Expected positional error at one residue after predicted and true structures are aligned on another residue. Low within-domain values with high between-domain values support more confident internal geometry than relative domain placement. PAE is not a physical residue–residue distance and need not be symmetric.[ref]
PAE: A measure of global confidence in AlphaFold2 predictions by EMBL-EBI. Formal definition and interpretation of inter-domain confidence
Articles by others on the same topic
AlphaFold is an artificial intelligence system developed by DeepMind, designed to predict protein structures from amino acid sequences. It utilizes deep learning techniques to model the complex physical interactions that govern how proteins fold into their three-dimensional shapes, which is crucial for understanding their functions in biological processes. The importance of AlphaFold lies in its ability to accurately predict protein structures at a level of detail that has not been achievable with traditional experimental methods alone, such as X-ray crystallography or cryo-electron microscopy.
