DecoderTCR: Compositional Pretraining and Entropy-Guided Decoding for TCR-pMHC Interactions
Lai, B.; Englund, M.; Bharanikumar, R.; Nocedal, I.; Davariashtiyani, A.; Perera, J.; Khan, A. A.
Show abstract
Modeling recognition between T-cell receptors (TCRs) and peptide-MHC (pMHC) complexes is a fundamental challenge in computational immunology, constrained by sparse paired interaction data relative to abundant unpaired sequences. We introduce DecoderTCR, a masked language model framework that addresses this through two contributions: (1) a compositional continual pre-training curriculum that learns component representations from marginal data before refining cross-chain dependencies from limited pairs, and (2) Iterative Entropy-Guided Refinement (IEGR), a non-autoregressive decoding algorithm that resolves high-confidence positions first to provide context for uncertain regions. On held-out benchmarks, DecoderTCR achieves 0.96 AUROC for zero-shot pMHC binding prediction and 0.76 AUROC for epitope-specific TCR recognition, approaching supervised baselines without epitope-specific training. Learned representations recover structural contacts without coordinate supervision, and generated sequences exhibit realistic recombination statistics. Experimental validation reveals a prediction-generation gap: strong discrimination does not yet yield reliable generation, highlighting an open challenge for the field.
Matching journals
The top 1 journal accounts for 50% of the predicted probability mass.
Similar papers in this journal
- BERTrand - peptide:TCR binding prediction using Bidirectional Encoder Representations from Transformers augmented with random TCR pairing 96%
- EPIC-TRACE: predicting TCR binding to unseen epitopes using attention and contextualized embeddings 96%
- BERTMHC: Improves MHC-peptide class II interaction prediction with transformer and multiple instance learning 95%
Similar papers in this journal
- Paraplume: A fast and accurate paratope prediction method provides insights into repertoire-scale binding dynamics 95%
- Nucleotide context models outperform protein language models for predicting antibody affinity maturation 94%
- Design of immunogens for eliciting antibody responses that may protect against SARS-CoV-2 variants 94%
Similar papers in this journal
Similar papers in this journal
- TEINet: a deep learning framework for prediction of TCR-epitope binding specificity 93%
- Current challenges for epitope-agnostic TCR interaction prediction and a new perspective derived from image classification 93%
- Scalable embedding fusion with protein language models: insights from benchmarking text-integrated representations 92%
Similar papers in this journal
- Echidna: integrated simulations of single-cell immune receptor repertoires and transcriptomes 94%
- Refining the cis-regulatory grammar learned by sequence-to-activity models by increasing model resolution 92%
- nanoBERT: A deep learning model for gene agnostic navigation of the nanobody mutational space 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.