A fully automatic method yielding initial models from high-resolution cryo-electron microscopy maps

Abstract

We report a fully automated procedure for the optimization and interpretation of reconstructions from cryo-electron microscopy (cryo-EM) data, available in Phenix as phenix.map_to_model. We applied our approach to 476 datasets with resolution of 4.5 Å or better, including reconstructions of 47 ribosomes and 32 other protein-RNA complexes. The median fraction of residues in the deposited structures reproduced automatically was 71% for reconstructions determined at resolutions of 3 Å or better and 47% for those at resolutions worse than 3 Å.

Fig. 1.

Automated interpretation of cryo-EM maps. A. Section through deposited cryo-EM reconstruction and deposited interpretation for lactate dehydrogenase (EMDB entry 8191). B. Automatically sharpened version of map in A with automatically generated model (PDB entry 5k0z). C. Automatic interpretation of β-galactosidase at a resolution of 2.2 Å. D. Automatically sharpened version of map for EMDB entry 6630 (glutamate dehydrogenase) with three independent automatically-generated interpretations (using chain-tracing, green model, feature-based helix and strand identification, blue model, and pattern-based secondary structure identification with fragment-based extension, magenta model). E. Composite model derived from the three models in D. F. Automatically interpreted reconstruction of the Mycobacterium smegmatis ribosome (yellow tubes) compared with deposited model (green ribbons). G. Automatically generated model of the ERAD channel Hrd1 (purple ribbons) compared with deposited model (brown ribbons). H. detail of automatically-built Mycobacterium smegmatis ribosome, and I, corresponding portion of deposited model. See text for details. Graphics created with Chimera.

Fig. 2.

Residues in deposited models reproduced by automated analysis of cryo-EM reconstructions. Protein chains are indicated by blue dots and RNA chains are indicated by open brown diamonds. Residues are considered matched if C_α atom or P atom coordinates match within 3 Å (see Methods). Rms coordinate differences are assessed for all matched residues. A. Fraction of residues in deposited structure reproduced by automated analysis. Blue dots are protein chains and orange squares are RNA chains in panels A-C. B. Rms coordinate differences between matched residues in deposited structure and automated analysis. C. Fraction of residues in automated analysis matching a residue in the deposited model that also share the residue type of the matching residue in the deposited structure. The expected fraction matching based on random sequence assignment is roughly 6% for protein with 20 amino acids with frequencies in eukaryotes and roughly 25% for RNA with 4 bases and similar frequencies, illustrated by the horizontal lines in Fig. 2C. D and E, automatically generated and deposited models of horse spleen apoferritin (EMDB entry 2788 and PDB entry 4v1w). F. Comparison of fraction of deposited models reproduced by MAINMAST (blue diamonds), de novo Rosetta modeling (purple circles), and using the automated procedure described here (red triangles), all based on maps cut out from deposited maps based on a single chain of the deposited model as described. Graphics created with Chimera.