Skip to main content
skill CX Codex

tooluniverse-lipidomics — Claude Code skill

tooluniverse-lipidomics is a Claude Code skill that identifies and classifies lipids, maps metabolic pathways, and retrieves disease associations for lipidomics analysis.

Apache-2.0 238 installs ★ 1,798 updated 2026-10-24

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-lipidomics -a claude-code
Open on GitHub

What tooluniverse-lipidomics does

tooluniverse-lipidomics connects multiple lipid and disease databases to support end-to-end lipidomics analysis. Given a lipid name, mass, or abbreviation, the skill retrieves its structure and assigns it to one of eight LIPID MAPS categories: fatty acyls, glycerolipids, glycerophospholipids, sphingolipids, sterol lipids, prenol lipids, saccharolipids, and polyketides. Each category has distinct metabolic roles and disease contexts. The skill then maps the lipid to biosynthesis and degradation enzymes via KEGG and Reactome, and pulls disease associations from CTD and DisGeNET.

Core tools include LipidMaps_search_by_name, LipidMaps_get_compound_by_id, SwissLipids_search, HMDB_search, kegg_search_pathway, CTD_get_gene_diseases, and PubMed_search_articles. For specialized lipid classes—sphingolipids, eicosanoids, steroids, fatty acids—the skill already knows the relevant pathways. The skill queries databases rather than assuming lipid IDs or disease links.

Requires network access to LIPID MAPS, HMDB, KEGG, Reactome, PubChem, and CTD. Not for general metabolomics (amino acids, sugars, organic acids); use a separate metabolomics skill for those.

What it helps with

  • Identify a lipid species from mass spectrometry m/z and retention time
  • Find metabolic pathways that involve ceramide or sphingomyelin biosynthesis and degradation
  • Retrieve lipid biomarkers for Alzheimer's disease and cardiovascular disease from HMDB
  • Map genes and enzymes in lipid metabolism pathways to diabetes risk
  • Compare lipid profiles between healthy and diseased samples

Example prompts for the agent

  • Identify lipid Cer(d18:1/16:0) and retrieve its sphingolipid biosynthesis pathway
  • What genes and biomarkers are associated with altered sphingolipid metabolism in neurodegeneration?
  • Search HMDB and KEGG for lipid biomarkers of cardiovascular disease

How to install tooluniverse-lipidomics

1Skills CLI (Vercel)

npx skills add mims-harvard/ToolUniverse --skill tooluniverse-lipidomics -a claude-code

2Manually: put the files in place

~/.claude/skills/tooluniverse-lipidomics/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/tooluniverse-lipidomics/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about tooluniverse-lipidomics

How do I install tooluniverse-lipidomics in Claude Code?

Run npx skills add mims-harvard/ToolUniverse --skill tooluniverse-lipidomics -a claude-code in your terminal, then verify by opening ~/.claude/skills/tooluniverse-lipidomics/SKILL.md.

What does tooluniverse-lipidomics do?

The skill identifies and classifies lipids using LIPID MAPS categories, retrieves their metabolic pathways (synthesis and degradation enzymes), and finds disease associations via scientific databases. Use it to analyze lipidomics data, discover lipid biomarkers, and explore lipid metabolism in disease.

When should I use tooluniverse-lipidomics instead of other skills?

Use this skill for lipid-specific analysis and disease links. For broad metabolomics (amino acids, sugars, organic acids), use tooluniverse-metabolomics. For drug ADMET prediction, use tooluniverse-admet-prediction.

Source text

SKILL.md · Apache-2.0
---
name: tooluniverse-lipidomics
description: Lipid analysis and lipid-disease associations using LIPID MAPS classification, HMDB metabolite data, KEGG/Reactome lipid pathways (sphingolipid, eicosanoid, steroid, fatty acid), and PubChem chemical info. Use for lipid identification, lipid metabolism pathway mapping, and lipid-associated disease analysis (cardiovascular, diabetes, NAFLD).
disable-model-invocation: true
---

# Lipidomics Analysis

Integrated pipeline for lipid identification, classification, pathway mapping, and disease association analysis. Distinct from general metabolomics because lipids have unique classification systems (LIPID MAPS), specialized pathways (sphingolipid, eicosanoid, steroid), and disease associations (cardiovascular, neurodegeneration, metabolic syndrome).

## Reasoning Strategy

Lipid identification starts with mass spectrometry: the lipid class is determined by the head group fragment mass (e.g., m/z 184 for phosphocholine in positive mode), total chain length and saturation from the precursor exact mass, and individual fatty acid chains from neutral loss or product ion scans. LIPID MAPS classification organizes lipids by chemical structure into 8 categories — knowing the category immediately tells you the likely biological context (sphingolipids → apoptosis/neurodegeneration; glycerophospholipids → membrane remodeling; eicosanoids → inflammation). Structural specificity matters biologically: Cer(d18:1/16:0) and Cer(d18:1/24:1) have different membrane properties and disease associations despite being the same lipid class. Always map changed lipids back to metabolic pathways because lipids are intermediates — an elevated ceramide could mean increased synthesis (CERS activity up), decreased degradation (ASAH1 down), or shunting from sphingomyelin (SMPD1 up).

**LOOK UP DON'T GUESS**: Do not assume a lipid's LIPID MAPS ID, exact mass, or pathway membership — query `LipidMaps_search_by_name` first. Do not guess which diseases are associated with a lipid class; retrieve them from HMDB or CTD.

**Key principles**:
1. **LIPID MAPS classification first** — use the 8-category system (fatty acyls, glycerolipids, glycerophospholipids, sphingolipids, sterol lipids, prenol lipids, saccharolipids, polyketides)
2. **Structural specificity matters** — chain length, unsaturation, and sn-position affect biological function
3. **Connect to pathways** — lipids are metabolic intermediates; always map to biosynthesis/degradation pathways
4. **Disease context** — many lipids are disease biomarkers (sphingolipids in neurodegeneration, oxidized lipids in CVD)
5. **Evidence grading** — T1: clinical biomarker studies, T2: mechanistic studies, T3: association data, T4: computational prediction

---

## When to Use

- "Identify this lipid species from m/z and retention time"
- "What pathways involve ceramide/sphingomyelin?"
- "Lipid biomarkers for Alzheimer's disease"
- "What diseases are associated with altered sphingolipid metabolism?"
- "Map my lipidomics results to KEGG pathways"
- "Compare lipid profiles between conditions"

**Not this skill**: For general metabolomics (amino acids, sugars, organic acids), use `tooluniverse-metabolomics`. For drug ADMET properties, use `tooluniverse-admet-prediction`.

---

## Core Tools

| Tool | Use For |
|------|---------|
| `LipidMaps_search_by_name` | Lipid identification by name, abbreviation, or mass |
| `LipidMaps_get_compound_by_id` | Detailed lipid info (structure, classification, pathways) |
| `SwissLipids_search` | Lipid identification by name/shorthand — SIB's complementary lipid database, use when LIPID MAPS misses a species (see below) |
| `SwissLipids_get_lipid` | Full SwissLipids entry: name, formula, monoisotopic mass, cross-refs |
| `SwissLipids_get_children` | Descend the SwissLipids classification tree (category → class → species) one level |
| `HMDB_search` / `HMDB_get_metabolite` | Lipid metabolite details, disease associations |
| `kegg_search_pathway` | Lipid metabolism pathways (keyword=`sphingolipid`, `glycerolipid`, etc.) |
| `KEGG_get_pathway_genes` | Enzymes in lipid pathways |
| `PubChem_get_compound_properties_by_CID` | Chemical properties (mass, formula, SMILES) |
| `CTD_get_gene_diseases` | Gene-disease links for lipid metabolism enzymes |
| `LipidMaps_get_gene` | Resolve a lipid-metabolism gene (symbol/NCBI ID/LMP ID) to its LIPID MAPS Proteome Database record — name, synonyms, chromosome location, species |
| `LipidMaps_get_protein` | Same lookup at the protein level — adds UniProt/RefSeq cross-references and amino-acid sequence |
| `DisGeNET_search_gene` | Disease associations for lipid genes |
| `PubMed_search_articles` | Published lipidomics studies |
| `OpenTargets_get_associated_drugs_by_target_ensemblID` | Drugs targeting lipid metabolism enzymes |

---

## Workflow

```
Phase 0: Lipid Identity Resolution
  Name/mass/abbreviation → LIPID MAPS ID → classification
    |
Phase 1: Structural Classification
  LIPID MAPS 8-category system → subclass → molecular species
    |
Phase 2: Pathway Mapping
  KEGG lipid metabolism → biosynthesis/degradation enzymes
    |
Phase 3: Disease Associations
  CTD/DisGeNET/HMDB → lipid-disease links with evidence
    |
Phase 4: Interpretation & Report
  Biological significance → biomarker potential → recommendations
```

### Phase 0: Lipid Identity Resolution

```
LipidMaps_search_by_name(query="ceramide")  → LMSP ID, exact mass, classification
HMDB_search(compound_name="ceramide")       → HMDB ID, disease links
PubChem_get_CID_by_compound_name(name="ceramide") → CID, SMILES
```

**LIPID MAPS search tips**:
- Generic names work well: "ceramide", "sphingomyelin", "phosphatidylcholine"
- Species-level abbreviations like "Cer(d18:1/16:0)" may return 0 results — use the generic class name first, then filter by chain length from results
- For exact mass search: use `LipidMaps_search_by_formula` with molecular formula (e.g., "C34H67NO3")
- If name search fails, try PubChem: `PubChem_get_CID_by_compound_name(name="C16 Ceramide")` then cross-reference

**SwissLipids as a second lipid database** — when LIPID MAPS doesn't have a species
or you want its independent classification, SwissLipids (swisslipids.org, SIB)
covers the same ground with its own ID space and hierarchy:

```
SwissLipids_search(query="PC(16:0/18:1)")   → real hit: entity_id "SLM:000088148"
SwissLipids_get_lipid(entity_id="SLM:000000510") → real entry: "hexadecanoate"
  (palmitate), formula C16H31O2, mass 255.4167, charge -1, plus a full
  adduct_mz table ([M+H]+, [M+Na]+, [M-H]-, etc.) useful for matching
  observed MS peaks directly — LIPID MAPS entries don't include this table.
SwissLipids_get_children(entity_id="SLM:000000338") → descend one level in the
  classification tree (e.g. from a lipid category down to its member species)
```

Shorthand abbreviations like `PC(16:0/18:1)` work directly in `SwissLipids_search`
(unlike LIPID MAPS, which often needs the generic class name first). Note
`classification` can come back as an empty array `[]` for some entries — a real
data gap in SwissLipids, not a failed lookup; fall back to LIPID MAPS for that
lipid's category if classification is required.

### Phase 1: Structural Classification

Use `LipidMaps_get_compound_by_id` to retrieve the LIPID MAPS 8-category classification (FA, GL, GP, SP, ST, PR, SL, PK) for any lipid. The category immediately signals biological context: SP (sphingolipids) → apoptosis/neurodegeneration; GP (glycerophospholipids) → membrane remodeling; FA-derived eicosanoids → inflammation.

### Phase 2: Pathway Mapping

Key lipid metabolism pathways in KEGG:

| Pathway | KEGG ID | Key Enzymes | Disease Relevance |
|---------|---------|-------------|-------------------|
| Sphingolipid metabolism | hsa00600 | SMPD1, CERS1-6, ASAH1 | Niemann-Pick, Fabry, Gaucher |
| Glycerophospholipid metabolism | hsa00564 | PLA2, LPCAT, LPIN | Barth syndrome, atherosclerosis |
| Arachidonic acid metabolism | hsa00590 | COX1/2, LOX, CYP450 | Inflammation, asthma, CVD |
| Steroid biosynthesis | hsa00100 | HMGCR, CYP51A1, DHCR7 | Hypercholesterolemia, Smith-Lemli-Opitz |
| Fatty acid biosynthesis | hsa00061 | FASN, ACC, SCD | Obesity, NAFLD, cancer |
| Fatty acid degradation | hsa00071 | CPT1, ACADM, HADHA | MCAD deficiency, VLCAD deficiency |
| Bile acid biosynthesis | hsa00120 | CYP7A1, CYP27A1 | Cholestasis, gallstones |
| Ether lipid metabolism | hsa00565 | AGPS, GNPAT | Rhizomelic chondrodysplasia |

```python
# Map lipids to pathways
kegg_search_pathway(keyword="sphingolipid")  # → hsa00600
KEGG_get_pathway_genes(pathway_id="hsa00600")  # → SMPD1, CERS1, ...
```

### Phase 3: Disease Associations

For each lipid or lipid enzyme, resolve the gene/protein record first if needed, then check disease links:

```python
LipidMaps_get_gene(input_value="SMPD1", input_item="gene_symbol")  # LMPD record: name, synonyms, chromosome
  # verified live example: input_value="FASN" → {"gene_symbol": "Fasn", "lmp_id": "LMP001577", "gene_name": "fatty acid synthase", ...}
LipidMaps_get_protein(input_value="P49327", input_item="uniprot_id")  # adds UniProt/RefSeq xrefs + sequence
CTD_get_gene_diseases(input_terms="SMPD1")  # sphingomyelinase → Niemann-Pick
DisGeNET_search_gene(gene="SMPD1")  # broader disease associations
HMDB_get_metabolite(compound_name="ceramide")  # metabolite-disease links
PubMed_search_articles(query="ceramide biomarker Alzheimer")  # clinical evidence
```

**Disease context**: Ceramide elevation → apoptosis, Alzheimer's, insulin resistance. Sphingomyelin depletion → Niemann-Pick. Oxidized phospholipids → CVD. Altered bile acid ratios → NAFLD, cholestasis. Eicosanoid elevation → inflammation. Always verify via HMDB or CTD rather than relying on memory.

### Phase 4: Interpretation & Report

**Computational procedure: Lipid class enrichment analysis**

```python
# When user provides a list of significantly changed lipids
import pandas as pd
from scipy.stats import fisher_exact

# Input: list of changed lipids with LIPID MAPS categories
changed = pd.DataFrame({
    'lipid': ['Cer(d18:1/16:0)', 'SM(d18:1/16:0)', 'PC(16:0/18:1)', 'LPC(18:0)'],
    'category': ['SP', 'SP', 'GP', 'GP'],
    'direction': ['up', 'down', 'unchanged', 'up'],
    'fold_change': [2.1, 0.5, 1.1, 1.8]
})

# Count changed vs unchanged per category
from collections import Counter
changed_cats = Counter(changed[changed['direction'] != 'unchanged']['category'])
total_cats = Counter(changed['category'])

# Report
print("Lipid class enrichment:")
for cat in total_cats:
    n_changed = changed_cats.get(cat, 0)
    n_total = total_cats[cat]
    print(f"  {cat}: {n_changed}/{n_total} changed")

# Interpretation
if changed_cats.get('SP', 0) / max(total_cats.get('SP', 1), 1) > 0.5:
    print("→ Sphingolipid metabolism is significantly altered")
    print("  Consider: apoptosis, neurodegeneration, insulin resistance")
```

**Report structure**:
1. **Lipid Identity** — LIPID MAPS classification, structural features
2. **Pathway Context** — which metabolic pathways are affected
3. **Disease Associations** — evidence-graded disease links
4. **Biomarker Assessment** — clinical utility of identified lipid changes
5. **Mechanistic Model** — how lipid changes connect to disease biology
6. **Recommendations** — validation experiments, clinical follow-up

---

## Limitations

- **No raw MS data processing** — this skill interprets identified lipids, not raw spectra. Use LipidSearch, MS-DIAL, or LipiDex for identification first.
- **LIPID MAPS coverage** — some rare or novel lipid species may not be in the database
- **Quantitative thresholds** — fold-change cutoffs are context-dependent; the skill provides frameworks, not universal thresholds
- **Species-specific** — most disease data is human; rat/mouse lipid metabolism can differ significantly

© mims-harvard · Apache-2.0 · mims-harvard/ToolUniverse

Similar skills

All skills for AI and ML →

From the same set136

The whole set →
tooluniverse-small-molecule-discovery tooluniverse-small-molecule-discovery is a Claude Code skill for finding and analyzing small molecules, from compound names to structures, activity, ADMET properties, and availability. CX Codex +1 240installs tooluniverse-gene-disease-association tooluniverse-gene-disease-association is a skill that cross-references gene-disease associations across databases and scores evidence concordance for clinical and research queries. CX Codex +1 240installs tooluniverse-protein-modification-analysis tooluniverse-protein-modification-analysis is a Claude Code skill for studying protein post-translational modifications. It handles PTM site annotation, enzyme links, and disease associations. CX Codex +1 239installs tooluniverse-pathway-disease-genetics tooluniverse-pathway-disease-genetics traces GWAS variants through causal genes and biological pathways to drug targets. Use it to study disease mechanisms or prioritize repurposing candidates. CX Codex +1 239installs tooluniverse-comparative-genomics tooluniverse-comparative-genomics is a Claude Code skill that finds orthologs and assesses gene conservation across species. CX Codex +1 238installs tooluniverse-metabolomics-pathway The tooluniverse-metabolomics-pathway skill connects metabolites with pathways, enzymes, genes, and diseases. Use it when metabolomics work needs cross-database identification and mapping. CX Codex +1 238installs tooluniverse-electron-microscopy The tooluniverse-electron-microscopy skill for Claude Code searches and inspects electron microscopy records in EMDB, PDB, EMPIAR, and CryoET Data Portal. It helps link density maps to fitted atomic models. CX Codex +1 238installs tooluniverse-adverse-outcome-pathway tooluniverse-adverse-outcome-pathway maps industrial and environmental chemicals to adverse outcome pathways. Retrieves GHS classifications, IARC cancer statuses, LD50 toxicity values, and CTD gene interactions. CX Codex +1 236installs

Project sponsors

Companies that keep this analytics open