Input: Patient profile (disease + biomarkers + stage + prior treatments)

Phase 1: Patient Profile Standardization
  - Resolve disease to EFO/ontology IDs
  - Parse molecular alterations to gene + variant
  - Resolve gene symbols to Ensembl/Entrez IDs
  - Classify biomarker actionability (FDA-approved vs investigational)

Phase 2: Broad Trial Discovery
  - Disease-based trial search (ClinicalTrials.gov)
  - Biomarker-specific trial search
  - Intervention-based search (for known drugs targeting patient's biomarkers)
  - Collect NCT IDs for detailed analysis

Phase 3: Trial Characterization
  - Get eligibility criteria for top candidate trials
  - Get conditions and interventions
  - Get locations and status
  - Get trial descriptions and phase information

Phase 4: Molecular Eligibility Matching
  - Parse eligibility criteria text for biomarker requirements
  - Match patient's molecular profile to trial requirements
  - Score molecular eligibility

Phase 5: Drug-Biomarker Alignment
  - Identify trial intervention drugs
  - Check drug mechanisms against patient biomarkers (OpenTargets, ChEMBL)
  - FDA approval status for biomarker-drug combinations
  - Classify drugs (targeted therapy, immunotherapy, chemotherapy)

Phase 6: Evidence Assessment
  - FDA-approved biomarker-drug combinations
  - Clinical trial results for similar patients (PubMed)
  - CIViC clinical evidence
  - PharmGKB pharmacogenomics
  - Drug safety profiles

Phase 7: Geographic & Feasibility Analysis
  - Trial site locations
  - Enrollment status and dates
  - Distance from patient location (if provided)

Phase 8: Alternative Options
  - Basket trials (biomarker-driven, tumor-agnostic)
  - Expanded access and compassionate use
  - Related trials with different study designs

Phase 9: Scoring & Ranking
  - Calculate Trial Match Score (0-100) for each trial
  - Tier classification (Optimal/Good/Possible/Exploratory)
  - Rank by composite score
  - Generate recommendations

Phase 10: Report Synthesis
  - Executive summary (top 3 trials)
  - Patient profile summary
  - Ranked trial list with detailed analysis
  - Alternative options
  - Evidence grading
  - Completeness checklist

def resolve_disease(tu, disease_name):
    """Resolve disease name to EFO ID and standard terminology."""
    # OpenTargets disease search
    result = tu.tools.OpenTargets_get_disease_id_description_by_name(diseaseName=disease_name)
    hits = result.get('data', {}).get('search', {}).get('hits', [])

    if hits:
        disease_info = hits[0]
        return {
            'efo_id': disease_info.get('id'),
            'name': disease_info.get('name'),
            'description': disease_info.get('description'),
            'original_input': disease_name
        }

    # Fallback: OLS EFO search
    ols_result = tu.tools.ols_search_efo_terms(query=disease_name, limit=5)
    ols_terms = ols_result.get('data', {}).get('terms', [])
    if ols_terms:
        term = ols_terms[0]
        return {
            'efo_id': term.get('short_form'),
            'name': term.get('label'),
            'description': term.get('description', [''])[0] if term.get('description') else '',
            'original_input': disease_name
        }

    return {'efo_id': None, 'name': disease_name, 'description': '', 'original_input': disease_name}

def resolve_gene(tu, gene_symbol):
    """Resolve gene symbol to cross-database IDs."""
    # Normalize common aliases
    alias_map = {
        'HER2': 'ERBB2', 'HER-2': 'ERBB2',
        'PD-L1': 'CD274', 'PDL1': 'CD274',
        'PD-1': 'PDCD1', 'PD1': 'PDCD1',
        'VEGF': 'VEGFA',
    }
    normalized = alias_map.get(gene_symbol.upper(), gene_symbol)

    # MyGene resolution
    result = tu.tools.MyGene_query_genes(query=normalized, species='human')
    hits = result.get('hits', [])

    gene_hit = None
    for hit in hits:
        if hit.get('symbol', '').upper() == normalized.upper():
            gene_hit = hit
            break
    if not gene_hit and hits:
        gene_hit = hits[0]

    if gene_hit:
        ensembl = gene_hit.get('ensembl', {})
        ensembl_id = ensembl.get('gene') if isinstance(ensembl, dict) else (ensembl[0].get('gene') if isinstance(ensembl, list) and ensembl else None)
        return {
            'symbol': gene_hit.get('symbol'),
            'entrez_id': gene_hit.get('entrezgene'),
            'ensembl_id': ensembl_id,
            'name': gene_hit.get('name'),
            'original_input': gene_symbol
        }

    return {'symbol': gene_symbol, 'entrez_id': None, 'ensembl_id': None, 'name': None, 'original_input': gene_symbol}

def classify_biomarker_actionability(tu, gene_symbol, alteration):
    """Classify biomarker as FDA-approved, guideline, or investigational."""
    # Check FDA pharmacogenomic biomarkers
    fda_result = tu.tools.fda_pharmacogenomic_biomarkers()
    fda_biomarkers = fda_result.get('results', [])

    fda_match = [b for b in fda_biomarkers if gene_symbol.upper() in str(b.get('Biomarker', '')).upper()]

    if fda_match:
        return {
            'level': 'FDA-approved',
            'drugs': [b.get('Drug') for b in fda_match],
            'labeling_sections': [b.get('LabelingSection') for b in fda_match]
        }

    # Check OpenTargets for drugs targeting this gene
    # (done in Phase 5)

    return {'level': 'investigational', 'drugs': [], 'labeling_sections': []}

def parse_biomarker(biomarker_text):
    """Parse free-text biomarker into structured components."""
    import re

    # Pattern: "GENE VARIANT" (e.g., "EGFR L858R")
    mutation_match = re.match(r'(\w+)\s+([A-Z]\d+[A-Z])', biomarker_text, re.IGNORECASE)
    if mutation_match:
        return {'gene': mutation_match.group(1), 'alteration': mutation_match.group(2), 'type': 'mutation'}

    # Pattern: "GENE exon N deletion/insertion"
    exon_match = re.match(r'(\w+)\s+exon\s+(\d+)\s+(\w+)', biomarker_text, re.IGNORECASE)
    if exon_match:
        return {'gene': exon_match.group(1), 'alteration': f'exon {exon_match.group(2)} {exon_match.group(3)}', 'type': 'exon_alteration'}

    # Pattern: "GENE1-GENE2 fusion" or "GENE1/GENE2"
    fusion_match = re.match(r'(\w+)[-/](\w+)\s*(fusion)?', biomarker_text, re.IGNORECASE)
    if fusion_match:
        return {'gene': fusion_match.group(2), 'alteration': f'{fusion_match.group(1)}-{fusion_match.group(2)}', 'type': 'fusion', 'partner': fusion_match.group(1)}

    # Pattern: "GENE amplification"
    amp_match = re.match(r'(\w+)\s+amplification', biomarker_text, re.IGNORECASE)
    if amp_match:
        return {'gene': amp_match.group(1), 'alteration': 'amplification', 'type': 'amplification'}

    # Pattern: "PD-L1 XX%"
    expression_match = re.match(r'([\w-]+)\s+(\d+%|high|low|positive|negative)', biomarker_text, re.IGNORECASE)
    if expression_match:
        return {'gene': expression_match.group(1), 'alteration': expression_match.group(2), 'type': 'expression'}

    # Pattern: "MSI-high", "TMB-high"
    status_match = re.match(r'(MSI|TMB|dMMR|MMR)[-\s]*(high|low|stable|deficient|proficient)', biomarker_text, re.IGNORECASE)
    if status_match:
        return {'gene': status_match.group(1), 'alteration': status_match.group(2), 'type': 'status'}

    # Fallback: treat as gene name
    return {'gene': biomarker_text.split()[0], 'alteration': ' '.join(biomarker_text.split()[1:]), 'type': 'unknown'}

def search_trials_by_disease(tu, disease_name, status_filter=None, phase_filter=None, page_size=20):
    """Search ClinicalTrials.gov by disease/condition."""
    query_parts = []
    if status_filter:
        query_parts.append(f'AREA[OverallStatus]{status_filter}')
    if phase_filter:
        query_parts.append(phase_filter)

    query_term = ' AND '.join(query_parts) if query_parts else disease_name

    result = tu.tools.search_clinical_trials(
        condition=disease_name,
        query_term=query_term if query_parts else disease_name,
        pageSize=page_size
    )

    # Response: {studies: [{NCT ID, brief_title, brief_summary, overall_status, condition, phase}], nextPageToken, total_count}
    if isinstance(result, str):
        return []  # No studies found

    return result.get('studies', [])

def search_trials_by_biomarker(tu, gene_symbol, alteration, disease_name=None, page_size=15):
    """Search trials mentioning specific biomarkers."""
    # Search 1: Gene + alteration
    biomarker_query = f'{gene_symbol} {alteration}' if alteration else gene_symbol

    result = tu.tools.search_clinical_trials(
        condition=disease_name if disease_name else '',
        query_term=biomarker_query,
        pageSize=page_size
    )

    if isinstance(result, str):
        return []

    return result.get('studies', [])

def search_trials_by_intervention(tu, drug_name, disease_name=None, page_size=10):
    """Search trials by intervention/drug name."""
    result = tu.tools.search_clinical_trials(
        condition=disease_name if disease_name else '',
        intervention=drug_name,
        query_term=drug_name,
        pageSize=page_size
    )

    if isinstance(result, str):
        return []

    return result.get('studies', [])

def search_trials_alternative(tu, condition, intervention=None, limit=10):
    """Alternative trial search with different API endpoint."""
    params = {
        'action': 'search_studies',
        'condition': condition,
        'limit': limit
    }
    if intervention:
        params['intervention'] = intervention

    result = tu.tools.clinical_trials_search(**params)

    return result.get('studies', [])

def deduplicate_trials(trial_lists):
    """Merge and deduplicate trials from multiple searches."""
    seen_ncts = set()
    unique_trials = []

    for trials in trial_lists:
        for trial in trials:
            nct = trial.get('NCT ID') or trial.get('nctId', '')
            if nct and nct not in seen_ncts:
                seen_ncts.add(nct)
                unique_trials.append(trial)

    return unique_trials

def get_trial_eligibility(tu, nct_ids):
    """Get eligibility criteria for multiple trials."""
    # Process in batches of 10
    all_criteria = []
    for i in range(0, len(nct_ids), 10):
        batch = nct_ids[i:i+10]
        result = tu.tools.get_clinical_trial_eligibility_criteria(
            nct_ids=batch,
            eligibility_criteria='all'
        )
        if isinstance(result, list):
            all_criteria.extend(result)

    return all_criteria
    # Returns: [{NCT ID, eligibility_criteria: "Inclusion Criteria:\n...\nExclusion Criteria:\n..."}]

def get_trial_interventions(tu, nct_ids):
    """Get conditions, arm groups, and interventions for multiple trials."""
    all_interventions = []
    for i in range(0, len(nct_ids), 10):
        batch = nct_ids[i:i+10]
        result = tu.tools.get_clinical_trial_conditions_and_interventions(
            nct_ids=batch,
            condition_and_intervention='all'
        )
        if isinstance(result, list):
            all_interventions.extend(result)

    return all_interventions
    # Returns: [{NCT ID, condition, arm_groups: [{label, type, description, interventionNames}], interventions: [{type, name, description}]}]

def get_trial_locations(tu, nct_ids):
    """Get trial site locations."""
    all_locations = []
    for i in range(0, len(nct_ids), 10):
        batch = nct_ids[i:i+10]
        result = tu.tools.get_clinical_trial_locations(
            nct_ids=batch,
            location='all'
        )
        if isinstance(result, list):
            all_locations.extend(result)

    return all_locations
    # Returns: [{NCT ID, locations: [{facility, city, state, country}]}]

def get_trial_status(tu, nct_ids):
    """Get enrollment status and key dates."""
    all_status = []
    for i in range(0, len(nct_ids), 10):
        batch = nct_ids[i:i+10]
        result = tu.tools.get_clinical_trial_status_and_dates(
            nct_ids=batch,
            status_and_date='all'
        )
        if isinstance(result, list):
            all_status.extend(result)

    return all_status
    # Returns: [{NCT ID, overall_status, start_date, primary_completion_date, completion_date}]

def get_trial_descriptions(tu, nct_ids):
    """Get detailed trial descriptions."""
    all_descriptions = []
    for i in range(0, len(nct_ids), 10):
        batch = nct_ids[i:i+10]
        result = tu.tools.get_clinical_trial_descriptions(
            nct_ids=batch,
            description_type='full'
        )
        if isinstance(result, list):
            all_descriptions.extend(result)

    return all_descriptions
    # Returns: [{NCT ID, brief_title, official_title, brief_summary, detailed_description}]

def extract_biomarker_requirements(eligibility_text):
    """Extract biomarker requirements from eligibility criteria text."""
    import re

    requirements = {
        'required_biomarkers': [],
        'excluded_biomarkers': [],
        'biomarker_agnostic': False
    }

    if not eligibility_text:
        return requirements

    text_upper = eligibility_text.upper()

    # Common biomarker patterns in eligibility text
    # Required biomarkers (in inclusion criteria)
    inclusion_section = eligibility_text.split('Exclusion Criteria')[0] if 'Exclusion Criteria' in eligibility_text else eligibility_text
    exclusion_section = eligibility_text.split('Exclusion Criteria')[1] if 'Exclusion Criteria' in eligibility_text else ''

    # Look for gene mutation requirements
    gene_patterns = [
        r'(?:EGFR|KRAS|BRAF|ALK|ROS1|RET|MET|NTRK|HER2|ERBB2|PIK3CA|BRCA|PD-?L1|MSI|TMB|dMMR)',
    ]

    for pattern in gene_patterns:
        # In inclusion section
        for match in re.finditer(pattern, inclusion_section, re.IGNORECASE):
            gene = match.group(0).upper()
            context = inclusion_section[max(0, match.start()-100):match.end()+100]
            requirements['required_biomarkers'].append({
                'gene': gene,
                'context': context.strip()
            })

        # In exclusion section
        for match in re.finditer(pattern, exclusion_section, re.IGNORECASE):
            gene = match.group(0).upper()
            context = exclusion_section[max(0, match.start()-100):match.end()+100]
            requirements['excluded_biomarkers'].append({
                'gene': gene,
                'context': context.strip()
            })

    # Check for biomarker-agnostic / basket trial language
    basket_terms = ['tumor-agnostic', 'histology-independent', 'basket', 'any solid tumor', 'all comers', 'biomarker-selected']
    if any(term in text_upper.lower() for term in basket_terms):
        requirements['biomarker_agnostic'] = True

    return requirements