What makes nutrigenomics notable?

1.9K downloads. Trust evidence available

How should nutrigenomics be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

nutrigenomics

Generate a personalised nutrition report from your genetic data (23andMe, AncestryDNA, or VCF). Analyses 24 genes (28 SNPs) across 12 nutrient domains affecting nutrient metabolism, absorption, and food sensitivities. All processing is local — your genetic data never leaves your device. Skill: nutrigenomics Owner: drdaviddelorenzo Summary: Generate a personalised nutrition report from your genetic data (23andMe, AncestryDNA, or VCF). Analyses 24 genes (28 SNPs) across 12 nutrient domains affecting nutrient metabolism, absorption, and food sensitivities. All processing is local — your genetic data never leaves your device. Tags: genetics:0.2.2, health:0.2.2, latest:0.3.13, nutrigenomics:0.2.2, nutrit

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.9k

Updated

Oct 9, 2026

Version

0.3.13

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.9K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 1.9K downloadsadoption · observed Oct 9, 2026
Latest release: 0.3.13release · observed Sep 16, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17b0p2rzrcmaq7s3vr89zdwnx849d82:nutrigenomics

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-drdaviddelorenzo-nutrigenomics/snapshot"

Documentation

CLAWHUB

160,000 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: nutrigenomics
description: Generate a personalised nutrition report from your genetic data (23andMe, AncestryDNA, or VCF). Analyses 24 genes (28 SNPs) across 12 nutrient domains affecting nutrient metabolism, absorption, and food sensitivities. All processing is local — your genetic data never leaves your device.
version: 0.3.12
license: MIT
compatibility: Requires Python 3.11+ with pandas, numpy, matplotlib and seaborn; runs fully offline with no network access
metadata:
  openclaw:
    requires:
      bins: [python3]
    emoji: "🧬"
  hermes:
    tags: [genetics, nutrition, nutrigenomics, health, 23andme, ancestrydna, vcf]
    category: health
---

# Nutrigenomics — Personalised Nutrition from Genetic Data

**Skill ID**: `nutrigenomics`
**Version**: 0.3.12
**Status**: Beta
**Author**: David de Lorenzo
**Requires**: Python 3.11+ (standard library only for the analysis; pandas, numpy, matplotlib and seaborn are needed only for figures)

---

## What This Skill Does

The Nutrigenomics generates a **personalised nutrition report** from consumer
genetic data (23andMe, AncestryDNA raw files or VCF). It interrogates a curated
set of nutritionally-relevant SNPs drawn from GWAS Catalog, ClinVar, and
peer-reviewed nutrigenomics literature, then translates genotype calls into
actionable dietary and supplementation guidance — all computed locally.

**Key outputs**
- Markdown nutrition report with risk scores and per-SNP genotype calls
- Radar chart of nutrient risk profile
- Gene × nutrient heatmap
- Reproducibility bundle (`README_reproducibility.txt`, `environment.yml`, `checksums.txt`, `provenance.json`)

---

## Trigger Phrases

The Bio Orchestrator should route to this skill when the user says anything like:

- "personalised nutrition", "nutrigenomics", "diet genetics"
- "what should I eat based on my DNA"
- "nutrient metabolism", "vitamin absorption genetics"
- "MTHFR", "APOE", "FTO", "BCMO1", "VDR", "FADS1/2"
- "folate", "omega-3", "vitamin D", "caffeine metabolism", "lactose", "gluten"
- Input files: `.txt` or `.csv` (23andMe), `.csv` (AncestryDNA), `.vcf`

---

## Curated SNP Panel

> **Implemented panel: 28 SNPs across 24 genes, 12 nutrient domains** (see
> `data/snp_panel.json`). The tables below also list **3 documented candidate variants not yet in
> the scoring panel** — `ADRB2 rs1042713`, `HLA-DQ2` (proxy SNPs), and `GSTT1` (deletion) — which
> require genotyping/scoring approaches not yet implemented. They are shown for scientific context;
> the scorer evaluates only the 28 SNPs present in the JSON.

### Macronutrient Metabolism

| Gene    | SNP        | Nutrient Impact                          | Evidence |
|---------|------------|------------------------------------------|----------|
| FTO     | rs9939609  | Energy balance, fat mass, carb sensitivity | Strong (GWAS) |
| PPARG   | rs1801282  | Fat metabolism, insulin sensitivity      | Moderate |
| APOA5   | rs662799   | Triglyceride response to dietary fat     | Strong |
| TCF7L2

README.md

# Nutrigenomics

**Personalised nutrition recommendations from your genetic data**

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
[![Python 3.11+](https://img.shields.io/badge/Python-3.11%2B-blue)](https://www.python.org/)
[![OpenClaw Compatible](https://img.shields.io/badge/OpenClaw-compatible-green)](https://openclaw.ai)

---

## 🧬 What is Nutrigenomics?

Nutrigenomics generates **personalised nutrition recommendations** based on your genetic profile. Upload your DNA file from 23andMe, AncestryDNA, or as a VCF file, and receive:

- 📊 **Nutrient Risk Assessment** — How your genes affect nutrient absorption and metabolism
- 🔍 **Gene-by-Gene Breakdown** — 24 genes across 12 nutrient domains
- 📈 **Visual Reports** — Radar charts and interaction heatmaps
- 💡 **Actionable Recommendations** — Dietary optimisation and supplementation guidance
- 🔒 **100% Private** — All processing happens locally on your device

---

## ✨ Key Features

| Feature | Description |
|---------|-------------|
| **24 Genes / 28 SNPs** | MTHFR, APOE, FTO, FADS1/2, VDR, CYP1A2, and more |
| **12 Nutrient Domains** | Folate, vitamin D, omega-3, vitamin A/C/B6, carbohydrate, fat metabolism, caffeine, alcohol, lactose, antioxidant |
| **Multi-Format Support** | 23andMe (.txt, .csv), AncestryDNA (.csv), VCF |
| **Risk Scoring** | 0-10 scale per nutrient with evidence-based recommendations |
| **Visualisations** | Radar chart (nutrient profile) + heatmap (gene-nutrient interactions) |
| **Private** | All analysis runs locally—no data transmission |
| **Open Source** | MIT licensed, community-driven |

---

## 🚀 Quick Start

### Via OpenClaw (Recommended for non-technical users)

Once published to ClawHub:

```bash
clawhub install nutrigenomics
```

Then tell OpenClaw: **"Generate my personalised nutrition report"** and upload your genetic data.

### Manual Installation

1. **Clone this repository**:
   ```bash
   git clone https://github.com/drdaviddelorenzo/nutrigenomics.git
   cd nutrigenomics
   ```

2. **Install dependencies**:
   ```bash
   pip install -r requirements.txt
   ```

3. **Run analysis**:
   ```bash
   python openclaw_adapter.py \
     --input your_genome.csv \
     --format 23andme \
     --output results/
   ```

4. **View results**:
   ```bash
   cat results/nutrigenomics_report.md
   open results/nutrigenomics_radar.png
   open results/nutrigenomics_heatmap.png
   ```

---

## 📖 Usage Examples

### From 23andMe Data
```bash
python openclaw_adapter.py --input genome.txt --format 23andme
```

### From AncestryDNA
```bash
python openclaw_adapter.py --input ancestry.csv --format ancestry
```

### From VCF File
```bash
python openclaw_adapter.py --input variants.vcf --format vcf
```

### Generate Test Report
```bash
python examples/generate_patient.py --run
```

---

## 📊 What You'll Get

### Personalised Report (Markdown)
- Executive summary of top findings
- Per-nutrient gene tables
- Risk interpretations
- Dietary recommen

_meta.json

{
  "ownerId": "kn72g7f5vphy1xn5w81nf6m7j9820vwt",
  "slug": "nutrigenomics",
  "version": "0.3.13",
  "publishedAt": 1789541827447
}

ATTRIBUTION.md

# Attribution & Acknowledgments

## Nutrigenomics — Credits and Recognition

### Author & Maintainer
**David de Lorenzo** ([@drdaviddelorenzo](https://github.com/drdaviddelorenzo))
- **GitHub**: https://github.com/drdaviddelorenzo
- **Website**: https://drdaviddelorenzo.github.io
- **Email**: [email protected]

**Contributions:**
- Conceptualisation and design
- Core analysis engine development
- SNP panel curation
- OpenClaw platform implementation
- OpenClaw adaptation

### Scientific & Technical Foundation

#### Nutrigenomics Research & Literature
The SNP panel and risk scoring algorithm are informed by peer-reviewed nutrigenomics research. Key data sources include:

**Note**: This skill is educational and research-oriented. For the most current and verified scientific information, users should consult:
- The latest peer-reviewed publications indexed in PubMed
- GWAS Catalog for genetic association studies
- ClinVar for variant interpretations
- Their own healthcare providers for medical decisions

#### Data Sources
- **GWAS Catalog**: Buniello A, MacArthur JAL, Cerezo M, et al. (2019). The NHGRI-EBI GWAS Catalog of published genome-wide association studies, targeted arrays and summary statistics. *Nucleic Acids Research*. 47(D1):D1005-D1012. https://www.ebi.ac.uk/gwas/

- **ClinVar**: Landrum MJ, et al. (2024). ClinVar: improvements in accuracy, accessibility, and use of variant interpretations for clinical genetics. *Human Mutation*. https://www.ncbi.nlm.nih.gov/clinvar/

- **PubMed MEDLINE**: US National Library of Medicine. https://pubmed.ncbi.nlm.nih.gov/

### Platform & Infrastructure

- Original platform for skill development and testing
- Infrastructure for skill management
- Community collaboration features

- **OpenClaw**: Web-accessible AI-powered analysis platform
- User-friendly interface
- Scalable deployment
- Community skill marketplace
- https://openclaw.ai

### Software & Libraries

- **Python**: Python Software Foundation
- **Pandas**: McKinney W. (2010). Data structures for statistical computing in Python. Proceedings of the 9th Python in Science Conference.
- **NumPy**: Harris CR, Millman KJ, van der Walt SJ, et al. (2020). Array programming with NumPy. *Nature*. 585:357-362.
- **Matplotlib**: Hunter JD. (2007). Matplotlib: A 2D graphics environment. *Computing in Science & Engineering*. 9(3):90-95.
- **Seaborn**: Waskom ML. (2021). Seaborn: statistical data visualization. *Journal of Open Source Software*. 6(60):3021.
- **ReportLab**: ReportLab International Ltd.

### Community & Feedback

Special thanks to:

- **Nutrigenomics researchers** who published the foundational studies
- **OpenClaw development team** for platform support
- **Beta testers** who identified edge cases and improvements

---

## How to Cite This Work

If you use Nutrigenomics in research or educational contexts, please cite it as:

### BibTeX
```bibtex
@software{delorenzo2026nutrigenomics,
author = {de Lorenzo, David},
tit

CHANGELOG.md

# Changelog

All notable changes to Nutrigenomics are documented in this file.

The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

---
## [0.3.13] - 2026-09-15

### Fixed
- **Documentation figures no longer matched the panel.** README.md, README_OPENCLAW.md,
  SKILL.md, and openclaw.json still quoted an earlier panel size ("40+ genes", "8 nutrient
  categories", "58 SNPs"). Verified against `data/snp_panel.json` and corrected throughout to
  24 genes, 28 SNPs, 12 nutrient domains. SKILL.md also now notes 3 candidate variants
  (`ADRB2 rs1042713`, `HLA-DQ2`, `GSTT1`) that are documented for scientific context but not
  yet scored.
- **Generated report printed a stale tool version.** `generate_report.py` hardcoded
  `Nutrigenomics v0.2.8` in the report header regardless of the installed skill version. Now
  reads the version via `repro_bundle._skill_version()`, the same helper `provenance.json`
  already used, so the two cannot drift apart again.

---
## [0.3.12] - 2026-09-14

### Fixed
- **Two citations named the wrong paper.** Both pointed at studies that list the SNP only in a
  table of previously known loci:
  - `rs174546` (FADS1) cited PMID 25646338, a trans fatty-acid GWAS whose FADS1 hit is `rs174548`.
    Now PMID 20691134 (Zietemann et al. 2010, EPIC-Potsdam, n = 2066), which genotyped
    `rs174546` and reports it against PUFA levels and estimated delta-5 desaturase activity.
  - `rs4588` (GC) cited PMID 28757204, a CYP2R1 rare-variant paper (`rs117913124`). Now PMID
    19116321 (Sinotte et al. 2009), which genotyped `rs4588` and reports each rare allele with
    lower plasma 25(OH)D.

  Found by the ClawBio maintainer review of the same panel. The GWAS Catalog lists every variant
  appearing in a paper's known-loci table, which is not the same as the paper reporting it. No
  scores change.

---

## [0.3.11] - 2026-09-13

### Fixed
- **`rs953413` (ELOVL2, omega-3) scored the wrong allele as risk.** The panel had
  `ref_allele A`, `risk_allele G` for "decreased DHA synthesis", but the A allele is the one
  associated with lower DHA. In Tanaka et al. 2009 (InCHIANTI and GOLDN, PMID 19148276) DHA fell
  from GG through AG to AA in both cohorts (InCHIANTI 2.37 / 2.29 / 2.17, p = 0.004; GOLDN
  3.32 / 3.20 / 3.10, p = 0.002), and the authors state that "the presence of the minor (A)
  allele was associated with higher EPA/DPA and lower DHA". A functional study (iScience 2020,
  PMID 31928966) found the G allele gives higher ELOVL2 enhancer activity than A. GG, the
  highest-DHA genotype, was scored at maximum risk and AA at none. Now `ref G`, `risk A`.
  Orientation checked against Ensembl: G/A on the plus strand in GRCh37 and GRCh38, and not
  palindromic, so minus-strand T/C calls resolve correctly. **Omega-3 results for GG and AA
  genotypes change in every report generated before this release; AG is unaffected.**
- The c

Github ReposUpdated 10h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.