Artificial Intelligence and the Evolving Landscape of Immunopeptidomics

Area of Science:

• Immunology
• Bioinformatics
• Computational Biology

Background:

• Immunopeptidomics studies peptides presented by MHC molecules, crucial for neoantigen discovery and cancer immunotherapy.
• Challenges include complex mass spectrometry data, diverse peptide sources, and variable immune responses.

Purpose of the Study:

• To review the application of artificial intelligence (AI) in advancing immunopeptidomics workflows.
• To highlight how AI addresses limitations in identifying actionable neoantigens, using breast cancer as a case study.

Main Methods:

• Review of AI applications in de novo sequencing, peptide-spectrum matching, spectrum prediction, MHC binding prediction, and T-cell recognition modeling.
• Case study analysis focusing on breast cancer to illustrate AI's role in neoantigen identification.

Main Results:

• AI enhances the detection of MHC-bound peptides, including low-abundance, noncanonical, and post-translationally modified epitopes.
• AI improves peptide-spectrum matching and T-cell epitope prediction, aiding in neoantigen prioritization.
• AI reveals immunogenic features in previously 'cold' tumors like breast cancer.

Conclusions:

• AI is transforming immunopeptidomics by overcoming identification and prediction challenges.
• AI advancements expand neoantigen discovery pipelines and optimize cancer immunotherapies.
• Future AI models, including deep learning and multi-omics, promise more accurate and scalable immunotherapy development.