Create app.py

app.py

@@ -0,0 +1,161 @@
+import numpy as np
+import pandas as pd
+import gradio as gr
+from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import accuracy_score, classification_report
+import joblib
+
+# Generate more realistic synthetic genetic data
+def generate_realistic_genetic_data(n_samples=1000):
+    np.random.seed(42)
+
+    # Define genetic markers associated with different conditions
+    # Marker ranges based on typical genetic variation patterns
+    genetic_data = {
+        'BRCA1_mutation': np.random.choice([0, 1], size=n_samples, p=[0.95, 0.05]),  # BRCA1 mutation
+        'P53_variation': np.random.normal(0.5, 0.1, n_samples),  # P53 tumor suppressor variation
+        'APOE_allele': np.random.choice([2, 3, 4], size=n_samples, p=[0.1, 0.7, 0.2]),  # APOE allele types
+        'DNA_methylation': np.random.beta(2, 5, n_samples),  # DNA methylation levels
+        'telomere_length': np.random.normal(6000, 1000, n_samples),  # Telomere length
+        'CYP2D6_activity': np.random.gamma(2, 2, n_samples),  # CYP2D6 enzyme activity
+        'inflammatory_markers': np.random.exponential(2, n_samples),  # Inflammatory markers
+        'glucose_metabolism': np.random.normal(100, 15, n_samples),  # Glucose metabolism
+        'oxidative_stress': np.random.gamma(3, 1, n_samples),  # Oxidative stress levels
+        'immune_response': np.random.normal(0.7, 0.1, n_samples)  # Immune response strength
+    }
+
+    # Create DataFrame
+    df = pd.DataFrame(genetic_data)
+
+    # Generate disease status based on complex interactions
+    disease_probability = (
+        0.3 * genetic_data['BRCA1_mutation'] +
+        0.2 * (genetic_data['P53_variation'] > 0.7) +
+        0.15 * (genetic_data['APOE_allele'] == 4) +
+        0.1 * (genetic_data['DNA_methylation'] > 0.6) +
+        0.05 * (genetic_data['telomere_length'] < 5000) +
+        0.1 * (genetic_data['CYP2D6_activity'] > 5) +
+        0.05 * (genetic_data['inflammatory_markers'] > 3) +
+        0.05 * (genetic_data['glucose_metabolism'] > 120)
+    )
+
+    df['disease'] = (disease_probability > 0.5).astype(int)
+
+    return df
+
+# Data preprocessing
+def preprocess_data(data):
+    X = data.drop('disease', axis=1)
+    y = data['disease']
+
+    scaler = StandardScaler()
+    X_scaled = scaler.fit_transform(X)
+
+    return X_scaled, y, scaler
+
+# Train and evaluate model
+def train_and_evaluate_model():
+    # Generate and preprocess data
+    print("Generating synthetic genetic data...")
+    data = generate_realistic_genetic_data(1500)
+    print("\nData Sample:")
+    print(data.head())
+    print("\nData Statistics:")
+    print(data.describe())
+
+    # Preprocess data
+    X_scaled, y, scaler = preprocess_data(data)
+
+    # Split data
+    X_train, X_test, y_train, y_test = train_test_split(
+        X_scaled, y, test_size=0.2, random_state=42
+    )
+
+    # Train model
+    print("\nTraining Random Forest model...")
+    model = RandomForestClassifier(
+        n_estimators=100,
+        max_depth=5,
+        random_state=42
+    )
+    model.fit(X_train, y_train)
+
+    # Evaluate model
+    y_pred = model.predict(X_test)
+    accuracy = accuracy_score(y_test, y_pred)
+    print("\nModel Evaluation:")
+    print(f"Accuracy: {accuracy:.2f}")
+    print("\nClassification Report:")
+    print(classification_report(y_test, y_pred))
+
+    # Feature importance
+    feature_importance = pd.DataFrame({
+        'feature': data.drop('disease', axis=1).columns,
+        'importance': model.feature_importances_
+    })
+    print("\nFeature Importance:")
+    print(feature_importance.sort_values('importance', ascending=False))
+
+    return model, scaler
+
+# Prediction function
+def predict_disease(
+    brca1_mutation, p53_variation, apoe_allele, dna_methylation,
+    telomere_length, cyp2d6_activity, inflammatory_markers,
+    glucose_metabolism, oxidative_stress, immune_response
+):
+    # Create input array
+    input_data = np.array([
+        brca1_mutation, p53_variation, apoe_allele, dna_methylation,
+        telomere_length, cyp2d6_activity, inflammatory_markers,
+        glucose_metabolism, oxidative_stress, immune_response
+    ]).reshape(1, -1)
+
+    # Scale input data
+    scaled_data = scaler.transform(input_data)
+
+    # Make prediction
+    prediction = model.predict_proba(scaled_data)[0]
+
+    return {
+        "No Disease": float(prediction[0]),
+        "Disease": float(prediction[1])
+    }
+
+# Train model and get scaler
+print("Training model and preparing interface...")
+model, scaler = train_and_evaluate_model()
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=predict_disease,
+    inputs=[
+        gr.Number(label="BRCA1 Mutation (0 or 1)", value=0),
+        gr.Number(label="P53 Variation (typically 0.3-0.7)", value=0.5),
+        gr.Number(label="APOE Allele (2, 3, or 4)", value=3),
+        gr.Number(label="DNA Methylation (0-1)", value=0.4),
+        gr.Number(label="Telomere Length (typically 4000-8000)", value=6000),
+        gr.Number(label="CYP2D6 Activity (typically 0-10)", value=4),
+        gr.Number(label="Inflammatory Markers (typically 0-10)", value=2),
+        gr.Number(label="Glucose Metabolism (typically 70-130)", value=100),
+        gr.Number(label="Oxidative Stress (typically 0-10)", value=3),
+        gr.Number(label="Immune Response (typically 0.5-0.9)", value=0.7)
+    ],
+    outputs=gr.Label(label="Disease Prediction"),
+    title="Genetic Disease Prediction System",
+    description="""This system predicts genetic disease risk based on various genetic markers and biological indicators.
+                   Please input values within the suggested ranges for accurate predictions.""",
+    examples=[
+        # High-risk example
+        [1, 0.8, 4, 0.7, 4800, 6, 4, 125, 5, 0.6],
+        # Low-risk example
+        [0, 0.4, 3, 0.3, 6500, 3, 1, 95, 2, 0.8],
+        # Moderate-risk example
+        [0, 0.6, 3, 0.5, 5500, 4, 2, 110, 3, 0.7]
+    ]
+)
+
+# Launch the interface
+iface.launch(share=True)