Activity Number:
|
524
- Recent Advances in Methods for Genomic Data Analysis
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 11, 2022 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Statistics in Genomics and Genetics
|
Abstract #323536
|
|
Title:
|
Neural Network Models for Sequence-Based TCR and HLA Association Prediction
|
Author(s):
|
Si Liu* and Phil Bradley and Wei Sun
|
Companies:
|
Fred Hutchinson Cancer Research Center and Fred Hutchinson Cancer Research Center and Fred Hutchinson Cancer Research Center
|
Keywords:
|
neural networks;
deep learning;
T cell receptor;
human leukocyte antigen complex
|
Abstract:
|
T-cell mediated immunity relies on T-cell receptor(TCR) to recognize peptides bound by major histocompatibility complex(MHC). The human MHC is also called the human leukocyte antigen complex(HLA). It is important to account for HLA information in TCR analysis for predicting infection status. Currently in literature, the association between TCR and HLA is assessed through co-occurrence pattern. In this work we explore the capacity of certain neural network models to predict the association between TCR and HLA, based on the amino acid sequence information of HLA at certain positions and both CDR3 amino acid sequence information and V allele information of TCR. Our model can make predictions on HLA and TCR with amino acid sequences not seen during training.
|
Authors who are presenting talks have a * after their name.