ProteinMPNN-ddG Online Tool

Deep learning protein sequence models have shown outstanding performance at de novo protein design and variant effect prediction. We substantially im- prove performance without further training or use of additional experimental data by introducing a second term derived from the models themselves which align outputs for the task of stability prediction. On a task to predict variants which increase protein stability the absolute success probabilities of PROTEIN- MPNN and ESMIF are improved by 11% and 5% respectively. We term these models PROTEINMPNN-DDG and ESMIF-DDG