Exploring the Potential of Structure-Based Deep Learning Approaches for T cell Receptor Design

This repository contains data and results from the study titled "Exploring the Potential of Structure-Based Deep Learning Approaches for T cell Receptor Design". It includes the following compressed files: TCR_design_data_results: Contains data and results from the TCR design process with ProteinMPNN, ESM-IF, and RosettaDesig, as well as design evaluation with TCRModel2 and Rosetta. ATLAS_Benchmark: Contains data, scripts, and results of Molecular Dynamics simulations and MM/PBSA calculations of Native TCR:pMHC complexes collected from ATLAS for the binding affinity benchmarking. MD_MMPBSA_ProteinMPNN_[part1 and part2]: Contain input and output files from the topology generation process, molecular dynamics simulations, and MM/PBSA calculations of ProteinMPNN designs and their corresponding Native complex. MD_MMPBSA_ESM-IF_[part1 and part2]: Contains the input and output files from the topology generation process, molecular dynamics simulations, and MM/PBSA calculations of ESM-IF designs. MD_example_additional_scripts: contains additional scripts used in the MD system preparation and trajectory analyses. For further details, refer to the README.md files within each directory. The abstract of the corresponding study is provided below: "Deep learning methods, trained on the increasing set of available protein 3D structures and sequences, have substantially impacted the protein modeling and design field. These advancements have facilitated the creation of novel proteins, or the optimization of existing ones designed for specific functions, such as binding a target protein. Despite the demonstrated potential of such approaches in designing general protein binders, their application in designing immunotherapeutics remains relatively unexplored. A relevant application is the design of T cell receptors (TCRs). Given the crucial role of T cells in mediating immune responses, redirecting these cells to tumor or infected target cells through the engineering of TCRs has shown promising results in treating diseases, especially cancer. However, the computational design of TCR interactions presents challenges for current physics-based methods, particularly due to the unique natural characteristics of these interfaces, such as low affinity and cross-reactivity. For this reason, in this study, we explored the potential of two structure-based deep learning protein design methods, ProteinMPNN and ESM-IF, in designing fixed-backbone TCRs for binding target antigenic peptides presented by the MHC through different design scenarios. To evaluate TCR designs, we employed a comprehensive set of sequence- and structure-based metrics, highlighting the benefits of these methods in comparison to classical physics-based design methods and identifying deficiencies for improvement."