Liel Cohen-Lavi

BenchRep-T evaluates nine T-cell repertoire methods across four tasks, finding simple baselines competitive with complex models and no single method dominates all tasks.

The paper designs HLA class I superbinders using a computational framework, identifying peptides that bind multiple HLA alleles and showing broad immunogenic potential.

The paper benchmarks 23 TCR-epitope prediction models, finding that using paired-chain alpha-beta and CDR1/2/V/J data improves performance, and simple distance-based methods can be competitive.