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

model = joblib.load("RF.joblib")
scaler = joblib.load("norm.joblib")

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):
    aa_features = AAComposition.CalculateAADipeptideComposition(sequence)
    auto_features = Autocorrelation.CalculateAutoTotal(sequence)
    ctd_features = CTD.CalculateCTD(sequence)
    pseaac_features = PseudoAAC.GetAPseudoAAC(sequence, lamda=9)

    all_features = {**aa_features, **auto_features, **ctd_features, **pseaac_features}

    # Convert to DataFrame
    feature_df = pd.DataFrame([all_features])

    print("Extracted Features:", feature_df.columns.tolist())  # Debugging line

    # Ensure all selected features are present
    missing_features = [f for f in selected_features if f not in feature_df.columns]
    extra_features = [f for f in feature_df.columns if f not in selected_features]

    if missing_features:
        print(f"Missing Features ({len(missing_features)}):", missing_features)
    
    if extra_features:
        print(f"Extra Features ({len(extra_features)}):", extra_features)

    # Fix missing columns by adding them with default values (0)
    for feature in missing_features:
        feature_df[feature] = 0

    # Select only the required features
    feature_df = feature_df[selected_features]

    # Normalize
    normalized_features = scaler.transform(feature_df)

    return normalized_features


def predict(sequence):
    """Predict if the sequence is an AMP or not."""
    features = extract_features(sequence)
    prediction = model.predict(features)[0]
    probabilities = model.predict_proba(features)[0]
    
    prob_amp = probabilities[0]
    prob_non_amp = probabilities[1]

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

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 to predict whether it's an antimicrobial peptide (AMP) or not."
)

iface.launch(share=True)