Tooluniverse Expression Data Retrieval logo

Tooluniverse Expression Data Retrieval

CommunityPopular
wu-yc
tooluniverse-expression-data-retrieval

Retrieves gene expression and omics datasets from ArrayExpress and BioStudies with gene disambiguation, experiment quality assessment, and structured reports. Creates comprehensive dataset profiles with metadata, sample information, and download links. Use when users need expression data, omics datasets, or mention ArrayExpress (E-MTAB, E-GEOD) or BioStudies (S-BSST) accessions.

Overview

Publisherwu-yc
RepositoryLabClaw
Skill nametooluniverse-expression-data-retrieval
Stars
1.1K
Forks
161
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by wu-yc on GitHub. Read the source before you install it.

Installation

Install the Tooluniverse Expression Data Retrieval AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/wu-yc/LabClaw/tree/main/skills/bio/tooluniverse-expression-data-retrieval
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/wu-yc/LabClaw.git /tmp/LabClaw
mkdir -p .claude/skills
cp -r /tmp/LabClaw/skills/bio/tooluniverse-expression-data-retrieval .claude/skills/tooluniverse-expression-data-retrieval
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tooluniverse Expression Data Retrieval in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Tooluniverse Expression Data Retrieval on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Tooluniverse Expression Data Retrieval is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Gene Expression & Omics Data Retrieval

Retrieve gene expression experiments and multi-omics datasets with proper disambiguation and quality assessment.

IMPORTANT: Always use English terms in tool calls (gene names, tissue names, condition descriptions), even if the user writes in another language. Only try original-language terms as a fallback if English returns no results. Respond in the user's language.

Workflow Overview

Phase 0: Clarify Query (if ambiguous)
    ↓
Phase 1: Disambiguate Gene/Condition
    ↓
Phase 2: Search & Retrieve (Internal)
    ↓
Phase 3: Report Dataset Profile

Phase 0: Clarification (When Needed)

Ask the user ONLY if:

  • Gene name is ambiguous (e.g., "p53" → TP53 or MDM2 studies?)
  • Tissue/condition unclear for comparative studies
  • Organism not specified for non-human research

Skip clarification for:

  • Specific accession numbers (E-MTAB-, E-GEOD-, S-BSST*)
  • Clear disease/tissue + organism combinations
  • Explicit platform requests (RNA-seq, microarray)

Phase 1: Query Disambiguation

1.1 Gene Name Resolution

If searching by gene, first resolve official identifiers:

python
from tooluniverse import ToolUniverse
tu = ToolUniverse()
tu.load_tools()

# For gene-focused searches, resolve official symbol first
# This helps construct better search queries
# Example: "p53" → "TP53" (official HGNC symbol)

Gene Disambiguation Checklist:

  • Official gene symbol identified (HGNC for human, MGI for mouse)
  • Common aliases noted for search expansion
  • Species confirmed

1.2 Construct Search Strategy

User Query TypeSearch Strategy
Specific accessionDirect retrieval
Gene + condition"[gene] [condition]" + species filter
Disease only"[disease]" + species filter
Technology-specificAdd platform keywords (RNA-seq, microarray)

Phase 2: Data Retrieval (Internal)

Search silently. Do NOT narrate the process.

2.1 Search Experiments

python
# ArrayExpress search
result = tu.tools.arrayexpress_search_experiments(
    keywords="[gene/disease] [condition]",
    species="[species]",
    limit=20
)

# BioStudies for multi-omics
biostudies_result = tu.tools.biostudies_search_studies(
    query="[keywords]",
    limit=10
)

2.2 Get Experiment Details

For top results, retrieve full metadata:

python
# Get details for each relevant experiment
details = tu.tools.arrayexpress_get_experiment_details(
    accession=accession
)

# Get sample information
samples = tu.tools.arrayexpress_get_experiment_samples(
    accession=accession
)

# Get available files
files = tu.tools.arrayexpress_get_experiment_files(
    accession=accession
)

2.3 BioStudies Retrieval

python
# Multi-omics study details
study_details = tu.tools.biostudies_get_study_details(
    accession=study_accession
)

# Study structure
sections = tu.tools.biostudies_get_study_sections(
    accession=study_accession
)

# Available files
files = tu.tools.biostudies_get_study_files(
    accession=study_accession
)

Fallback Chains

PrimaryFallbackNotes
ArrayExpress searchBioStudies searchArrayExpress empty
arrayexpress_get_experiment_detailsbiostudies_get_study_detailsE-GEOD may have BioStudies mirror
arrayexpress_get_experiment_filesNote "Files unavailable"Some studies restrict downloads

Phase 3: Report Dataset Profile

Output Structure

Present as a Dataset Search Report. Hide search process.

markdown
# Expression Data: [Query Topic]

**Search Summary**
- Query: [gene/disease] in [species]
- Databases: ArrayExpress, BioStudies
- Results: [N] relevant experiments found

**Data Quality Overview**: [assessment based on criteria below]

---

## Top Experiments

### 1. [E-MTAB-XXXX]: [Title]

| Attribute | Value |
|-----------|-------|
| **Accession** | [accession with link] |
| **Organism** | [species] |
| **Experiment Type** | RNA-seq / Microarray |
| **Platform** | [specific platform] |
| **Samples** | [N] samples |
| **Release Date** | [date] |

**Description**: [Brief description from metadata]

**Experimental Design**:
- Conditions: [treatment vs control, etc.]
- Replicates: [N biological, M technical]
- Tissue/Cell type: [if specified]

**Sample Groups**:
| Group | Samples | Description |
|-------|---------|-------------|
| Control | [N] | [description] |
| Treatment | [N] | [description] |

**Data Files Available**:
| File | Type | Size |
|------|------|------|
| [filename] | Processed data | [size] |
| [filename] | Raw data | [size] |
| [filename] | Sample metadata | [size] |

**Quality Assessment**: ●●● High / ●●○ Medium / ●○○ Low
- Sample size: [adequate/limited]
- Replication: [yes/no]
- Metadata completeness: [complete/partial]

---

### 2. [E-GEOD-XXXXX]: [Title]
[Same structure as above]

---

## Multi-Omics Studies (from BioStudies)

### [S-BSST-XXXXX]: [Title]

| Attribute | Value |
|-----------|-------|
| **Accession** | [accession] |
| **Study Type** | [proteomics/metabolomics/integrated] |
| **Organism** | [species] |
| **Samples** | [N] |

**Data Types Included**:
- [ ] Transcriptomics
- [ ] Proteomics
- [ ] Metabolomics
- [ ] Other: [specify]

---

## Summary Table

| Accession | Type | Samples | Platform | Quality |
|-----------|------|---------|----------|---------|
| [E-MTAB-X] | RNA-seq | [N] | Illumina | ●●● |
| [E-GEOD-X] | Microarray | [N] | Affymetrix | ●●○ |

---

## Recommendations

**For [specific analysis type]**:
- Best experiment: [accession] - [reason]
- Alternative: [accession] - [reason]

**Data Integration Notes**:
- Platform compatibility: [notes on combining datasets]
- Batch considerations: [if applicable]

---

## Data Access

### Direct Download Links
- [E-MTAB-XXXX processed data](link)
- [E-MTAB-XXXX raw data](link)

### Database Links
- ArrayExpress: https://www.ebi.ac.uk/arrayexpress/experiments/[accession]
- BioStudies: https://www.ebi.ac.uk/biostudies/studies/[accession]

Retrieved: [date]

Data Quality Tiers

Assessment criteria for expression experiments:

TierSymbolCriteria
High Quality●●●≥3 bio replicates, complete metadata, processed data available
Medium Quality●●○2-3 replicates OR some metadata gaps, data accessible
Low Quality●○○No replicates, sparse metadata, or data access issues
Use with Caution○○○Single sample, no replication, outdated platform

Include assessment rationale:

markdown
**Quality**: ●●● High
- ✓ 4 biological replicates per condition
- ✓ Complete sample annotations
- ✓ Processed and raw data available
- ✓ Recent RNA-seq platform

Completeness Checklist

Every dataset report MUST include:

Per Experiment (Required)

  • Accession number with database link
  • Organism
  • Experiment type (RNA-seq/microarray/etc.)
  • Sample count
  • Brief description
  • Quality assessment

Search Summary (Required)

  • Query parameters stated
  • Number of results
  • Databases searched

Recommendations (Required)

  • Best dataset for user's purpose (or "No suitable data found")
  • Data access notes

Include Even If Empty

  • Multi-omics studies section (or "No multi-omics studies found")
  • Data integration notes (or "Single-platform data, no integration needed")

Common Use Cases

Disease Gene Expression

User: "Find breast cancer RNA-seq data"

python
result = tu.tools.arrayexpress_search_experiments(
    keywords="breast cancer RNA-seq",
    species="Homo sapiens",
    limit=20
)

→ Report top experiments with quality assessment

Gene-Specific Studies

User: "Find TP53 expression experiments in mouse"

python
result = tu.tools.arrayexpress_search_experiments(
    keywords="TP53 p53",  # Include aliases
    species="Mus musculus",
    limit=15
)

→ Report experiments studying this gene

Specific Accession Lookup

User: "Get details for E-MTAB-5214" → Single experiment profile with all details and files

Multi-Omics Integration

User: "Find proteomics and transcriptomics studies for liver disease" → Search both ArrayExpress and BioStudies, note integration potential


Error Handling

ErrorResponse
"No experiments found"Broaden keywords, remove species filter, try synonyms
"Accession not found"Verify format (E-MTAB-, E-GEOD-, S-BSST*), check if withdrawn
"Files not available"Note in report: "Data files restricted by submitter"
"API timeout"Retry once, then note: "(metadata retrieval incomplete)"

Tool Reference

ArrayExpress (Gene Expression)

ToolPurpose
arrayexpress_search_experimentsKeyword/species search
arrayexpress_get_experiment_detailsFull metadata
arrayexpress_get_experiment_filesDownload links
arrayexpress_get_experiment_samplesSample annotations

BioStudies (Multi-Omics)

ToolPurpose
biostudies_search_studiesMulti-omics search
biostudies_get_study_detailsStudy metadata
biostudies_get_study_filesData files
biostudies_get_study_sectionsStudy structure

Search Parameters Reference

ArrayExpress

ParameterDescriptionExample
keywordsFree text search"breast cancer RNA-seq"
speciesScientific name"Homo sapiens"
arrayPlatform filter"Illumina"
limitMax results20

BioStudies

ParameterDescriptionExample
queryFree text"proteomics liver"
limitMax results10

Frequently asked questions

What does the Tooluniverse Expression Data Retrieval AI skill do?

Retrieves gene expression and omics datasets from ArrayExpress and BioStudies with gene disambiguation, experiment quality assessment, and structured reports. Creates comprehensive dataset profiles with metadata, sample information, and download links. Use when users need expression data, omics datasets, or mention ArrayExpress (E-MTAB, E-GEOD) or BioStudies (S-BSST) accessions.

Why use Tooluniverse Expression Data Retrieval on TypingMind?

Because you install it once and use it with any model. Tooluniverse Expression Data Retrieval is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Tooluniverse Expression Data Retrieval in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wu-yc/LabClaw/tree/main/skills/bio/tooluniverse-expression-data-retrieval. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Tooluniverse Expression Data Retrieval?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Tooluniverse Expression Data Retrieval?

As many as you like. As long as a model supports skills, you can use Tooluniverse Expression Data Retrieval with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Tooluniverse Expression Data Retrieval AI skill free?

It is published on GitHub by wu-yc. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇