Loading...

Improving Peptide-MHC Class I Binding Prediction using Cross-Encoder Transformer Models

Bahrami, Amirhossein | 2024

0 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 57617 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Sharifi Zarchi, Ali
  7. Abstract:
  8. The Major Histocompatibility Complex (MHC) Class I molecules play a crucial role in the immune system. These molecules present peptides derived from intracellular proteins on the cell surface to be recognized by T cells. This process is vital for identifying and eliminating cancerous or infected cells. In cancer therapy, particularly in the development of personalized vaccines, accurately selecting peptides that can effectively bind to MHC Class I and stimulate a strong immune response is a significant challenge. This research introduces an innovative neural network model that utilizes a cross-encoder architecture and leverages a pre-trained model to simultaneously process peptide and MHC sequences. Due to its high capacity for precisely analyzing these interactions, this model offers higher accuracy than existing methods in predicting peptide-MHC Class I binding. The enhanced accuracy of this model not only aids in the more precise identification of effective peptides but also improves the design of cancer vaccines capable of eliciting a strong and effective immune response. Implementing this model in the cancer vaccine development process can significantly improve therapeutic outcomes, as vaccines designed based on more accurate predictions are more likely to effectively target cancer cells and generate the desired immune response in the patient, leading to improved treatment quality and efficacy
  9. Keywords:
  10. Binding Prediction ; Major Histocompatibility Complex (MHC) ; Peptides ; Cross-Encoder Architecture ; Personalized Vaccines ; Cancer Immunotherapy

 Digital Object List

 Bookmark

No TOC