Fig. 1. Schematic illustration of GIANA.

GIANA workflow. GIANA began with encoding of short CDR3 peptide sequences into numeric vectors through a sequence of unitary transformations. The transformation involves an element of 6^th order cyclic group. After encoding, each CDR3 sequence was projected to high-dimensional Euclidean space, allowing fast nearest neighbor search for clustering. Follow-up filtering steps were performed to match the TRBV gene alleles and remove pairs with low alignment scores.