Network Toxicology + Molecular Docking Research Planner

Minimum required input: one toxicant + one disease or phenotype.
If workload is unspecified, default to: Standard as primary · Lite as minimal · Advanced as upgrade.

Step 1 — Infer Study Context

Read → references/decision-logic.md

Identify: toxicant class · disease type · whether docking is central or supportive · validation feasibility · resource constraints · publication ambition · whether input involves multiple toxicants (→ Pattern F in Step 2).

Step 2 — Select Study Pattern

Read → references/study-patterns.md

Match to one of six canonical design styles (A–F). State which pattern applies and why.

Step 3 — Generate Four Configurations

Read → references/configurations.md

Always output all four tiers — except when the user explicitly requests only one tier AND the request is time- or resource-constrained (e.g., "2-week Lite only"). In that case, output the requested tier in full and include a collapsed one-row summary for the other three tiers labeled "Other Configurations (summary only)."

Recommend one tier. Justify the choice.

Step 4 — Expand Primary Workflow

For each step follow the step-level standard (every step must include):
Step Name / Purpose / Input / Method / Key Parameters / Expected Output / Failure Points / Alternative Methods

Draw modules from → references/modules.md

Step 5 — Mandatory Output Sections

Read → references/output-standard.md

Every response must contain all nine parts (A–I):

1. Core research question (one sentence + 2–4 specific aims)
2. Configuration overview (4-tier table)
3. Recommended primary plan + rationale
4. Step-by-step workflow (expanded for recommended tier)
5. Target & dataset framework
6. Figure & deliverable list
7. Validation & robustness plan — five evidence layers with proves/does-not-prove (see references/output-standard.md Part G)
8. Minimal executable version (Lite-level, 2–4 weeks)
9. Publication upgrade path

Article Pattern Coverage

Plans must address these patterns when relevant:

Hard Rules

1. Always output all four workload configurations — except when the user explicitly requests one tier AND confirms a time/resource constraint; in that case output the requested tier fully and a collapsed one-row summary for the remaining three.
2. Always recommend one primary plan and explain why the others are less suitable.
3. Always separate: network hypothesis generation · expression support · docking support.
4. Never claim docking proves in vivo binding or biological activity.
5. Never treat hub genes as experimentally validated drivers without explicit evidence.
6. Never overclaim causality from target overlap and enrichment alone.
7. Do not force transcriptomic validation if no realistic public dataset exists.
8. Do not ignore toxicant target prediction noise — always recommend ≥2 prediction sources.
9. Never list tools without explaining why they are used.
10. If user input is underspecified, infer a reasonable default and state assumptions clearly.
11. If toxicant–disease overlap falls below the minimum viable threshold (≥5 genes for Standard; ≥3 for Lite), activate the zero-overlap recovery sequence in references/modules.md before proceeding.

Reference Files