tooluniverse-epigenomics

mims-harvard/tooluniverse · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/mims-harvard/tooluniverse --skill tooluniverse-epigenomics
0 commentsdiscussion
summary

Production-ready skill combining Python computation (pandas, scipy, numpy, pysam, statsmodels) with ToolUniverse annotation tools for epigenomics analysis.

skill.md

Genomics and Epigenomics Data Processing

Production-ready skill combining Python computation (pandas, scipy, numpy, pysam, statsmodels) with ToolUniverse annotation tools for epigenomics analysis.

LOOK UP, DON'T GUESS

When uncertain about any scientific fact, SEARCH databases first.

When to Use

Methylation data, ChIP-seq peaks, ATAC-seq, multi-omics integration, genome-wide epigenomic statistics. Keywords: methylation, CpG, ChIP-seq, ATAC-seq, histone, chromatin, epigenetic.

NOT for: RNA-seq DEG, variant calling, gene enrichment, protein structure.


Key Principles

  1. Data-first - Load/inspect before analysis
  2. Question-driven - Extract specific numeric answer
  3. Coordinate system awareness - Track genome build (hg19/hg38/mm10), chr prefix
  4. Statistical rigor - FDR correction, effect size filtering
  5. CpG identification - Parse Illumina probe IDs, genomic coordinates

Workflow

Phase 0: Question Parsing

Identify data files, specific statistic, thresholds, genome build. Categorize by keywords. See ANALYSIS_PROCEDURES.md for decision tree.

Phase 1: Methylation Processing

  • Load beta/M-value matrix (CSV/TSV/parquet/HDF5)
  • Filter by variance, missing rate, probe type, chromosome, CpG island relation
  • Differential methylation: T-test/Wilcoxon between groups + FDR
  • Age-related CpG: Pearson/Spearman correlation + FDR
  • Chromosome density: CpG count / chromosome length

Phase 2: ChIP-seq Peak Analysis

  • Load BED/narrowPeak/broadPeak, normalize chromosomes
  • Peak stats, annotation to genes, overlap analysis (Jaccard)

Phase 3: ATAC-seq

  • NFR detection (<150bp peaks), region classification

Phase 4: Multi-Omics Integration

  • Methylation-expression correlation per probe-gene (Pearson/Spearman + FDR)
  • ChIP-seq + expression: promoter peaks vs expression levels

Phase 5: Clinical Data

  • Missing data analysis across modalities, complete case identification

Phase 6: ToolUniverse Annotation

ENCODE tools:

  • ENCODE_search_rnaseq_experiments: assay_type ("total RNA-seq" default; fall back to "polyA plus RNA-seq"), biosample, limit
  • ENCODE_search_histone_experiments: target (e.g., "H3K27ac"), cell_type/tissue/biosample, limit

GEO tools: GEO_search_rnaseq_datasets, GEO_search_atacseq_datasets -- both accept limit or max_results

GTEx tools:

  • GTEx_get_median_gene_expression: gene_symbol (NOT Ensembl ID)
  • GTEx_query_eqtl: gene_symbol, tissue_id (case-sensitive exact, e.g., "Whole_Blood")

Other: ensembl_lookup_gene (requires species='homo_sapiens'), ensembl_get_regulatory_features (NO "chr" prefix), SCREEN_get_regulatory_elements, ChIPAtlas_* (requires operation param), SRA_search_experiments (library_strategy: "ChIP-Seq"/"Bisulfite-Seq"/"ATAC-seq")

Phase 7: Genome-Wide Statistics

Global mean/median beta, probe variance, chromosome density, DMP counts.

See CODE_REFERENCE.md for full implementations.


Common Patterns

Pattern Key Steps
Differential methylation Filter probes → groups → t-test → FDR → threshold
Age-related CpG density Correlate with age → FDR → map to chr → density ratio
Multi-omics missing data Extract IDs → intersect → check NaN → complete case count
ChIP-seq annotation Load peaks → annotate genes → classify regions
Methylation-expression Align samples → correlate → FDR → anti-correlations

GTEx Tissue IDs

Whole_Blood, Liver, Lung, Breast_Mammary_Tissue, Brain_Cortex, Heart_Left_Ventricle, Kidney_Cortex, Thyroid, Adipose_Subcutaneous, Muscle_Skeletal


Evidence Grading

Grade Criteria
Strong padj < 0.01 AND abs(delta-beta) >= 0.2, replicated
Moderate padj < 0.05 AND abs(delta-beta) >= 0.1
Weak padj < 0.05 but delta-beta < 0.1
Insufficient padj >= 0.05 or no replication

Delta-beta >= 0.2 = strong effect. ChIP-seq: q < 0.01, FE >= 2 for confidence. ATAC-seq NFR < 150bp = active regulatory. Always apply BH FDR. Verify genome build consistency.


Limitations

  • No pybedtools/pyBigWig: pure Python intervals
  • Illumina-centric (450K/EPIC); uses t-test/Wilcoxon (not limma)
  • No peak calling (assumes pre-called)
  • API rate limits: ~20 genes per batch

Reference Files

CODE_REFERENCE.md, TOOLS_REFERENCE.md, ANALYSIS_PROCEDURES.md, QUICK_START.md

how to use tooluniverse-epigenomics

How to use tooluniverse-epigenomics on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your development machine
  • Node.js version 16.0+ with npm package manager (verify with node --version)
  • Active project directory or workspace where you want to add tooluniverse-epigenomics
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/mims-harvard/tooluniverse --skill tooluniverse-epigenomics

The skills CLI fetches tooluniverse-epigenomics from GitHub repository mims-harvard/tooluniverse and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/tooluniverse-epigenomics

Reload or restart Cursor to activate tooluniverse-epigenomics. Access the skill through slash commands (e.g., /tooluniverse-epigenomics) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

User Story & Requirements Generation

Create detailed user stories, acceptance criteria, and feature specs

Example

Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios

Reduce spec writing time by 50%, ensure comprehensive coverage

Competitive Analysis

Research competitors, compare features, identify gaps

Example

Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities

Complete competitive research in 2 hours instead of 2 days

Roadmap Prioritization

Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs

Example

Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale

Make data-driven prioritization decisions faster

Stakeholder Communication

Draft PRDs, status updates, and stakeholder presentations

Example

Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement

Save 3-5 hours/week on communication overhead

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client
  • Access to product documentation and roadmap tools (Jira, Notion, etc.)
  • Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
  • Stakeholder contact information and communication channels

Time Estimate

30-60 minutes to see productivity improvements

Installation Steps

  1. 1.Install product management skill
  2. 2.Start with user story generation for known feature
  3. 3.Progress to competitive analysis: research 2-3 competitors
  4. 4.Use for roadmap prioritization: apply RICE/ICE scoring
  5. 5.Draft stakeholder communications and refine based on feedback
  6. 6.Build template library for recurring PM tasks
  7. 7.Share effective prompts with product team

Common Pitfalls

  • Not validating competitive research—verify facts before sharing
  • Accepting user stories without involving engineering team
  • Over-relying on frameworks without qualitative judgment
  • Not customizing outputs to company culture and communication style
  • Skipping stakeholder validation of generated requirements

Best Practices

✓ Do

  • +Validate research and competitive analysis with real data
  • +Collaborate with engineering when generating technical requirements
  • +Customize frameworks and templates to your company context
  • +Use skill for first drafts, refine with stakeholder input
  • +Document successful prompt patterns for PM tasks
  • +Combine AI efficiency with human judgment and intuition

✗ Don't

  • Don't publish competitive analysis without fact-checking
  • Don't finalize user stories without engineering review
  • Don't make prioritization decisions solely on AI scoring
  • Don't skip customer validation of generated requirements
  • Don't ignore company-specific context and culture

💡 Pro Tips

  • Provide context: company goals, constraints, customer feedback
  • Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
  • Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
  • Use skill for 70% generation + 30% customization to company needs

When to Use This

✓ Use When

Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.

✗ Avoid When

Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.

Learning Path

  1. 1Basic: user stories, feature specs, status updates
  2. 2Intermediate: competitive analysis, prioritization frameworks, PRDs
  3. 3Advanced: product strategy, go-to-market planning, OKR setting
  4. 4Expert: product vision, market positioning, business model innovation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.728 reviews
  • Evelyn Gupta· Dec 24, 2024

    tooluniverse-epigenomics fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Diego Wang· Dec 8, 2024

    I recommend tooluniverse-epigenomics for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Diya Lopez· Nov 27, 2024

    Keeps context tight: tooluniverse-epigenomics is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Michael Jackson· Nov 15, 2024

    We added tooluniverse-epigenomics from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • Lucas Reddy· Oct 18, 2024

    Registry listing for tooluniverse-epigenomics matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Ren Rahman· Oct 6, 2024

    Solid pick for teams standardizing on skills: tooluniverse-epigenomics is focused, and the summary matches what you get after install.

  • Yash Thakker· Sep 25, 2024

    Keeps context tight: tooluniverse-epigenomics is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Rahul Santra· Sep 21, 2024

    Useful defaults in tooluniverse-epigenomics — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Dhruvi Jain· Aug 16, 2024

    Registry listing for tooluniverse-epigenomics matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Pratham Ware· Aug 12, 2024

    tooluniverse-epigenomics has been reliable in day-to-day use. Documentation quality is above average for community skills.

showing 1-10 of 28

1 / 3