HLABrew for Human Leukocyte Antigen Class I-Presented Epitope Recognition and Mimotope Discovery

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Not specified in abstract

• Primary Outcome: State-of-the-art performance in HLA class I epitope prediction with hierarchical and allele-aware representations

• Nnt Or Sensitivity: Sensitivity and specificity metrics not provided

• Confidence Interval: Not reported

Clinical Application

Computational tool requiring bioinformatics expertise and appropriate datasets; feasibility depends on implementation complexity and computational requirements Relevant to Australian precision medicine initiatives and cancer immunotherapy programs; would need validation against Australian population HLA diversity and integration with existing TGA-approved immunotherapy workflows Patients requiring personalized immunotherapy or vaccine development, particularly those with characterized HLA class I allotypes

Abstract

Accurate identification of human leukocyte antigen (HLA) class I-presented epitopes is essential for developing personalized vaccines and immunotherapies. Here, we present HLABrew, a unified deep learning framework for HLA class I epitope prediction and allele-specific mimotope design. By integrating the Transformer, variational autoencoder, and dual cross-attention, HLABrew achieves state-of-the-art performance with hierarchical and allele-aware representations. HLABrew accurately deconvolves multiallelic immunopeptidomics data to recover allele-specific binding motifs and expand epitope coverage. Leveraging its generative capacity, HLABrew further designs mimotopes guided by learned peptide-HLA binding preferences, with the potential to enhance antigen presentation and provide candidates for downstream immunogenicity evaluation.