Research Projects

The adaptive immune system is a specialized defense mechanism that safeguards the body against various infectious agents and malignant diseases by accurately identifying and targeting pathogens and abnormal cells. T cells and B cells play a crucial role in this process. T cells recognize specific antigens through interactions with peptide-major histocompatibility complex (pMHC) molecules and initiate immune responses. On the other hand, B cells produce monoclonal antibodies (mAbs) that exhibit a high level of specificity in binding and neutralizing particular antigens. The recent advancements in artificial intelligence and machine learning (AI/ML) have greatly improved the understanding of recognition specificity in antigen-antibody (Ag-Ab) and TCR-pMHC complexes. Techniques such as deep learning, large language models, and generative AI have played a significant role in this progress. Deep learning-based approaches have also made it easier to predict the 3D structures of Ab-Ag and TCR-pMHC, allowing for more accurate modeling and precise identification of interaction interfaces. The main goal of this proposal is to develop computational methods that utilize AI/ML techniques to understand the adaptive immune response. The objective of this initiative is to enhance therapeutic development by designing high-affinity therapeutic monoclonal antibodies (mAbs), and prediction of TCR-pMHC binding for adaptive cell therapies. This project focuses on two primary tasks: (A) designing high-affinity therapeutic mAbs and (B) predicting the 3D structures, binding affinity, and specificity-determining residues for TCR-pMHC complexes. By utilizing advanced computational methods and a wealth of immune-genomic information, this endeavour aims to optimize the accuracy and efficacy of vaccines and immunotherapies. Ultimately, this investigation aims to propel the field of immunotherapy forward and make significant contributions towards more efficient disease prevention and treatment approaches.