app.py

import gradio as gr
import joblib
import numpy as np
import pandas as pd
from propy import AAComposition, Autocorrelation, CTD, PseudoAAC
from sklearn.preprocessing import MinMaxScaler

# Load model and scaler
model = joblib.load("RF.joblib")
scaler = joblib.load("norm (4).joblib")

# Feature list (KEEP THIS CONSISTENT)
selected_features = [
    "_SolventAccessibilityC3", "_SecondaryStrC1", "_SecondaryStrC3", "_ChargeC1", "_PolarityC1",
    "_NormalizedVDWVC1", "_HydrophobicityC3", "_SecondaryStrT23", "_PolarizabilityD1001",
    "_PolarizabilityD2001", "_PolarizabilityD3001", "_SolventAccessibilityD1001",
    "_SolventAccessibilityD2001", "_SolventAccessibilityD3001", "_SecondaryStrD1001",
    "_SecondaryStrD1075", "_SecondaryStrD2001", "_SecondaryStrD3001", "_ChargeD1001",
    "_ChargeD1025", "_ChargeD2001", "_ChargeD3075", "_ChargeD3100", "_PolarityD1001",
    "_PolarityD1050", "_PolarityD2001", "_PolarityD3001", "_NormalizedVDWVD1001",
    "_NormalizedVDWVD2001", "_NormalizedVDWVD2025", "_NormalizedVDWVD2050", "_NormalizedVDWVD3001",
    "_HydrophobicityD1001", "_HydrophobicityD2001", "_HydrophobicityD3001", "_HydrophobicityD3025",
    "A", "R", "D", "C", "E", "Q", "H", "I", "M", "P", "Y", "V",
    "AR", "AV", "RC", "RL", "RV", "CR", "CC", "CL", "CK", "EE", "EI", "EL",
    "HC", "IA", "IL", "IV", "LA", "LC", "LE", "LI", "LT", "LV", "KC", "MA",
    "MS", "SC", "TC", "TV", "YC", "VC", "VE", "VL", "VK", "VV",
    "MoreauBrotoAuto_FreeEnergy30", "MoranAuto_Hydrophobicity2", "MoranAuto_Hydrophobicity4",
    "GearyAuto_Hydrophobicity20", "GearyAuto_Hydrophobicity24", "GearyAuto_Hydrophobicity26",
    "GearyAuto_Hydrophobicity27", "GearyAuto_Hydrophobicity28", "GearyAuto_Hydrophobicity29",
    "GearyAuto_Hydrophobicity30", "GearyAuto_AvFlexibility22", "GearyAuto_AvFlexibility26",
    "GearyAuto_AvFlexibility27", "GearyAuto_AvFlexibility28", "GearyAuto_AvFlexibility29",
    "GearyAuto_AvFlexibility30", "GearyAuto_Polarizability22", "GearyAuto_Polarizability24",
    "GearyAuto_Polarizability25", "GearyAuto_Polarizability27", "GearyAuto_Polarizability28",
    "GearyAuto_Polarizability29", "GearyAuto_Polarizability30", "GearyAuto_FreeEnergy24",
    "GearyAuto_FreeEnergy25", "GearyAuto_FreeEnergy30", "GearyAuto_ResidueASA21",
    "GearyAuto_ResidueASA22", "GearyAuto_ResidueASA23", "GearyAuto_ResidueASA24",
    "GearyAuto_ResidueASA30", "GearyAuto_ResidueVol21", "GearyAuto_ResidueVol24",
    "GearyAuto_ResidueVol25", "GearyAuto_ResidueVol26", "GearyAuto_ResidueVol28",
    "GearyAuto_ResidueVol29", "GearyAuto_ResidueVol30", "GearyAuto_Steric18",
    "GearyAuto_Steric21", "GearyAuto_Steric26", "GearyAuto_Steric27", "GearyAuto_Steric28",
    "GearyAuto_Steric29", "GearyAuto_Steric30", "GearyAuto_Mutability23", "GearyAuto_Mutability25",
    "GearyAuto_Mutability26", "GearyAuto_Mutability27", "GearyAuto_Mutability28",
    "GearyAuto_Mutability29", "GearyAuto_Mutability30", "APAAC1", "APAAC4", "APAAC5",
    "APAAC6", "APAAC8", "APAAC9", "APAAC12", "APAAC13", "APAAC15", "APAAC18", "APAAC19",
    "APAAC24"
]

def extract_features(sequence):
    """Extract selected features, ensure order matches trained features, and normalize them."""
    if len(sequence) <= 9:
        return "Error: Protein sequence must be longer than 9 amino acids to extract features (for lamda=9)."

    all_features_dict = {}

    # Calculate all dipeptide features
    dipeptide_features = AAComposition.CalculateAADipeptideComposition(sequence)
    
    # Add only the first 420 features to the dictionary
    first_420_keys = list(dipeptide_features.keys())[:420]  # Get the first 420 keys
    filtered_dipeptide_features = {key: dipeptide_features[key] for key in first_420_keys}
    
    all_features_dict.update(filtered_dipeptide_features)

    auto_features = Autocorrelation.CalculateAutoTotal(sequence)
    all_features_dict.update(auto_features)

    ctd_features = CTD.CalculateCTD(sequence)
    all_features_dict.update(ctd_features)

    pseudo_features = PseudoAAC.GetAPseudoAAC(sequence, lamda=9)
    all_features_dict.update(pseudo_features)

    feature_values = list(all_features_dict.values())
    feature_array = np.array(feature_values).reshape(-1, 1) # Reshape to (1, n_features) - CORRECT SHAPE
    print(f"Shape of feature_array before normalization: {feature_array.shape}") # Debug print

    normalized_features = scaler.transform(feature_array.T) # Normalize - NO TRANSPOSE
    normalized_features = normalized_features.flatten() # Flatten AFTER normalization if needed


    selected_feature_dict = {feature: normalized_features[i] for i, feature in enumerate(selected_features) if feature in all_features_dict}

    selected_feature_df = pd.DataFrame([selected_feature_dict])
    selected_feature_array = selected_feature_df.T.to_numpy()

    return selected_feature_array


def predict(sequence):
    """Predicts whether the input sequence is an AMP."""
    features = extract_features(sequence)
    if isinstance(features, str) and features.startswith("Error:"):
        return features

    prediction = model.predict(features.T)[0]
    probabilities = model.predict_proba(features.T)[0]

    if prediction == 0:
        return f"{probabilities[0] * 100:.2f}% chance of being an Antimicrobial Peptide (AMP)"
    else:
        return f"{probabilities[1] * 100:.2f}% chance of being Non-AMP"

# Gradio interface
iface = gr.Interface(
    fn=predict,
    inputs=gr.Textbox(label="Enter Protein Sequence"),
    outputs=gr.Label(label="Prediction"),
    title="AMP Classifier",
    description="Enter an amino acid sequence (e.g., FLPVLAGGL) to predict AMP."
)

iface.launch(share=True)