tooluniverse-literature-deep-research

# Literature Deep Research

Systematic literature research: disambiguate, search with collision-aware queries, grade evidence, produce structured reports.

**KEY PRINCIPLES**: (1) Disambiguate first (2) Right-size deliverable (3) Grade every claim T1-T4 (4) All sections mandatory even if "limited evidence" (5) Source attribution for every claim (6) English-first queries, respond in user's language (7) Report = deliverable, not search log

---

## LOOK UP, DON'T GUESS

Search PubMed/EuropePMC FIRST before reasoning. A published paper beats memory.

**Factoid search strategy:**
1. Extract KEY TERMS (most specific nouns/verbs)
2. `EuropePMC_search_articles(query="term1 term2 term3", limit=5)`
3. No results -> BROADEN (remove most restrictive term)
4. Too many -> NARROW (add specific terms)
5. Answer usually in abstract of top results
6. Failed query -> try DIFFERENT TERMS/synonyms, don't repeat

---

## COMPUTE, DON'T DESCRIBE
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.

## Workflow

```
Phase 0: Clarify + Mode Select → Phase 1: Disambiguate + Profile → Phase 2: Literature Search → Phase 3: Report
```

---

## Phase 0: Mode Selection

| Mode | When | Deliverable |
|------|------|-------------|
| **Factoid** | Single concrete question | 1-page fact-check report + bibliography |
| **Mini-review** | Narrow topic | 1-3 page narrative |
| **Full Deep-Research** | Comprehensive overview | 15-section report + bibliography |

### Factoid Mode (Fast Path)
```markdown
# [TOPIC]: Fact-check Report
## Question / ## Answer (with evidence rating) / ## Source(s) / ## Verification Notes / ## Limitations
```

### Domain Detection

| Pattern | Domain | Action |
|---------|--------|--------|
| Gene/protein symbol | Biological target | Full bio disambiguation |
| Drug name | Drug | Drug disambiguation (1.5) |
| Disease name | Disease | Disease disambiguation (1.6) |
| CS/ML topic | General academic | Skip bio tools, literature-only |
| Cross-domain | Interdisciplinary | Resolve each entity in its domain |

### Cross-Skill Delegation
- Gene/protein deep-dive: `tooluniverse-target-research`
- Drug profile: `tooluniverse-drug-research`
- Disease profile: `tooluniverse-disease-research`

Use this skill for **literature synthesis**. Use specialized skills for **entity profiling**. For max depth, run both.

---

## Phase 1: Subject Disambiguation + Profile

### 1.1 Biological Target Resolution
```
UniProt_search → UniProt_get_entry_by_accession → UniProt_id_mapping
ensembl_lookup_gene → MyGene_get_gene_annotation
```

### 1.2 Naming Collision Detection
Check first 20 results. If >20% off-topic, build negative filter: `NOT [collision1] NOT [collision2]`.
Gene family: `"ADAR" NOT "ADAR2" NOT "ADARB1"`. Cross-domain: add context terms.

### 1.3 Baseline Profile (Bio Targets)
```
InterPro_get_protein_domains, UniProt_get_ptm_processing_by_accession, HPA_get_subcellular_location,
GTEx_get_median_gene_expression, GO_get_annotations_for_gene, Reactome_map_uniprot_to_pathways,
STRING_get_protein_interactions, intact_get_interactions, OpenTargets_get_target_tractability_by_ensemblID
```
GPCR targets: delegate to `tooluniverse-target-research`.

### 1.5 Drug Disambiguation
**Identity**: `OpenTargets_get_drug_chembId_by_generic_name`, `ChEMBL_get_drug`, `PubChem_get_CID_by_compound_name`, `drugbank_get_drug_basic_info_by_drug_name_or_id`
**Targets**: `ChEMBL_get_drug_mechanisms`, `OpenTargets_get_associated_targets_by_drug_chemblId`, `DGIdb_get_drug_gene_interactions`
**Safety**: `OpenTargets_get_drug_adverse_events_by_chemblId`, `OpenTargets_get_drug_indications_by_chemblId`, `search_clinical_trials`

### 1.6 Disease Disambiguation
```
OpenTargets disease search → EFO/MONDO IDs
DisGeNET_get_disease_genes, DisGeNET_search_disease
CTD_get_disease_chemicals
```

### 1.7 Compound Queries (e.g., "metformin in breast cancer")
Resolve both entities, then cross-reference via CTD_get_chemical_gene_interactions, CTD_get_chemical_diseases, OpenTargets drug-target/drug-disease tools. Intersect shared targets/pathways.

### 1.8 General Academic / 1.9 Interdisciplinary
Non-bio: skip bio tools, use ArXiv/DBLP/OSF. Cross-domain: resolve bio entities with 1.1-1.3, search CS/general in parallel, merge and cross-reference.

---

## Phase 2: Literature Search

**Methodology stays internal. Report shows findings, not process.**

### 2.1 Query Strategy
**Step 1: Seeds** (15-30 core papers): domain-specific title searches with date/sort filters.
**Step 2: Citation expansion**: `PubMed_get_cited_by`, `EuropePMC_get_citations/references`, `PubMed_get_related`, `SemanticScholar_get_recommendations`, `OpenCitations_get_citations`
**Step 3: Collision-filtered broader queries**: `"[TERM]" AND ([context]) NOT [collision]`

### 2.2 Literature Tools — core set + adaptive by domain

Run the **core multi-field set on every review** (catches what any single index misses), then add the domain rows that match the subject. Don't fire every source blindly — 6–10 well-chosen indexes beat 20 noisy ones.

**ALWAYS run (core, all disciplines)**: `PubMed_search_articles`, `EuropePMC_search_articles`, `openalex_search_works` (query param `search`/`query`) **or** `openalex_literature_search` (query param `search_keywords`) — pick one and match its param; mixing them silently returns off-topic results — and `SemanticScholar_search_papers`

**Then add by domain:**

| Domain | Add these | Notes |
|--------|-----------|-------|
| Biomedical / clinical | `PMC_search_papers` (full text), `PubTator3_LiteratureSearch` (entity & `relations:` queries), `PubMed_Guidelines_Search` (clinical guidelines) | PubTator normalizes gene/drug/disease entities |
| Biology (ecology/evolution/plant) | **EuropePMC as PRIMARY** + OpenAlex