Appendix for " Disentangled Wasserstein Autoencoder for Protein Engineering " Anonymous Author(s) Affiliation Address email 1 Data preparation 1 1.1 Combination of data sources 2

We repeat this process until the size of the negative set is 5x that of the positive set. The expanded dataset is then provided to the respective ERGO model. Any unobserved pair is treated as negative. Performance is shown in Table S2. TCRs that have more than one positive prediction or have at least one wrong prediction.