Quality Control

From lamm-mit/scienceclaw, Apache-2.0.

More from lamm-mit/scienceclaw