About Workshop
Generative AI is transforming protein engineering by enabling the design of novel protein structures and sequences for specific biological targets.
In this hands-on international workshop, participants will complete a guided protein-binder design workflow using RFdiffusion, ProteinMPNN and AlphaFold 3-class models. Through Google Colab and a disease-relevant case study, they will generate binder backbones, design compatible sequences, evaluate structural confidence and target interactions, and rank promising candidates for further optimisation and experimental validation.
By the end of the workshop, participants will have developed a reusable target-to-binder computational workflow for protein engineering, biologics and drug-discovery research.
Aim
To provide participants with practical knowledge and hands-on experience in designing novel protein binders against biologically relevant targets using generative AI, inverse-folding models and protein-structure prediction tools.
The workshop aims to help participants move from a target protein structure to a computationally generated, evaluated and prioritised binder candidate suitable for further research, optimisation and experimental validation.What Participants Will Learn
By the end of the workshop, participants will be able to:
-
- Understand generative AI, diffusion models and inverse folding in protein engineering.
- Prepare target protein structures and identify binding sites, interface residues and hotspots.
- Generate and filter diverse protein-binder backbones using RFdiffusion.
- Design compatible amino-acid sequences using ProteinMPNN.
- Assess sequence quality, solubility, hydrophobicity, charge and aggregation risks.
- Predict designed protein structures and target–binder complexes using AlphaFold 3-class models.
- Interpret pLDDT, PAE, pTM and ipTM scores and analyse interface contacts and structural clashes.
- Rank promising binder candidates and understand the need for experimental validation.
Structure
📅 Day 1: Target Structural Backbone Generation with RFdiffusion
Core Objective: Master score-based diffusion models to generate novel protein backbones, binder scaffolds, and target-conditioned functional sites.- Principles of generative denoising diffusion probabilistic models (DDPMs) in 3D protein structure space
- De novo scaffold generation and motif scaffolding for functional site presentation
- Target-conditioned diffusion: setting hotspot residues, binding pockets, and symmetry constraints
- Generating diverse candidates and evaluating structural backbone quality
📅 Day 2: Sequence Generation & Inverse Folding with ProteinMPNN
Core Objective: Translate target structural backbones into physical amino acid sequences engineered for high-affinity target binding.- Fundamentals of message-passing graph neural networks (GNNs) in sequence inverse folding
- Fixed-backbone sequence design and residue-level conditioning (temperature, fixed positions)
- Optimizing amino acid sequence recovery, solubility, and aggregation propensity
- Automating multi-sequence sampling per generated backbone scaffold
📅 Day 3: Biomolecular Complex Validation with AlphaFold 3 & Boltz-1
Core Objective: Predict complex interactions, score binding interfaces, and perform final candidate selection using next-generation AI architectures.- Next-generation structure prediction: from AlphaFold 2 Evoformer to AlphaFold 3 Pairformer & diffusion modules
- Modeling biomolecular complexes: protein-protein interactions, nucleic acids, and small-molecule ligands
- Evaluating interface confidence metrics: pLDDT, PAE (Predicted Aligned Error), and ipTM scores
- Lead candidate ranking and automated export for wet-lab gene synthesis and expression
Important Dates
Registration Ends
4:30 PM
Workshop Dates
2026-08-10
5:30 PM
5:30 PM
What You Will Gain
Outcomes
After completing the workshop, participants will be able to execute a guided target-to-binder computational design workflow and generate:
- Novel protein-binder backbones
- Designed amino-acid sequences
- Predicted protein structures
- Target–binder complex models
- Structural-confidence analysis
- Protein-interface assessment
- Sequence-quality results
- A ranked list of computational binder candidates
- A reusable Google Colab workflow
- A roadmap for experimental validation
Who Should Attend
- Protein engineering and computational protein-design researchers
- Structural bioinformatics and computational biology researchers
- Protein–protein interaction and molecular-modelling researchers
- Drug-discovery, biologics and therapeutic-protein researchers
- Antibody, peptide and enzyme-engineering researchers
- Synthetic biology, cancer biology and immunotherapy researchers
- PhD scholars, postdoctoral fellows and faculty members
- Biotechnology, bioinformatics and pharmaceutical professionals