mims-harvard/tooluniverse-expression-data-retrieval
plugin/skills/tooluniverse-expression-data-retrieval/SKILL.md
Retrieve gene expression and omics datasets from ArrayExpress and BioStudies with gene disambiguation and quality assessment. Use for finding RNA-seq/microarray datasets by organism/tissue/condition, comparing across studies (case-control, time-series, dose-response), and assessing dataset suitability before downloading. Always uses English search terms.
$ install --global
skillsauthnpx skillsauth add mims-harvard/tooluniverse tooluniverse-expression-data-retrievalInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 22, 2026, 6:20 AM223.2s3 files scanned
SKILL.md
- name:
- tooluniverse-expression-data-retrieval
- description:
- Retrieve gene expression and omics datasets from ArrayExpress and BioStudies with gene disambiguation and quality assessment. Use for finding RNA-seq/microarray datasets by organism/tissue/condition, comparing across studies (case-control, time-series, dose-response), and assessing dataset suitability before downloading. Always uses English search terms.
- disable-model-invocation:
- true
Gene Expression & Omics Data Retrieval
Retrieve gene expression experiments and multi-omics datasets with disambiguation and quality assessment.
IMPORTANT: Always use English terms in tool calls. Respond in the user's language.
LOOK UP DON'T GUESS: Never assume which datasets exist or their accessions. Always search to confirm.
Domain Reasoning
Before retrieving, determine: organism, tissue, experimental design (case-control/time-series/dose-response). These affect which database to search and how to interpret results. RNA-seq provides wider dynamic range; microarray has extensive legacy data. Prioritize experiments with >=3 biological replicates, complete annotations, and both raw+processed data.
Workflow
Phase 0: Clarify (if ambiguous) → Phase 1: Disambiguate → Phase 2: Search & Retrieve → Phase 3: Report
Phase 0: Clarification (When Needed)
Ask ONLY if: gene name ambiguous, tissue/condition unclear, organism not specified. Skip for: specific accessions (E-MTAB-, E-GEOD-, S-BSST*), clear disease/tissue+organism, explicit platform requests.
Phase 1: Query Disambiguation
Resolve official gene symbol (HGNC for human, MGI for mouse). Note common aliases for search expansion.
| User Query Type | Search Strategy | |-----------------|-----------------| | Specific accession | Direct retrieval | | Gene + condition | "[gene] [condition]" + species filter | | Disease only | "[disease]" + species filter | | Technology-specific | Add platform keywords |
Phase 2: Data Retrieval (Internal)
Search silently. Do NOT narrate the process.
# ArrayExpress search
result = tu.tools.arrayexpress_search_experiments(keywords="[gene/disease]", species="[species]", limit=20)
# Get experiment details, samples, files
details = tu.tools.arrayexpress_get_experiment(accession=accession)
samples = tu.tools.arrayexpress_get_experiment_samples(accession=accession)
files = tu.tools.arrayexpress_get_experiment_files(accession=accession)
# BioStudies for multi-omics
biostudies = tu.tools.biostudies_search(query="[keywords]", limit=10)
study = tu.tools.biostudies_get_study(accession=study_accession)
study_files = tu.tools.biostudies_get_study_files(accession=study_accession)
Fallback Chains
| Primary | Fallback | |---------|----------| | ArrayExpress search | BioStudies search | | arrayexpress_get_experiment | biostudies_get_study | | arrayexpress_get_experiment_files | Note "Files unavailable" |
Phase 3: Report Dataset Profile
Present as a Dataset Search Report. Hide search process. Include:
- Search Summary: query, databases searched, result count
- Top Experiments (per experiment):
- Accession, organism, type (RNA-seq/microarray), platform, sample count, date
- Description, experimental design (conditions, replicates, tissue)
- Sample groups table, data files table
- Quality assessment (●●●/●●○/●○○)
- Multi-Omics Studies (from BioStudies): accession, type, data types included
- Summary Table: all experiments ranked
- Recommendations: best dataset for user's purpose, integration notes
- Data Access: download links, database URLs
Data Quality Tiers
| Tier | Symbol | Criteria | |------|--------|----------| | High | ●●● | >=3 bio replicates, complete metadata, processed data available | | Medium | ●●○ | 2-3 replicates OR some metadata gaps | | Low | ●○○ | No replicates, sparse metadata, or access issues | | Caution | ○○○ | Single sample, no replication, outdated platform |
Reasoning Framework
Dataset quality: Prioritize >=3 biological replicates, complete annotations, both raw+processed data. Single-replicate experiments can inform but not be sole evidence.
Platform comparison: RNA-seq = wider dynamic range, novel transcripts. Microarray = probe-limited but extensive legacy data. Cross-platform combining requires batch correction.
Metadata scoring: Rate 0-5 on: (1) sample annotations, (2) design documented, (3) pipeline described, (4) raw data deposited, (5) publication linked. Score <=2 warrants caution.
GEO vs ArrayExpress: GEO has broader coverage (older studies); ArrayExpress enforces stricter metadata. BioStudies captures multi-omics. Search both.
Synthesis Questions
- Does the dataset have sufficient replication and metadata for the intended analysis?
- Are there batch effects or confounding variables?
- Do multiple datasets show concordant patterns, and can they be integrated?
Error Handling
| Error | Response | |-------|----------| | "No experiments found" | Broaden keywords, remove species filter, try synonyms | | "Accession not found" | Verify format, check if withdrawn | | "Files not available" | Note: "Data files restricted by submitter" | | "API timeout" | Retry once, note "(metadata retrieval incomplete)" |
Tool Reference
ArrayExpress: arrayexpress_search_experiments (search), arrayexpress_get_experiment (metadata), arrayexpress_get_experiment_files (downloads), arrayexpress_get_experiment_samples (annotations)
BioStudies: biostudies_search (search), biostudies_get_study (metadata+sections), biostudies_get_study_files (files)
Additional Sources:
GEO_search_rnaseq_datasets/geo_search_datasets-- GEO (largest RNA-seq repo)OmicsDI_search_datasets-- cross-repository aggregation (GEO+ArrayExpress+PRIDE+MassIVE)GTEx_get_expression_summary-- baseline tissue expression (54 normal tissues, param:gene_symbol)ENAPortal_search_studies-- sequencing studies (param:querywithdescription="...")CxGDisc_search_datasets-- single-cell datasets (needs exact disease ontology terms)PubMed_search_articles-- dataset discovery via publications
Search Parameters
ArrayExpress: keywords (free text), species (scientific name), array (platform filter), limit
BioStudies: query (free text), limit
Related Skills
mims-harvard/tooluniverse-self-review
tools
VerifiedTrustedCommunity
Generate the success criteria for a task or question, then review work against them. Given a task, goal, or open-ended question, decompose it into scenarios, evaluation perspectives, and fine-grained weighted YES/NO criteria using the Recursive Expansion Tree (RET) method; if work is supplied, score it criterion-by-criterion and surface what is missing or could be better. Use when asked to self-review or check your own work, judge whether a task is done well or completely, build a definition-of-done or completeness checklist, create an evaluation rubric or grading criteria, score or grade answers to a question, set up an LLM-as-judge rubric, or when the user mentions self-review, completeness check, success criteria, evaluation criteria, scoring rubric, Qworld, or the RET algorithm.
1,583SKILL.mdUpdated Jul 22, 2026
mims-harvard/tooluniverse-peptide-target-deorphanization
tools
VerifiedTrustedCommunity
Find the real protein target(s) of a peptide from its sequence — peptide target deorphanization / off-target identification, for ANY target class (GPCR, ion channel, protease, cytokine/growth-factor receptor, enzyme, integrin), not only GPCRs. Use when a peptide has a phenotype but does not bind its hypothesized target, when a peptide binds a target in one species or assay but not another, or to screen candidate targets for an orphan peptide. A target-class router steers a multi-route keyless pipeline (PROSITE/ELM motif, BLAST homology, HGNC/InterPro/GPCRdb/GtoPdb target-family enumeration, OpenTargets phenotype anchor, EnsemblCompara/Alliance cross-species reconciliation) plus optional NVIDIA-NIM co-folding (Boltz2, AlphaFold2-Multimer, OpenFold3) for structural confirmation.
1,583SKILL.mdUpdated Jul 22, 2026
mims-harvard/tooluniverse-cs-setup
tools
VerifiedTrustedCommunity
Install or update ToolUniverse in Claude Science — create the conda env, install the tooluniverse pip package, and (re)build the tooluniverse-research skill by fetching the current workflow library from GitHub. Use for first-time setup, upgrading the ToolUniverse version, refreshing the bundled workflows after an upstream release, or reinstalling on a new machine.
1,583SKILL.mdUpdated Jul 22, 2026
mims-harvard/tooluniverse-codex-plugin
tools
VerifiedTrustedCommunity
Install, set up, verify, update, pin, uninstall, or troubleshoot the ToolUniverse plugin on OpenAI Codex. ALWAYS consult this skill for any of those — don't answer from memory, because the exact marketplace name (mims-harvard/ToolUniverse), the "codex plugin marketplace add" then "codex plugin add -m tooluniverse" flow, Codex's startup auto-upgrade behavior, the uvx tooluniverse MCP server, and the API-key env vars are easy to get wrong. Use it whenever someone wants to get ToolUniverse (or "the 1000+ scientific tools" / "the harvard tools") working on Codex, says the Codex plugin or its tools/skills won't load, hits a uvx or MCP-server startup error, asks how Codex updates it, wants to pin or remove it, or finds it running an old tool version — even if they never say the word "plugin". Not for the Claude Code plugin (use tooluniverse-claude-code-plugin), for running research with the tools, or for authoring new tools or skills.
1,583SKILL.mdUpdated Jul 22, 2026