[HTML][HTML] SwarmTCR: a computational approach to predict the specificity of T cell receptors

R Ehrlich, L Kamga, A Gil, K Luzuriaga, LK Selin… - BMC …, 2021 - Springer
R Ehrlich, L Kamga, A Gil, K Luzuriaga, LK Selin, D Ghersi
BMC bioinformatics, 2021Springer
Background With more T cell receptor sequence data becoming available, the need for
bioinformatics approaches to predict T cell receptor specificity is even more pressing. Here
we present SwarmTCR, a method that uses labeled sequence data to predict the specificity
of T cell receptors using a nearest-neighbor approach. SwarmTCR works by optimizing the
weights of the individual CDR regions to maximize classification performance. Results We
compared the performance of SwarmTCR against another nearest-neighbor method and …
Background
With more T cell receptor sequence data becoming available, the need for bioinformatics approaches to predict T cell receptor specificity is even more pressing. Here we present SwarmTCR, a method that uses labeled sequence data to predict the specificity of T cell receptors using a nearest-neighbor approach. SwarmTCR works by optimizing the weights of the individual CDR regions to maximize classification performance.
Results
We compared the performance of SwarmTCR against another nearest-neighbor method and showed that SwarmTCR performs well both with bulk sequencing data and with single cell data. In addition, we show that the weights returned by SwarmTCR are biologically interpretable.
Conclusions
Computationally predicting the specificity of T cell receptors can be a powerful tool to shed light on the immune response against infectious diseases and cancers, autoimmunity, cancer immunotherapy, and immunopathology. SwarmTCR is distributed freely under the terms of the GPL-3 license. The source code and all sequencing data are available at GitHub ( https://github.com/thecodingdoc/SwarmTCR ).
Springer