The end of protein structure prediction: Improving prediction accuracy in chimeric proteins by windowed multiple sequence alignment

AlphaFold2 has predicted the structures of almost every known protein. A simple means to create proteins beyond those found in nature, is by unnaturally fusing together two known proteins. Here we demonstrate that dependence on multiple sequence alignment, limits the success with which AlphaFold and ESMfold capture such chimeric forms of otherwise well predicted, individual, proteins. Specifically we show that peptides are predicted with significantly reduced accuracy when added to the terminal ends of scaffold proteins. Appending the multiple sequence alignment for the individual peptide tags to that of the scaffold protein often restores prediction accuracy.