AI-Driven Macromolecular Design: From Proteins to Programmable Nanostructures

To provide participants with practical and conceptual understanding of AI-based protein design and computational strategies for developing and evaluating programmable macromolecular and nanoscale structures.

• Understand protein sequence–structure–function relationships.
• Learn how AI is applied to protein structure prediction and design.
• Explore generative models for de novo protein engineering.
• Understand inverse folding and AI-assisted sequence optimization.
• Analyze structural confidence and protein design quality.
• Explore protein–protein interactions and molecular self-assembly.
• Understand the principles of protein nanoparticles and nanocages.
• Apply computational methods to evaluate and rank designed structures.
• Connect protein engineering workflows with nanotechnology applications.

Day 1: Protein Structure Analysis & AI-Based Prediction

• Protein sequence–structure–function relationships. Protein domains, motifs, and functional regions. Structural databases: UniProt, RCSB PDB, AlphaFold DB . AI-based structure prediction using AlphaFold/ESMFold concepts . Interpret pLDDT, PAE, RMSD, and TM-score . Protein visualization using PyMOL/ChimeraX .
• Hands-on: Retrieve, visualize, and evaluate a protein structure using confidence and structural-comparison metrics.

Day 2: Generative AI for Protein Design & Optimization

• Introduction to de novo and generative protein design. RFdiffusion for protein backbone generation. ProteinMPNN for inverse folding and sequence design. Analyze charge, hydrophobicity, and sequence properties. Validate designs using structural prediction and comparison. Rank candidate protein designs using multiple metrics.
• Hands-on: Generate candidate protein sequences, validate their structures, and rank the best designs.

Day 3: Protein Self-Assembly & Programmable Nanostructures

• Protein–protein interactions and interface engineering. Oligomers, multimers, symmetry, and self-assembly. Protein nanocages and programmable architectures. Analyze inter-chain contacts, distances, and steric clashes. Visualize and rank protein assemblies. Applications in drug delivery, vaccines, biosensors, and biomaterials .
• Hands-on: Build and evaluate a programmable protein assembly using structural and interface-based criteria.

• Analyze protein sequences and 3D structures.
• Interpret structural confidence metrics such as pLDDT, PAE, and RMSD.
• Understand workflows involving RFdiffusion, ProteinMPNN, and structure-prediction models.
• Generate and compare AI-designed protein candidates.
• Evaluate sequence and structural properties of designed proteins.
• Analyze protein interfaces and self-assembly characteristics.
• Construct and visualize simple protein-based nanostructures.
• Compare candidate structures using computational quality metrics.
• Develop an end-to-endprotein-to-nanostructure design workflow.

Biotechnology and bioinformatics students Biochemistry and molecular biology students Nanotechnology and materials science students Computational biology researchers Structural biology researchers Pharmaceutical and drug-discovery researchers Biomedical engineering students Synthetic biology and protein-engineering researchers PhD scholars, faculty members, and research professionals