PAE Viewer: A webserver for the interactive visualization of the predicted aligned error for multimer structure predictions and crosslinks
Elfmann, C.; Stuelke, J.
Show abstract
The development of AlphaFold for protein structure prediction has opened a new era in structural biology. This is even more the case for AlphaFold-Multimer for the prediction of protein complexes. The interpretation of these predictions has become more important than ever, but it is difficult for the non-specialist. While an evaluation of the prediction quality is provided for monomeric protein predictions by the AlphaFold Protein Structure Database, such a tool is missing for predicted complex structures. Here, we present the PAE Viewer webserver (http://www.subtiwiki.uni-goettingen.de/v4/paeViewerDemo), an online tool for the integrated visualization of predicted protein complex using a 3D structure display combined with an interactive representation of the Predicted Aligned Error (PAE). This metric allows an estimation of the quality of the prediction. Importantly, our webserver also allows the integration of experimental cross-linking data which helps to interpret the reliability of the structure predictions. With the PAE Viewer, the user obtains a unique tool which for the first time allows the intuitive evaluation of the PAE for protein complex structure predictions. GRAPHICAL ABSTRACT O_FIG_DISPLAY_L [Figure 1] M_FIG_DISPLAY The Predicted Aligned Error (PAE) is an indication of the reliability of protein structure predictions. The PAE Viewer webserver allows the intuitive and interactive evaluation of complex structure predictions. C_FIG_DISPLAY
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A3D Database: Structure-based Protein Aggregation Predictions for the Human Proteome 96%
- MutaFrame - an interpretative visualization framework for deleteriousness prediction of missense variants in the human exome 95%
- PICKLUSTER: A protein-interface clustering and analysis plug-in for UCSF ChimeraX 95%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.