T-cell Receptor Diversity Estimates for Repertoires (TCRDivER) uses sequence similarity to find signatures of immune response
Vujovic, M.; Marcatelli, P.; Chain, B.; Kaplinsky, J.; Andresen, T. L.
Show abstract
We propose TCRDivER, a global approach to T-cell repertoire comparison using diversity profiles sensitive to both clone size and sequence similarity. As immunotherapies improve, the long standing biological interest in connecting outcome with T cell receptor (TCR) repertoire status has become more urgent. Here we show that new insights can be extracted from high throughput repertoire sequencing data. Most current efforts focus on identification of immunisation-specific sequence motifs or on monitoring changes in frequency of individual clones. Applying TCRDivER to murine spleen samples shows it characterises an additional dimension of repertoire variation, beyond conventional diversity estimates, allowing distinction between immunised and non-immunised samples. We further apply TCRDivER to repertoires from human blood. In both cases we show characteristic relationships between repertoire features. These reveal biologically interpretable relationships between sequence similarity and clonal expansions. We thereby demonstrate a new tool for investigation in clinical and research applications.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Somatic hypermutation analysis for improved identification of B cell clonal families from next-generation sequencing data 96%
- An Integrated Approach to the Characterization of Immune Repertoires Using AIMS: An Automated Immune Molecule Separator 94%
- Using B cell receptor lineage structures to predict affinity 93%
Similar papers in this journal
- A Novel Approach to T-Cell Receptor Beta Chain (TCRB) Repertoire Encoding Using Lossless String Compression 95%
- Rapid T cell receptor interaction grouping with ting 94%
- BERTrand - peptide:TCR binding prediction using Bidirectional Encoder Representations from Transformers augmented with random TCR pairing 94%
Similar papers in this journal
- Interpretable deep learning to uncover the molecular binding patterns determining TCR-epitope interactions 93%
- Guiding a language-model based protein design method towards MHC Class-I immune-visibility profiles for vaccines and therapeutics 93%
- DoggifAI: a transformer based approach for antibodycaninisation 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.