example_usage.py

#!/usr/bin/env python3
"""Example usage of AssayExtract."""

from assay_extract import AssayClassifier

# Initialize
classifier = AssayClassifier()

# Example 1: Simple extraction
print("=" * 70)
print("EXAMPLE 1: Extract measures from methods text")
print("=" * 70)

methods = """
We assessed anxiety using the elevated plus maze for 5 minutes. 
Social behavior was measured with the three-chamber social approach test. 
Spatial learning and memory were tested on the morris water maze over 5 days. 
Motor coordination was evaluated on the accelerating rotarod.
"""

print("Input Methods Section:")
print(methods)

results = classifier.extract_measures(methods)

print("\nExtracted Measures:")
for i, result in enumerate(results, 1):
    print(f"\n{i}. {result.canonical_name}")
    print(f"   Domain: {result.outcome_domain}")
    if result.subdomain:
        print(f"   Subdomain: {result.subdomain}")
    print(f"   Description: {result.measure_description[:80]}...")

# Example 2: Multi-domain extraction
print("\n" + "=" * 70)
print("EXAMPLE 2: Extract from multi-domain methods")
print("=" * 70)

multi_domain_methods = """
Behavioral tests included the elevated plus maze for anxiety assessment and 
rotarod for motor coordination. Brain tissue was analyzed using 
immunohistochemistry with DAB detection. We also performed 18F-FDG PET imaging 
to assess metabolic activity.
"""

print("Input:")
print(multi_domain_methods)

results = classifier.extract_measures(multi_domain_methods)

print(f"\nFound {len(results)} measures:\n")
by_domain = {}
for result in results:
    domain = result.outcome_domain
    if domain not in by_domain:
        by_domain[domain] = []
    by_domain[domain].append(result.canonical_name)

for domain, measures in sorted(by_domain.items()):
    print(f"{domain}:")
    for measure in measures:
        print(f"  - {measure}")
    print()

# Example 3: Access the assay vocabulary
print("\n" + "=" * 70)
print("EXAMPLE 3: Access the assay vocabulary")
print("=" * 70)

# Full vocabulary
vocab = classifier.get_vocabulary()
print(f"Total vocabulary entries: {len(vocab)}")

print("\nFirst 5 vocabulary entries:")
for entry in vocab[:5]:
    print(f"- {entry['canonical_name']}")
    print(f"  Domain: {entry['outcome_domain']}")
    print(f"  Subdomain: {entry.get('subdomain', 'N/A')}")
    print()

# Get all assays from one domain
behavioral = classifier.get_by_domain("Behavioral")
print(f"Number of Behavioral assays: {len(behavioral)}")

print("\nFirst 10 Behavioral assays:")
for entry in behavioral[:10]:
    print(f"- {entry['canonical_name']}")