PP
Paul Pereira
Author with expertise in Prediction of Peptide-MHC Binding Affinity
Achievements
Open Access Advocate
Cited Author
Key Stats
Upvotes received:
0
Publications:
1
(100% Open Access)
Cited by:
10
h-index:
2
/
i10-index:
2
Reputation
Biology
< 1%
Chemistry
< 1%
Economics
< 1%
Show more
How is this calculated?
Publications
1

Benchmarking solutions to the T-cell receptor epitope prediction problem: IMMREP22 workshop report

Pieter Meysman et al.Oct 28, 2022
+16
B
J
P
Abstract Many different solutions to predicting the cognate epitope target of a T-cell receptor (TCR) have been proposed. However several questions on the advantages and disadvantages of these different approaches remain unresolved, as most methods have only been evaluated within the context of their initial publications and data sets. Here, we report the findings of the first public TCR-epitope prediction benchmark performed on 23 prediction models in the context of the ImmRep 2022 TCR-epitope specificity workshop. This benchmark revealed that the use of paired-chain alpha-beta, as well as CDR1/2 or V/J information, when available, improves classification obtained with CDR3 data, independent of the underlying approach. In addition, we found that straight-forward distance-based approaches can achieve a respectable performance when compared to more complex machine-learning models. Finally, we highlight the need for a truly independent follow-up benchmark and provide recommendations for the design of such a next benchmark.