AI Agent Hub
Back to skills
Comparative Network Toxicology Shared Mechanism Research Planner icon

Comparative Network Toxicology Shared Mechanism Research Planner

Professional Updated 2026.08.29

Paste the following prompt into your AI chat to install this skill:

Please follow https://skillhub.cn/install/skillhub.md to install the @user_c7479c7a/comparative-network-toxicology-shared-mechanism-reference-grounded skill into your AI assistant.

About this skill

Problem

Comparing two exposures under one toxic phenotype often produces tool lists or vague reviews instead of an executable design with shared versus specific targets, evidence layers, and validation logic.

How It Works

The skill generates a structured research plan through a fixed workflow:
- Validates inputs such as exposure A + exposure B + shared toxic phenotype + validation emphasis
- Selects patterns for shared/specific mapping, enrichment, PPI, docking, or orthogonal cross-checks
- Outputs Lite / Standard / Advanced / Publication+ workload configs and recommends one primary path
- Builds stepwise workflow, figure plan, minimal executable version, and publication upgrade path
- Adds a reference pack and self-critical risk review, requiring verifiable citations and explicit evidence gaps

Scope Notes

It is for network-toxicology research design, not clinical diagnosis, individual exposure advice, pure wet-lab work, or pure epidemiology. If references or data cannot be verified, it states the gap instead of inventing conclusions.

Use Cases

  • Compare parent pesticide and metabolite hepatotoxicity targets, decompose shared versus specific targets, and draft four workload configs.
  • Before a PFAS analog cardiotoxicity paper, design shared-specific pathways, PPI hubs, and docking validation workflow.
  • When reviewers demand stronger evidence, add a verified reference pack, dependency check, and risk review to a plasticizer neurotoxicity plan.
  • For co-exposed liver injury pollutants, plan enrichment, hub screening, docking support, and orthogonal validation priorities.

Best For

  • Toxicology PhD students: need exposure-target-pathway comparative designs instead of scattered tool lists.
  • Pharma or testing-lab R&D engineers: need reviewable, reproducible shared-toxicity mechanism plans.
  • Computational toxicology researchers: care about evidence dependencies across PPI, enrichment, docking, and cross-checks.
  • Journal paper authors: need method logic, verified literature support, and risk boundaries to avoid overclaiming.