Predicting recognition between T cell receptors and epitopes using contextualized motifs
Jokinen, E.; Dumitrescu, A.; Huuhtanen, J.; Gligorijevic, V.; Heinonen, M.; Mustjoki, S.; Bonneau, R.; Lähdesmäki, H.
Show abstract
We introduce TCRconv, a deep learning model for predicting recognition between T-cell receptors and epitopes. TCRconv uses a deep protein language model and convolutions to extract contextualized motifs and provides state-of-the-art TCR-epitope prediction accuracy. Using TCR repertoires from COVID-19 patients, we demonstrate that TCRconv can provide insight into T-cell dynamics and phenotypes during the disease.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Deep learning predictions of TCR-epitope interactions reveal epitope-specific chains in dual alpha T cells 97%
- NeoPrecis: Enhancing Immunotherapy Response Prediction through Integration of Qualified Immunogenicity and Clonality-Aware Neoantigen Landscapes 96%
- APMAT analysis reveals the association between CD8 T cell receptors, cognate antigen, and T cell phenotype and persistence 96%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- Deep autoregressive generative models capture the intrinsics embedded in T-cell receptor repertoires 97%
- DeepImmuno: Deep learning-empowered prediction and generation of immunogenic peptides for T cell immunity 94%
- Rigorous benchmarking of T cell receptor repertoire profiling methods for cancer RNA sequencing 93%
Similar papers in this journal
- Chrysalis: decoding tissue compartments in spatial transcriptomics with archetypal analysis 94%
- T-cell receptor structures and predictive models reveal comparable alpha and beta chain structural diversity despite differing genetic complexity 93%
- Frequency-dependent selection of neoantigens fosters tumor immune escape and predicts immunotherapy response 93%
"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.