AI Therapeutic Protein Engineering Research

Machine Learning-Based Protein Structure Prediction

Interns will work with deep learning models like AlphaFold and RoseTTAFold to predict 3D structures of therapeutic proteins from amino acid sequences. They will validate predictions against experimental structures, optimize model parameters, and contribute to developing novel architectures for improved accuracy on challenging protein targets.

Computational Protein Mutation and Variant Analysis

Interns will analyze how specific mutations affect protein function, stability, and immunogenicity using molecular dynamics simulations and bioinformatics tools. They will predict deleterious variants, design beneficial mutations for enhanced therapeutic efficacy, and create computational pipelines for high-throughput variant screening.

Protein-Ligand Binding and Drug Target Interaction Modeling

Interns will conduct molecular docking studies and perform binding affinity predictions for therapeutic proteins interacting with disease targets or pharmaceutical compounds. They will use tools like AutoDock, GROMACS, and machine learning models to optimize protein-ligand interactions and support drug candidate selection.

Immunogenicity and Safety Prediction for Therapeutic Proteins

Interns will develop and apply computational methods to predict epitopes, aggregation propensity, and potential immunogenic responses to engineered therapeutic proteins. They will analyze sequence features associated with reduced immunogenicity and contribute to in silico optimization strategies for safer biotherapeutics.

Generative AI for De Novo Protein Design and Optimization

Interns will utilize generative models and reinforcement learning approaches to design novel protein sequences with desired functional properties and structural characteristics. They will validate computationally designed proteins for manufacturability, stability, and therapeutic efficacy using experimental or simulation-based approaches.