Improved AlphaFold modeling with implicit experimental information.

Journal Article (Journal Article)

Machine-learning prediction algorithms such as AlphaFold and RoseTTAFold can create remarkably accurate protein models, but these models usually have some regions that are predicted with low confidence or poor accuracy. We hypothesized that by implicitly including new experimental information such as a density map, a greater portion of a model could be predicted accurately, and that this might synergistically improve parts of the model that were not fully addressed by either machine learning or experiment alone. An iterative procedure was developed in which AlphaFold models are automatically rebuilt on the basis of experimental density maps and the rebuilt models are used as templates in new AlphaFold predictions. We show that including experimental information improves prediction beyond the improvement obtained with simple rebuilding guided by the experimental data. This procedure for AlphaFold modeling with density has been incorporated into an automated procedure for interpretation of crystallographic and electron cryo-microscopy maps.

Full Text

Duke Authors

Cited Authors

  • Terwilliger, TC; Poon, BK; Afonine, PV; Schlicksup, CJ; Croll, TI; Millán, C; Richardson, JS; Read, RJ; Adams, PD

Published Date

  • November 2022

Published In

Volume / Issue

  • 19 / 11

Start / End Page

  • 1376 - 1382

PubMed ID

  • 36266465

Pubmed Central ID

  • PMC9636017

Electronic International Standard Serial Number (EISSN)

  • 1548-7105

Digital Object Identifier (DOI)

  • 10.1038/s41592-022-01645-6


  • eng

Conference Location

  • United States