Analyzing HLA Sequences to Predict Organ Rejection and Find Targets for Immunosuppression

Overview

Organ rejection is a dangerous medical complication that can occur after an organ transplant. Currently, all transplant patients are prescribed life-long immunosuppressors to decrease the risk of organ rejection. However, these medications can increase the susceptibility to other infections and cancers. Human leukocyte antigen (HLA) mismatches between donors and recipients can initiate T-cell activation, which is known to be the primary mediator of organ rejection. However, HLA genes are very polymorphic, and classifying “whole†HLA mismatches does not account for the allele differences that can start rejection. One solution is to create a machine-learning model that can analyze donor and recipient HLA sequences to predict MHC-peptide complexes, which are the molecules that T-cells recognize to start an immune response. This information can be used to predict rejection and find precise targets for immunosuppression. The project used datasets with MHC class I-peptide binding information to analyze donor and recipient HLA sequences. The expected result is that the model can accurately predict MHC-peptide complexes and rejection targets. In conclusion, focusing on MHC-peptide presentation can account for HLA polymorphism and is more accurate in predicting organ rejection. Additionally, this data can be used to administer personalized and targeted immunosuppressors or decrease the need for broad immunosuppressors altogether. A similar model can be developed to predict antibody-mediated rejection (AMR) using MHC-class II datasets and be modified to support other organ transplants.

Competition history

• AJAS 2025 Category not listed

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

• All Computational Biology and Bioinformatics projects
• AJAS Computational Biology and Bioinformatics projects
• Every AJAS 2025 project