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
Predicted Aligned Error (PAE) is a term that is primarily used in the context of various prediction or estimation models, particularly in machine learning and data science, though it may not be a widely recognized term across all fields. The concept generally relates to assessing the accuracy and alignment of predictions made by a model compared to actual outcomes. In essence, PAE can denote the extent to which predictions deviate from actual values, emphasizing how well the predicted outcomes match the expected results.