Skip to main content
. 2023 Dec 18;3:1274599. doi: 10.3389/fbinf.2023.1274599

FIGURE 1.

FIGURE 1

Overview of our cross-TCR-interpreter model. Data tensor sizes are denoted. The cross-attention layers in the middle of the figure were analyzed using structural data after being trained with sequence data. Each embedding layer takes amino acid sequences as the input.