4.5 Article

DeepTracer-ID: De novo protein identification from cryo-EM maps

Journal

BIOPHYSICAL JOURNAL
Volume 121, Issue 15, Pages 2840-2848

Publisher

CELL PRESS
DOI: 10.1016/j.bpj.2022.06.025

Keywords

-

Categories

Funding

  1. School of Medicine and built
  2. NIH [G20-RR31199, GM122510, K99GM138756, K99CA259526]
  3. NSF [2030381]
  4. University of Washington Bothell
  5. l'Agence Nationale de la Recherche [ANR-21-CE11-0001-01]
  6. Div Of Biological Infrastructure
  7. Direct For Biological Sciences [2030381] Funding Source: National Science Foundation

Ask authors/readers for more resources

The recent revolution in cryo-electron microscopy has allowed for the direct determination of macromolecular structures from cell extracts. However, accurately identifying the correct protein from a cryo-EM map is still challenging and often requires additional information. In this study, the researchers propose a server-based method called DeepTracer-ID that can identify candidate proteins from a cryo-EM map without the need for extra information. The method utilizes DeepTracer to generate a protein backbone model and searches it against a library of AlphaFold2 predictions for all proteins in the organism. The method showed high accuracy and robustness in identifying proteins from high-resolution cryo-EM maps.
The recent revolution in cryo-electron microscopy (cryo-EM) has made it possible to determine macromolecular structures directly from cell extracts. However, identifying the correct protein from the cryo-EM map is still challenging and often needs additional sequence information from other techniques, such as tandem mass spectrometry and/or bioinformatics. Here, we present DeepTracer-ID, a server-based approach to identify the candidate protein in a user-provided organism de novo from a cryo-EM map, without the need for additional information. Our method first uses DeepTracer to generate a protein backbone model that best represents the cryo-EM map, and this model is then searched against the library of AlphaFold2 predictions for all proteins in the given organism. This method is highly accurate and robust for high-resolution cryo-EM maps: in all 13 experimental maps tested blindly, DeepTracer-ID identified the correct proteins as the top candidates. Eight of the maps were of known structures, while the other five unpublished maps were validated by prior protein annotation and careful inspection of the model refined into the map. The program also showed promising results for both homomeric and heteromeric protein complexes. This platform is possible because of the recent breakthroughs in large-scale three-dimensional protein structure prediction.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.5
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available