wu-yc/labclaw/tooluniverse-disease-research

User: "Research Parkinson's disease"
 
Agent Actions (internal, not shown to user):
1. Create "parkinsons_disease_research_report.md" with template
2. Research DIM 1 → Update Identity section
3. Research DIM 2 → Update Clinical section
4. ... continue for all 10 dimensions
5. Present final report to user

# Disease Research Report: {Disease Name}
 
**Report Generated**: {date}
**Disease Identifiers**: (to be filled)
 
---
 
## Executive Summary
 
(Brief 3-5 sentence overview - fill after all research complete)
 
---
 
## 1. Disease Identity & Classification
 
### Ontology Identifiers
| System | ID | Source |
|--------|-----|--------|
| EFO | | |
| ICD-10 | | |
| UMLS CUI | | |
| SNOMED CT | | |
 
### Synonyms & Alternative Names
-(list with source)
 
### Disease Hierarchy
-Parent: 
-Subtypes:
 
**Sources**: (list tools used)
 
---
 
## 2. Clinical Presentation
 
### Phenotypes (HPO)
| HPO ID | Phenotype | Description | Source |
|--------|-----------|-------------|--------|
 
### Symptoms & Signs
-(list with source)
 
### Diagnostic Criteria
-(from literature/MedlinePlus)
 
**Sources**: (list tools used)
 
---
 
## 3. Genetic & Molecular Basis
 
### Associated Genes
| Gene | Score | Ensembl ID | Evidence | Source |
|------|-------|------------|----------|--------|
 
### GWAS Associations
| SNP | P-value | Odds Ratio | Study | Source |
|-----|---------|------------|-------|--------|
 
### Pathogenic Variants (ClinVar)
| Variant | Clinical Significance | Condition | Source |
|---------|----------------------|-----------|--------|
 
**Sources**: (list tools used)
 
---
 
## 4. Treatment Landscape
 
### Approved Drugs
| Drug | ChEMBL ID | Mechanism | Phase | Target | Source |
|------|-----------|-----------|-------|--------|--------|
 
### Clinical Trials
| NCT ID | Title | Phase | Status | Intervention | Source |
|--------|-------|-------|--------|--------------|--------|
 
### Treatment Guidelines
-(from literature)
 
**Sources**: (list tools used)
 
---
 
## 5. Biological Pathways & Mechanisms
 
### Key Pathways
| Pathway | Reactome ID | Genes Involved | Source |
|---------|-------------|----------------|--------|
 
### Protein-Protein Interactions
-(tissue-specific networks)
 
### Expression Patterns
| Tissue | Expression Level | Source |
|--------|------------------|--------|
 
**Sources**: (list tools used)
 
---
 
## 6. Epidemiology & Risk Factors
 
### Prevalence & Incidence
-(from literature)
 
### Risk Factors
| Factor | Evidence | Source |
|--------|----------|--------|
 
### GWAS Studies
| Study | Sample Size | Findings | Source |
|-------|-------------|----------|--------|
 
**Sources**: (list tools used)
 
---
 
## 7. Literature & Research Activity
 
### Publication Trends
-Total publications (5 years): 
-Current year: 
-Trend: 
 
### Key Publications
| PMID | Title | Year | Citations | Source |
|------|-------|------|-----------|--------|
 
### Research Institutions
-(from OpenAlex)
 
**Sources**: (list tools used)
 
---
 
## 8. Similar Diseases & Comorbidities
 
### Similar Diseases
| Disease | Similarity Score | Shared Genes | Source |
|---------|-----------------|--------------|--------|
 
### Comorbidities
-(from literature/clinical data)
 
**Sources**: (list tools used)
 
---
 
## 9. Cancer-Specific Information (if applicable)
 
### CIViC Variants
| Gene | Variant | Evidence Level | Clinical Significance | Source |
|------|---------|----------------|----------------------|--------|
 
### Molecular Profiles
-(biomarkers)
 
### Targeted Therapies
| Therapy | Target | Evidence | Source |
|---------|--------|----------|--------|
 
**Sources**: (list tools used)
 
---
 
## 10. Drug Safety & Adverse Events
 
### Drug Warnings
| Drug | Warning Type | Description | Source |
|------|--------------|-------------|--------|
 
### Clinical Trial Adverse Events
| Trial | Drug | Adverse Event | Frequency | Source |
|-------|------|---------------|-----------|--------|
 
### FAERS Reports
-(FDA adverse event data)
 
**Sources**: (list tools used)
 
---
 
## References
 
### Data Sources Used
| Tool | Query | Section |
|------|-------|---------|
 
### Database Versions
-OpenTargets: (version/date)
-ClinVar: (version/date)
-GWAS Catalog: (version/date)

from datetime import datetime
def create_report_file(disease_name):
    """Create initial report file with template"""
    filename = f"{disease_name.lower().replace(' ', '_')}_research_report.md"
    
    template = f"""# Disease Research Report: {disease_name}
**Report Generated**: {datetime.now().strftime('%Y-%m-%d %H:%M')}
**Disease Identifiers**: Pending research...
---
## Executive Summary
*Research in progress...*
---
## 1. Disease Identity & Classification
*Researching...*
## 2. Clinical Presentation
*Pending...*
[... rest of template ...]
"""
    
    with open(filename, 'w') as f:
        f.write(template)
    
    return filename

def research_with_citations(tu, disease_name, report_file):
    """Research and update report with full citations"""
    
    references = []  # Track all sources
    
    # === DIMENSION 1: Identity ===
    
    # Get EFO ID
    efo_result = tu.tools.OSL_get_efo_id_by_disease_name(disease=disease_name)
    efo_id = efo_result.get('efo_id')
    references.append({
        'tool': 'OSL_get_efo_id_by_disease_name',
        'params': {'disease': disease_name},
        'section': 'Identity'
    })
    
    # Get ICD codes
    icd_result = tu.tools.icd_search_codes(query=disease_name, version="ICD10CM")
    references.append({
        'tool': 'icd_search_codes',
        'params': {'query': disease_name, 'version': 'ICD10CM'},
        'section': 'Identity'
    })
    
    # Get UMLS
    umls_result = tu.tools.umls_search_concepts(query=disease_name)
    references.append({
        'tool': 'umls_search_concepts',
        'params': {'query': disease_name},
        'section': 'Identity'
    })
    
    # Get synonyms from EFO
    if efo_id:
        efo_term = tu.tools.ols_get_efo_term(obo_id=efo_id.replace('_', ':'))
        references.append({
            'tool': 'ols_get_efo_term',
            'params': {'obo_id': efo_id},
            'section': 'Identity'
        })
        
        # Get subtypes
        children = tu.tools.ols_get_efo_term_children(obo_id=efo_id.replace('_', ':'), size=20)
        references.append({
            'tool': 'ols_get_efo_term_children',
            'params': {'obo_id': efo_id, 'size': 20},
            'section': 'Identity'
        })
    
    # UPDATE REPORT FILE with Identity section
    update_report_section(report_file, 'Identity', {
        'efo_id': efo_id,
        'icd_codes': icd_result,
        'umls': umls_result,
        'synonyms': efo_term.get('synonyms', []) if efo_term else [],
        'subtypes': children
    }, references[-5:])  # Last 5 references for this section
    
    # === DIMENSION 2: Clinical ===
    # ... continue for all dimensions

def update_report_section(filename, section_name, data, sources):
    """Update a specific section in the report file"""
    
    # Read current file
    with open(filename, 'r') as f:
        content = f.read()
    
    # Format section content with citations
    if section_name == 'Identity':
        section_content = format_identity_section(data, sources)
    elif section_name == 'Clinical':
        section_content = format_clinical_section(data, sources)
    # ... etc
    
    # Replace placeholder with actual content
    placeholder = f"## {section_number}. {section_name}\n*Researching...*"
    content = content.replace(placeholder, section_content)
    
    # Write back
    with open(filename, 'w') as f:
        f.write(content)
def format_identity_section(data, sources):
    """Format Identity section with proper citations"""
    
    source_list = ', '.join([s['tool'] for s in sources])
    
    return f"""## 1. Disease Identity & Classification
### Ontology Identifiers
| System | ID | Source |
|--------|-----|--------|
| EFO | {data['efo_id']} | OSL_get_efo_id_by_disease_name |
| ICD-10 | {data['icd_codes']} | icd_search_codes |
| UMLS CUI | {data['umls']} | umls_search_concepts |
### Synonyms & Alternative Names
{format_list_with_source(data['synonyms'], 'ols_get_efo_term')}
### Disease Subtypes
{format_list_with_source(data['subtypes'], 'ols_get_efo_term_children')}
**Sources**: {source_list}
"""

# Required tools - use all
tu.tools.OSL_get_efo_id_by_disease_name(disease=disease_name)
tu.tools.OpenTargets_get_disease_id_description_by_name(diseaseName=disease_name)
tu.tools.ols_search_efo_terms(query=disease_name)
tu.tools.ols_get_efo_term(obo_id=efo_id)
tu.tools.ols_get_efo_term_children(obo_id=efo_id, size=30)
tu.tools.umls_search_concepts(query=disease_name)
tu.tools.umls_get_concept_details(cui=cui)
tu.tools.icd_search_codes(query=disease_name, version="ICD10CM")
tu.tools.snomed_search_concepts(query=disease_name)

tu.tools.OpenTargets_get_associated_phenotypes_by_disease_efoId(efoId=efo_id)
tu.tools.get_HPO_ID_by_phenotype(query=symptom)  # for each key symptom
tu.tools.get_phenotype_by_HPO_ID(id=hpo_id)  # for top phenotypes
tu.tools.MedlinePlus_search_topics_by_keyword(term=disease_name, db="healthTopics")
tu.tools.MedlinePlus_get_genetics_condition_by_name(condition=disease_slug)
tu.tools.MedlinePlus_connect_lookup_by_code(cs=icd_oid, c=icd_code)

tu.tools.OpenTargets_get_associated_targets_by_disease_efoId(efoId=efo_id)
tu.tools.OpenTargets_target_disease_evidence(efoId=efo_id, ensemblId=gene_id)  # for top genes
tu.tools.clinvar_search_variants(condition=disease_name, max_results=50)
tu.tools.clinvar_get_variant_details(variant_id=vid)  # for top variants
tu.tools.clinvar_get_clinical_significance(variant_id=vid)
tu.tools.gwas_search_associations(disease_trait=disease_name, size=50)
tu.tools.gwas_get_variants_for_trait(disease_trait=disease_name, size=50)
tu.tools.gwas_get_associations_for_trait(disease_trait=disease_name, size=50)
tu.tools.gwas_get_studies_for_trait(disease_trait=disease_name, size=30)
tu.tools.GWAS_search_associations_by_gene(gene_name=gene)  # for top genes
tu.tools.gnomad_get_variant_frequency(variant=variant)  # for key variants