AI-Guided Therapeutic Antibody Engineering: Structure, Affinity & Developability Optimization
From Antibody Sequence to Therapeutic Candidate — Design, Predict and Optimize with AI.
About This Course
This three-day workshop introduces an integrated computational workflow for therapeutic-antibody engineering, from sequence analysis and CDR mapping to structure prediction, antigen-binding analysis, affinity estimation, and developability assessment. Participants will explore antibody databases, structural bioinformatics tools, and machine-learning methods to analyse antibody candidates. Guided hands-on activities using SAbDab, ANARCI, AlphaFold/ColabFold, PyMOL, PRODIGY, Biopython, XGBoost, SHAP, and Google Colab will support therapeutic candidate prioritisation.
Aim
To provide participants with practical knowledge of antibody sequence analysis, AI-assisted structure prediction, antibody–antigen interaction assessment, affinity analysis, and developability-based therapeutic candidate prioritisation.
Workshop Objectives
- Understand therapeutic-antibody architecture, sequence features, CDRs, paratopes, and epitopes.
- Explore antibody sequence and structure databases for candidate retrieval and analysis.
- Analyse antibody–antigen interfaces, contact residues, and affinity-related molecular interactions.
- Apply AI and machine-learning tools for antibody structure and developability assessment.
- Develop a multi-parameter workflow to prioritise therapeutic-antibody candidates based on structure, interaction, affinity, and developability profiles.
Workshop Structure
📅 Day 1: Antibody Sequence, CDR Mapping and Structure Prediction
- Therapeutic-antibody architecture: heavy and light chains, VH/VL domains, and CDRs
- Monoclonal antibodies, antibody fragments, and bispecific formats
- Antibody sequence retrieval and annotation
- CDR identification and antibody numbering schemes
- Paratopes, epitopes, and antigen-binding regions
- Principles of antibody 3D structure prediction
- AI-assisted antibody structure modelling
- Structural inspection of variable domains and binding regions
- Comparison of experimentally resolved and predicted antibody structures
🛠️ Hands-on:
- Retrieve therapeutic antibody sequences from public databases
- Identify and annotate CDR regions
- Explore antibody numbering and sequence features
- Predict or inspect antibody 3D structures
- Visualise potential antigen-binding regions
🧰 Tools Covered:
SAbDab, UniProt, RCSB PDB, ANARCI / AbNumber, AlphaFold / ColabFold, PyMOL
📅 Day 2: Antibody–Antigen Interaction and Affinity Analysis
- Principles of antibody–antigen molecular recognition
- Epitope–paratope interaction analysis
- Interpretation of antibody–antigen complex structures
- Interface-residue and contact mapping
- Hydrogen bonds, salt bridges, and hydrophobic interactions
- Structural determinants of binding specificity
- Binding-interface surface analysis
- Mutation comparison at antigen-binding regions
- Computational estimation and interpretation of binding affinity
🛠️ Hands-on:
- Retrieve and inspect an antibody–antigen complex
- Identify epitope and paratope contact residues
- Analyse hydrogen bonds and interface interactions
- Compare selected interface mutations
- Estimate and interpret antibody–antigen binding affinity
🧰 Tools Covered:
RCSB PDB, PyMOL, PDBePISA, PRODIGY, Biopython, Python
📅 Day 3: AI-Based Developability Assessment and Candidate Prioritisation
- Introduction to antibody developability assessment
- Aggregation propensity, hydrophobicity, charge, and stability
- Sequence-based physicochemical properties
- Immunogenicity considerations in therapeutic-antibody development
- Generation of antibody sequence descriptors
- Preparing antibody datasets for machine learning
- Machine-learning approaches for candidate-property prediction
- XGBoost-based prediction and model evaluation
- SHAP-based interpretation of important antibody features
- Multi-parameter therapeutic-antibody candidate ranking
🛠️ Hands-on:
- Generate sequence-based antibody descriptors
- Compare developability-related properties across candidates
- Build a basic machine-learning prediction model
- Interpret influential features using SHAP
- Rank antibody candidates using structure, interaction, and developability criteria
🧰 Tools Covered:
Biopython, ProtParam, scikit-learn, XGBoost, SHAP, Python, Google Colab
Who Should Enrol?
- Graduate and postgraduate students in biotechnology, bioinformatics, molecular biology, biochemistry, pharmacy, and life sciences
- PhD scholars and research fellows working in antibody engineering, immunology, structural biology, or computational biology
- Academicians and faculty members interested in therapeutic-antibody research and AI-assisted biomolecular analysis
- Biotechnology and pharmaceutical researchers involved in biologics, monoclonal antibodies, and therapeutic development
- Industry professionals working in biopharmaceutical R&D, antibody discovery, protein engineering, or computational drug development
Important Dates
Registration Ends
October 26, 2026
IST 4: 30 PM
Workshop Dates
October 26, 2026 – October 28, 2026
IST 5:30 PM
Workshop Outcomes
- Retrieve and analyse antibody sequences and identify CDRs and variable-region features.
- Predict and inspect antibody 3D structures and visualise potential antigen-binding regions.
- Analyse antibody–antigen interactions and interpret key contact residues and affinity-related features.
- Evaluate developability parameters such as aggregation propensity, hydrophobicity, charge, and stability.
- Prioritise therapeutic-antibody candidates using integrated sequence, structure, interaction, and AI-based developability analysis.
Recording fee
Participants in India
₹2,499
Participants outside India
$50
- All session recordings
- Study material
- Certificate after completion
- 1-year access
The live sessions of this workshop are over, so the live fees no longer apply. The recordings are being uploaded. They appear in your dashboard as soon as they are ready, and we will e-mail you then.
Frequently asked questions
Will I get the recording?
Yes. Paid participants get the session recordings and study material in their NanoSchool dashboard (My registrations → Recorded Lectures / Study Material).
What if I miss a live session?
Watch the recording in your dashboard and send your questions to the mentor through the support desk.
Do I get a certificate?
Yes, an e-certificate of participation after the workshop, with a QR code anyone can verify and an "Add to LinkedIn" button.
Which fee category applies to me?
Choose the category that matches your current role: Student, Ph.D. Scholar / Researcher, Academician / Faculty or Industry Professional.
How can I pay?
By card, UPI or PayPal on the payment page; international bank transfer is also available there.
What is the refund policy?
See our Returns, Refunds & Cancellation policy: Returns, Refunds & Cancellation policy