Optimization for the latent dimension for BPTI (left panel) and EGFR (right panel).

The optimized value Δ² = (〈H_min〉_generated− 〈H_min〉_natural)² (y-axis) is plotted against the latent dimension K (x-axis). For each sequence in an ensemble (natural or generated) H_min is calculated by obtaining the minimum fractional Hamming distance to the natural sequences. Each box plot represents 10 runs, each run with a different random initialization, for each latent dimension. The optimum latent dimension is determined as the one that minimizes the average value of Δ² across the 10 runs. Optimal dimension for BPTI is 42, and for EGFR is 19.