From mims-harvard-tooluniverse
Analyzes microbiome and metagenomics data using MGnify, GTDB, ENA, literature tools. Searches studies by biome/keyword, retrieves taxonomic profiles, functional annotations, classifies genomes, finds publications.
npx claudepluginhub joshuarweaver/cascade-data-analytics --plugin mims-harvard-tooluniverseThis skill uses the workspace's default tool permissions.
Integrated pipeline for exploring microbiome studies, classifying taxa, assessing genome quality, linking microbial composition to clinical phenotypes, and interpreting findings through pathway analysis and literature context.
Conducts multi-round deep research on GitHub repos via API and web searches, generating markdown reports with executive summaries, timelines, metrics, and Mermaid diagrams.
Dynamically discovers and combines enabled skills into cohesive, unexpected delightful experiences like interactive HTML or themed artifacts. Activates on 'surprise me', inspiration, or boredom cues.
Generates images from structured JSON prompts via Python script execution. Supports reference images and aspect ratios for characters, scenes, products, visuals.
Integrated pipeline for exploring microbiome studies, classifying taxa, assessing genome quality, linking microbial composition to clinical phenotypes, and interpreting findings through pathway analysis and literature context.
Guiding principles:
When uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory.
When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.
| Database | Best For |
|---|---|
| MGnify | Processed metagenomics studies, taxonomic/functional results |
| GTDB | Standardized bacterial/archaeal taxonomy, species-level resolution |
| GMrepo | Gut species-to-human-health phenotype associations |
| ENA | Raw sequencing datasets and study metadata |
| KEGG | Pathway mapping for microbial functional annotations |
| PubMed/EuropePMC | Published microbiome-disease studies |
| CTD | Chemical-microbiome-disease relationships |
Phase 0: Parse query → organism, biome, phenotype, or accession
Phase 1: Study Discovery → MGnify_search_studies, ENAPortal_search_studies
Phase 2: Taxonomic Classification → GTDB_search_genomes, GTDB_get_species, GTDB_search_taxon
Phase 3: Genome Quality → MGnify_search_genomes, MGnify_get_genome (CheckM metrics)
Phase 4: Functional Annotation → MGnify GO terms + KEGG pathway mapping
Phase 5: Clinical Associations → GMrepo species-phenotype links
Phase 6: Literature → PubMed/EuropePMC + CTD gene-disease
Phase 7: Interpretation & Report Synthesis
Phase 1: ENA requires structured queries (e.g., study_title="*IBD*"), not free text. If ENA fails, fall back to MGnify.
Phase 2: GTDB uses its own naming (e.g., s__Bacteroides_A fragilis vs NCBI Bacteroides fragilis). Always note discrepancies. Use GTDB_search_taxon(operation="search_taxon", query=name).
Phase 3 - Quality tiers (MIMAG):
Phase 4 - Functional interpretation: Don't just list GO terms. Connect to biology:
| Functional Category | Key KEGG Pathways | Significance |
|---|---|---|
| SCFA production | map00650, map00640 | Gut barrier, anti-inflammatory |
| LPS biosynthesis | map00540 | Pro-inflammatory, endotoxemia |
| Bile acid metabolism | map00120 | Fat absorption, FXR signaling |
| Tryptophan metabolism | map00380 | Serotonin, AhR, immune |
| Vitamin biosynthesis | map00730/740/760 | Host nutritional contribution |
Use kegg_search_pathway(keyword=...) (NOT query). Pathway IDs need organism prefix (hsa, ko, eco), NOT bare map.
Phase 5: GMrepo uses MeSH terms: "Crohn Disease" not "IBD", "Colitis, Ulcerative" not "UC", "Colorectal Neoplasms" not "colorectal cancer". Try NCBI taxon IDs if species name fails.
Phase 6 - Evidence grading:
Phase 7 - Report: Executive summary, study landscape, GTDB taxonomy, functional interpretation (not GO term lists), clinical relevance with evidence grades, mechanistic model, genome catalog with quality tiers, data gaps.