AI-Guided Targeted Protein Degradation: PROTACs, Molecular Glues & Degrader Design
From Protein Inhibition to Protein Destruction — Design, Model and Prioritise Next-Generation Degraders with AI.
About This Course
This three-day hands-on workshop introduces participants to Targeted Protein Degradation (TPD), an emerging therapeutic strategy that removes disease-associated proteins rather than simply inhibiting them. Participants will explore PROTACs, molecular glues, E3-ligase biology, ternary-complex formation, linker design and AI-assisted degrader prediction through guided computational activities using structural biology, cheminformatics and machine-learning tools.
Aim
To provide participants with practical knowledge of targeted protein degradation, PROTAC and molecular-glue design, ternary-complex modelling, molecular-property analysis and AI-assisted degrader prioritisation for modern drug-discovery and therapeutic-research applications.
Course Objectives
- Understand the biological principles of targeted protein degradation and event-driven pharmacology.
- Explore the ubiquitin–proteasome system and the role of E3 ligases in protein degradation.
- Understand PROTAC architecture, including target ligands, linkers and E3-ligase recruiters.
- Identify disease-relevant protein targets and suitable ligands for degrader development.
- Analyse target–PROTAC–E3 ternary-complex structures.
- Evaluate linker and molecular properties influencing degrader performance.
- Understand molecular-glue degraders and induced-proximity mechanisms.
- Generate molecular descriptors and fingerprints for degrader molecules.
- Build machine-learning models for degrader-activity prediction.
- Apply explainable AI and multi-parameter ranking for candidate prioritisation.
Syllabus
📅 Day 1: Targeted Protein Degradation & PROTAC Design
Focus: Understanding TPD biology and building a computational PROTAC design strategy.
Topics Covered
- Event-driven protein degradation and the ubiquitin–proteasome system
- Role of E3 ligases, including CRBN and VHL
- PROTAC architecture: warhead, linker and E3-ligase recruiter
- Target selection, ligand identification and E3-ligase pairing
- Introduction to molecular glues and other induced-proximity modalities
🛠️ Hands-on Activities
- Select a disease-relevant protein target
- Retrieve target and E3-ligase structures
- Identify suitable ligands and recruiter molecules
- Build a preliminary PROTAC design strategy
🧰 Tools Covered:
UniProt, RCSB PDB, AlphaFold DB, PubChem, ChEMBL, PROTAC databases, RDKit
📅 Day 2: Ternary Complex Modeling, Linker Design & Molecular Glues
Focus: Evaluating structural features that influence productive protein degradation.
Topics Covered
- Target–PROTAC–E3 ternary-complex formation
- Ternary-complex geometry and cooperativity
- Linker length, flexibility, polarity and attachment points
- PROTAC physicochemical and beyond-Rule-of-Five properties
- Molecular glue degraders and neosubstrate recruitment
🛠️ Hands-on Activities
- Analyse a representative ternary complex
- Compare alternative linker designs
- Calculate key molecular properties
- Visualise and prioritise degrader architectures
🧰 Tools Covered:
RCSB PDB, AlphaFold DB, RDKit, PyMOL, Py3Dmol, Python, PROTAC databases
📅 Day 3: AI-Based Degrader Prediction & Candidate Prioritisation
Focus: Using machine learning and explainable AI to predict degrader performance and rank candidates.
Topics Covered
- Key TPD metrics: DC₅₀, Dmax, potency and selectivity
- Degrader descriptors and molecular fingerprints
- Machine-learning models for activity prediction
- Explainable AI for identifying important molecular features
- Multi-parameter ranking using activity, structure and physicochemical properties
- Computational limitations and experimental-validation considerations
- 🛠️ Hands-on Activities
- Prepare a degrader activity dataset
- Generate RDKit descriptors and fingerprints
- Train and evaluate an ML prediction model
- Apply SHAP analysis
- Rank degrader candidates using multiple criteria
🧰 Tools Covered:
RDKit, Python, Pandas, Scikit-learn, XGBoost, SHAP, PyMOL, Py3Dmol
Who Should Enrol?
- Graduate and Postgraduate Students from Biotechnology, Bioinformatics, Biochemistry, Molecular Biology, Pharmacy, Pharmaceutical Sciences, Chemistry, Biomedical Sciences, Life Sciences, and related disciplines
- Ph.D. Scholars and Researchers working in drug discovery, cancer biology, protein science, medicinal chemistry, molecular pharmacology, structural biology, chemical biology, or computational biology
- Academicians and Faculty Members interested in targeted protein degradation, PROTACs, molecular glues, AI-enabled drug discovery, and computational therapeutic research
- Industry Professionals from pharmaceutical, biotechnology, CRO, medicinal chemistry, computational chemistry, bioinformatics, and AI/ML-driven drug-discovery teams
Course Outcomes
- Explain how targeted protein degradation differs from conventional drug inhibition.
- Identify suitable disease targets and E3 ligases for degrader development.
- Design the basic architecture of a PROTAC molecule.
- Interpret target–PROTAC–E3 ternary complexes.
- Evaluate linker and molecular properties affecting degrader behaviour.
- Understand the mechanism of molecular-glue degraders.
- Generate molecular descriptors and fingerprints for degrader molecules.
- Build and evaluate an ML model for degrader-activity prediction.
- Use explainable AI to identify important molecular features.
- Prioritise degrader candidates using structural, molecular and predicted activity information.
- Prepare a computationally supported degrader-design strategy for further research or experimental validation.
Course fee
Learners in India
₹2,499
Learners outside India
$50
- Video lectures
- Study material
- Certificate after completion
- 365-day access
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
How is this course taught?
Through recorded video lectures from the original live workshop, with the study material. Watch at your own pace, any time.
How long do I have access?
365 days from your registration, on your NanoSchool dashboard.
Do I get a certificate?
Yes, an e-certificate after completion, with a QR code anyone can verify and an "Add to LinkedIn" button.
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

