Version Compatibility

Reference examples tested with: pandas 2.2+

Before using code patterns, verify installed versions match. If versions differ:

• Python: pip show <package> then help(module.function) to check signatures

If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying.

Epitope Prediction

"Predict B-cell and T-cell epitopes in my protein" → Identify immunogenic regions in antigens for vaccine design using sequence-based and structure-based prediction tools.

• Python: IEDB API for B-cell epitope prediction (BepiPred)
• Python: mhcflurry for T-cell epitope MHC binding prediction

B-Cell Epitope Prediction

Goal: Predict linear B-cell epitopes from protein sequence using IEDB prediction tools.

Approach: Submit sequence to IEDB B-cell prediction API with selectable method (BepiPred-2.0 recommended) and parse tab-separated results.

BepiPred-2.0 (Sequence-Based)

import requests

def predict_bcell_epitopes_iedb(sequence, method='bepipred2'):
    '''Predict B-cell epitopes using IEDB API

    Methods:
    - bepipred2: Deep learning (recommended)
    - bepipred: Original BepiPred
    - emini: Surface accessibility
    - kolaskar-tongaonkar: Antigenicity
    - parker: Hydrophilicity

    BepiPred-2.0 uses deep learning on crystal structures
    Threshold: >0.5 predicted as epitope (default)
    '''
    url = 'http://tools-cluster-interface.iedb.org/tools_api/bcell/'

    params = {
        'method': method,
        'sequence_text': sequence
    }

    response = requests.post(url, data=params)

    # Parse response (tab-separated)
    lines = response.text.strip().split('\n')
    header = lines[0].split('\t')
    data = [line.split('\t') for line in lines[1:]]

    return header, data

Parse BepiPred Results

import pandas as pd

def parse_bepipred_results(header, data, threshold=0.5):
    '''Parse BepiPred output and identify epitope regions

    Output columns:
    - Position: Amino acid position
    - Residue: Amino acid
    - Score: BepiPred score (higher = more likely epitope)

    Epitope threshold:
    - >0.5: Default, balanced sensitivity/specificity
    - >0.6: More stringent, fewer false positives
    - >0.4: More sensitive, more candidates
    '''
    df = pd.DataFrame(data, columns=header)
    df['Score'] = df['Score'].astype(float)
    df['Position'] = df['Position'].astype(int)

    # Identify epitope regions
    df['is_epitope'] = df['Score'] > threshold

    # Find continuous epitope regions
    epitopes = []
    current_epitope = []

    for _, row in df.iterrows():
        if row['is_epitope']:
            current_epitope.append(row)
        else:
            if len(current_epitope) >= 5:  # Minimum epitope length
                epitopes.append({
                    'start': current_epitope[0]['Position'],
                    'end': current_epitope[-1]['Position'],
                    'sequence': ''.join(r['Residue'] for r in current_epitope),
                    'avg_score': sum(r['Score'] for r in current_epitope) / len(current_epitope)
                })
            current_epitope = []

    return df, epitopes