Loading...

Prediction of HLA-Peptide Binding using 3D Structural Features

Bagh Golshani, Marjan | 2023

101 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56552 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Sharifi Zarchi, Ali
  7. Abstract:
  8. The human leukocyte antigen protein, commonly known as HLA, has the ability to present small protein fragments called peptides on the surface of cells, whether they originate from within the cell or externally. The binding of these peptides to HLA receptors is a crucial step that triggers an immune response. By estimating the affinity between peptides and HLA class I, we can identify novel antigens that have the potential to be targeted by cancer therapeutic vaccines. Computational methods that predict the binding affinity between peptides and HLA receptors have the potential to expedite the design process of cancer vaccines. Currently, most computational methods exclusively rely on sequence-based or pseudo-sequence-based data, which inherently come with certain limitations. However, recent studies have demonstrated that incorporating structure-based data can overcome some limitations. In our research, we aim to overcome these previous limitations by utilizing the new alphafold model and neural networks. We leverage the distinctive features of the three-dimensional structure of the HLA protein. Furthermore, our proposed method is pan-specific, meaning it can be applied to different types of HLAs. For our proposed model, we follow a two-step process. In the first step, we generate an embedding of the three-dimensional structure of HLAs. Then, using attention models, we prepare an embedding of peptides. By concatenating these two sets of data, we are able to predict whether the peptide and HLA bind together or not. Our proposed method demonstrates a higher precision value compared to existing methods, representing a significant advancement in the field of optimal selection of neoantigens. Overall, this work brings structure-based methods one step closer to the discovery pipeline of new antigens, thus contributing to the advancement and development of cancer vaccines
  9. Keywords:
  10. Peptides ; Binding Prediction ; Cancer Vaccine ; Human Leukocyte Antigen (HLA)Protein ; Alphafold Model ; Convolutional Neural Network

 Digital Object List

 Bookmark

No TOC