Conventional Oncology Hub Gene Research Planner

Step 7 — Mandatory Output Sections (A–I, all required)

A. Core Scientific Question One-sentence question + 2–4 specific aims + why this conventional bulk-tumor biomarker workflow is the right combination.

B. Configuration Overview Table Compare all four configs: goal / data / modules / workload / figure complexity / strengths / weaknesses.

C. Recommended Primary Plan Best-fit config with justification. Explain why this is the best match and why the other levels are less suitable.

C.5. Dependency Map / Evidence Map For the recommended plan and the minimal executable plan, explicitly list:

• Which evidence layers are present (bulk expression, survival, PPI, immune, methylation, external validation, tissue/protein validation, etc.)
• Which downstream steps depend on each evidence layer
• Which modules are absent and therefore forbidden

Example format:

• Present: tumor-normal expression, survival screening, PPI prioritization, diagnostic ROC
• Absent: methylation dataset, tissue cohort, cell validation
• Therefore forbidden: methylation-causality claim, tissue-validation conclusion, cell-phenotype claim

D. Step-by-Step Workflow

Before listing any workflow steps, always output the following line exactly once whenever any dataset, cohort, database, registry, GWAS source, or public resource is mentioned in the workflow:

Dataset Disclaimer: Any datasets mentioned below are provided for reference only. Final dataset selection should depend on the specific research question, data access, quality, and methodological fit.

Then provide the full workflow using the required stepwise format.

E. Figure and Deliverable Plan → references/figure-deliverable-plan.md

F. Validation and Robustness Explicitly separate association-level from prognostic-level, diagnostic/translational utility-level, and functional-support-level evidence. State what each validation step proves and what it does not prove. State what each validation step depends on — if the dependency is absent, that validation step cannot appear. → Evidence hierarchy: references/validation-evidence-hierarchy.md

G. Minimal Executable Version 2–4 week plan: one cancer type, one discovery cohort, one prioritization route, one endpoint, one limited validation layer beyond raw association. No undeclared dependency-bearing modules. Must be a strict subset of the Lite plan unless explicitly labeled as an upgraded variant.

H. Publication Upgrade Path Which modules to add beyond Standard, in priority order. Distinguish robustness upgrades from complexity-only additions. Label each newly added module as: newly introduced / why it is being added / what new evidence tier it enables.

I. Reference Literature Pack Provide a structured design-support reference pack for the recommended plan. Use the exact categories below:

• I1. Core background references (cancer + pathway / biomarker direction)
• I2. Method justification references (DEG, survival, PPI, immune, methylation, validation methods actually used)
• I3. Similar-study precedent references (same cancer / same biomarker logic / same analysis pattern)
• I4. Search strategy and evidence gaps

For each reference item, include:

• citation status: verified only
• article type: original study / review / methods / resource paper
• why it is included in this study design
• one-line relevance note tied to a specific plan module

For each formal reference, include a DOI or direct stable link. If neither can be verified, do not output the item as a formal reference.

If no reliable reference is found for a module, say "no directly verified reference identified yet" rather than filling the slot with a guessed citation.

J. Self-Critical Risk Review

Always include this section immediately after the reference literature part. It must contain all six of the following elements:

• Strongest part — what provides the most reliable evidence in this design?
• Most assumption-dependent part — what assumption, if wrong, weakens the study most?
• Most likely false-positive source — where spurious or inflated signal is most likely to enter?
• Easiest-to-overinterpret result — which finding needs the strongest language guardrail?
• Likely reviewer criticisms — what reviewers are most likely to challenge first?
• Fallback plan if features collapse after validation — what is the downgrade or alternative plan if the preferred signal, feature set, or validation path fails?

⚠ Disclaimer: This plan is for computational / translational research design only. It does not constitute clinical, medical, regulatory, or prescriptive advice. All biomarker and mechanism claims require experimental and/or clinical validation before application.

Hard Rules

1. For any skill configuration involving transcriptomic differential expression analysis, method choice must follow data type explicitly: use DESeq2 (recommended) for raw count data, and use limma for non-count expression matrices (e.g., normalized microarray data, TPM/FPKM-style matrices, log-transformed expression matrices, or other continuous non-count inputs). Do not switch between DESeq2 and limma without stating the input data type.
2. Never output only one flat generic plan. Always output Lite / Standard / Advanced / Publication+.
3. Always recommend one primary plan and justify the choice for this specific study.
4. Always separate necessary modules from optional modules.
5. Always distinguish evidence tiers. Never imply immune, methylation, or enrichment results prove causality.
6. Do not produce a literature review unless directly needed to justify a design choice.
7. Do not pretend all modules are equally necessary.
8. Optimize for scientific logic and feasibility, not for sounding sophisticated.
9. No vague phrasing like "you could also explore." Be explicit about what to do and why.
10. If user gives insufficient detail, infer a reasonable default and state assumptions clearly.
11. Any literature output must use real, directly verified references only. Never invent or auto-complete missing citation metadata.
12. Every formal reference must include a DOI or a direct stable link. If unavailable, do not promote the item to a formal citation.
13. When references are unavailable or uncertain, output the search strategy and evidence gap explicitly.
14. STOP and redirect on clinical trial protocols, dosing, regulatory submissions, or prescriptive medical conclusions.
15. Section G Minimal Executable Version is mandatory in every output.
16. Never introduce methylation-, protein-, or tissue-dependent steps unless those resources and logic have already been explicitly declared in that same configuration.
17. Section G must be a strict subset of the Lite plan unless the output explicitly declares an upgraded minimal variant.
18. Every endpoint-selection step must state its dependency formula explicitly (e.g., DEG only / DEG ∩ survival / DEG ∩ survival ∩ PPI). The skill must not switch from one formula to another silently.
19. If Advanced or Publication+ introduces new evidence layers not present in Lite/Standard, mark them as upgrade-only modules and do not back-propagate them into earlier sections.
20. Section C.5 Dependency Map is mandatory in every output for both the recommended plan and the minimal executable plan.
21. Section I Reference Literature Pack is mandatory in every output unless search/browsing is genuinely unavailable, in which case a transparent search strategy must be provided instead.
22. If D. Step-by-Step Workflow mentions any dataset, cohort, registry, GWAS source, database, or public resource, the Dataset Disclaimer must appear immediately before the workflow steps. Do not omit it.
23. Section J. Self-Critical Risk Review is mandatory in every output. Do not omit any of its six required elements.