Generative AI for Protein Design, Antibodies, and Therapeutic Discovery
Design the Next Generation of Therapeutics with Generative AI
About This Course
This workshop introduces the key concepts behind protein language models, diffusion models, structure-based generative design, antibody optimization, and AI-assisted biologics development. Participants will explore applications in antibody discovery, antigen binding prediction, protein stability improvement, enzyme engineering, and therapeutic candidate screening.
Aim
This workshop aims to introduce participants to the use of Generative AI in protein engineering, antibody design, and therapeutic discovery. It focuses on how AI models can generate, optimize, and evaluate novel protein and antibody candidates. Participants will learn how generative models support sequence design, structure prediction, affinity improvement, and developability assessment. The program bridges computational biology, AI, and next-generation biologics discovery.
Workshop Objectives
- Understand how generative AI is used in protein and antibody design.
- Learn sequence-based and structure-based protein generation concepts.
- Explore antibody design, binding affinity prediction, and developability analysis.
- Understand protein stability, specificity, and functional optimization strategies.
- Connect AI-generated candidates to therapeutic discovery workflows.
Workshop Structure
Day 1: Foundations of Protein AI and Structure Prediction
- Protein databases and sequence annotation
- Structure confidence, pLDDT, and basic model interpretation
- Search a protein sequence using UniProt
- Explore known structures using RCSB PDB
- View predicted structures using AlphaFold DB
- Predict or explore a protein structure using ColabFold / ESMFold demo
- Visualize protein structure using Mol* / PyMOL
- Tools: Google Colab, NCBI, PubMed / literature search & demo & UniProt
Day 2: Generative AI for Protein Design and Engineering
- Generate or explore protein sequence embeddings using a demo notebook
- Understand RFdiffusion-based protein scaffold/binder design workflow
- Use ProteinMPNN concept workflow for sequence redesign
- Compare native vs designed protein sequences
- Visualize designed protein structures
- Discuss developability checks: stability, solubility, immunogenicity, and manufacturability
- Tools: Google Colab, NCBI, PubMed / literature search & demo & UniProt
Day 3: Generative AI for Antibodies and Therapeutic Discovery
- Explore antibody sequence and structure basics
- Predict or view antibody structure using IgFold demo
- Identify CDR regions and binding-relevant regions
- Visualize antibody–antigen interaction concept
- Perform a basic docking workflow demonstration
- Create a therapeutic discovery workflow map
- Prepare a simple AI model validation checklist
- Tools: Google Colab, NCBI, PubMed / literature search & demo & UniProt
Important Dates
Registration Ends
May 2, 2026
IST 7:00 PM
Workshop Dates
May 2, 2026 – May 4, 2026
IST 8:00 PM
Workshop Outcomes
Participants will be able to:
- Explain how generative AI accelerates protein and antibody discovery.
- Understand AI workflows for designing and optimizing therapeutic proteins.
- Interpret outputs from protein language and structure-based AI models.
- Identify key developability factors for biologics candidates.
- Apply AI-driven thinking to therapeutic discovery and biologics R&D.
Meet Your Mentor(s)
DR. HARISHCHANDER ANANDARAM
Dr Harishchander Anandaram is an Assistant Professor at Centre for Excellence in Computational Engineering and Networking, Amrita Vishwa Vidyapeetham, Coimbatore, Tamil Nadu, India. He received his Ph.D. Degree in Bioengineering from Sathyabama Institute of Science and Technology, Chennai, in 2020. . . .
Fee Structure
Student Fee
₹2499 | $65
Ph.D. Scholar / Researcher Fee
₹3499 | $75
Academician / Faculty Fee
₹4499 | $87
Industry Professional Fee
₹5499 | $95
What You’ll Gain
- Live & recorded sessions
- e-Certificate upon completion
- Post-workshop query support
- Hands-on learning experience
View All Feedbacks →