minimax-ai/bio-research-forge

Coordinate a life-science research request that spans design, public databases, omics, statistics, writing, figures, reproducibility, or independent review. Use for multi-stage research work; do not use for a single narrow lookup.

Independently review a life-science manuscript, analysis, figure package, or repository for claim support, citation validity, numeric traceability, figure-code-data consistency, reproducibility, and privacy. Use as a final gate, not as author self-approval.

Audit whether biological materials, sampling, controls, replication, and measurements can answer a proposed question before experiments or analysis. Use for study planning and Go/No-Go decisions.

Detect and selectively use local life-science desktop or structural tools, including safe PyMOL rendering and explicit file opening in SnapGene, Cytoscape, or Fiji. Use when a user asks to work with these installed applications; never install tools silently or accept arbitrary commands.

Draft or restructure life-science Introduction and Discussion sections from supplied claims, results, figures, and verified literature. Use for argument construction; do not invent evidence, citations, or causal strength.

Plan, audit, or interpret public or user-authorized sequencing and omics workflows, including bulk RNA-seq, single-cell, amplicon, metagenomic, variant, and metabolomic analyses. Use only after design and metadata fit are checked.

Query public biological databases for genes, proteins, domains, structures, literature, networks, motifs, or general Solanaceae metadata through the bundled allowlisted MCP. Use for evidence lookup; never route private or pepper-specific data through it.

Design or review statistical, mixed-model, Bayesian, or machine-learning analyses for life-science data. Use when the main risk is estimand, dependence, model choice, diagnostics, leakage, or uncertainty.

Turn a life-science analysis into a cleanly rerunnable workflow with protected raw data, centralized parameters, fixed seeds, environment capture, provenance, and verified outputs. Use for publication or handoff-quality analysis.

Create and audit common RNA-seq result figures locally, including volcano, PCA, heatmap, expression boxplot, and enrichment dotplot, with PNG/PDF delivery and inline conversation preview. Use for RNA result plotting from user-selected tables; do not use private bundled datasets.

Create, revise, or audit publication-grade life-science figures with source-data traceability, export QA, and a PNG preview shown directly in the agent conversation. Use for manuscript figures, not dashboards or decorative infographics.

Decide whether a life-science computation should run locally, on a controlled HPC over SSH, or on an external cloud GPU based on data sensitivity, scale, cost, and reproducibility. Use before moving data or launching remote work.