New TCR-SRIM model offers interpretable epitope prediction

Researchers have developed TCR-SRIM, a novel model designed for predicting T cell receptor (TCR)-epitope binding. This model integrates protein language model embeddings with interpretable contact prototypes to analyze TCR-epitope interactions at a residue level. TCR-SRIM demonstrates state-of-the-art performance on the TCR-XAI benchmark and offers enhanced interpretability. The study also evaluated the impact of generated protein structures on model learning, finding that experimentally resolved structures provide more accurate interaction patterns and greater binding-site diversity compared to structures predicted by AlphaFold3, TCRModel2, and tFold-TCR. AI

IMPACT This research could lead to more accurate and interpretable tools for developing immunotherapies.

RANK_REASON The cluster contains an academic paper detailing a new model and its evaluation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• AlphaFold3
• epitope
• T cell receptor
• TCRModel2
• TCR-SRIM
• TCR-XAI
• tFold-TCR

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →