Figure 8.

Separation by structural properties in the latent space when 2 latent dimensions are used in the model. The axes are the 2 latent dimensions and each point is the encoded representation in the 2 dimensions of one input sequence. Clusters generally correspond to the homologues collected for each sequence. (A) Each sequence is coloured by CATH class32 according to the colours shown. (B) Sequences for one CATH architecture, ‘mainly beta single sheet’ (CATH ID 2.20), are highlighted in red.