Towards Antigenic Peptide Discovery with Better MHC-I Binding Prediction and Improved Benchmark Methodology
Abstract
The Major Histocompatibility Complex (MHC) is a crucial component of the cellular immune system in vertebrates, responsible for, among others, presenting peptides derived from intracellular proteins. The MHC-I presentation is vital in the immune response and holds great promise in vaccine development and cancer immunotherapy. In this study, we analyze the limitations of existing methods and benchmarks for MHC-I presentation. We introduce a new benchmark to measure crucial generalization properties and models' reliability on unseen MHC molecules and peptides. Finally, we present ImmunoBert, a pre-trained language model which significantly surpasses prior methods on our benchmark and also sets new state-of-the-art on the old benchmarks.
Cite
Text
Giziński et al. "Towards Antigenic Peptide Discovery with Better MHC-I Binding Prediction and Improved Benchmark Methodology." ICLR 2023 Workshops: MLDD, 2023.Markdown
[Giziński et al. "Towards Antigenic Peptide Discovery with Better MHC-I Binding Prediction and Improved Benchmark Methodology." ICLR 2023 Workshops: MLDD, 2023.](https://mlanthology.org/iclrw/2023/gizinski2023iclrw-antigenic/)BibTeX
@inproceedings{gizinski2023iclrw-antigenic,
title = {{Towards Antigenic Peptide Discovery with Better MHC-I Binding Prediction and Improved Benchmark Methodology}},
author = {Giziński, Stanisław and Preibisch, Grzegorz and Kucharski, Piotr and Tyrolski, Michał and Rembalski, Michał and Grzegorczyk, Piotr and Gambin, Anna},
booktitle = {ICLR 2023 Workshops: MLDD},
year = {2023},
url = {https://mlanthology.org/iclrw/2023/gizinski2023iclrw-antigenic/}
}