2023
DOI: 10.1101/2023.05.16.541002
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Automated model building and protein identification in cryo-EM maps

Abstract: Interpreting electron cryo-microscopy (cryo-EM) maps with atomic models requires high levels of expertise and labour-intensive manual intervention. We present ModelAngelo, a machine-learning approach for automated atomic model building in cryo-EM maps. By combining information from the cryo-EM map with information from protein sequence and structure in a single graph neural network, ModelAngelo builds atomic models for proteins that are of similar quality as those generated by human experts. For nucleotides, M… Show more

Help me understand this report
View published versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
55
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
3
3
3

Relationship

0
9

Authors

Journals

citations
Cited by 71 publications
(55 citation statements)
references
References 62 publications
0
55
0
Order By: Relevance
“…Positioning the ligand in BD2 was compatible with electron density, whereas positioning in BD1 caused a clash with DCAF16 due to the rigid linker. DCAF16 was built using a combination of models from ColabFold 69,70 (version 1.3), ModelAngelo 71 (version 0.2.2) and manual building in Coot. ColabFold correctly predicted the α5 and α6 helices that bind the DDB1 central cavity while ModelAngelo correctly built the 4-helical bundle of α3, 4, 7 and 8, as well as α6 in the DDB1 cavity.…”
Section: Methodsmentioning
confidence: 99%
“…Positioning the ligand in BD2 was compatible with electron density, whereas positioning in BD1 caused a clash with DCAF16 due to the rigid linker. DCAF16 was built using a combination of models from ColabFold 69,70 (version 1.3), ModelAngelo 71 (version 0.2.2) and manual building in Coot. ColabFold correctly predicted the α5 and α6 helices that bind the DDB1 central cavity while ModelAngelo correctly built the 4-helical bundle of α3, 4, 7 and 8, as well as α6 in the DDB1 cavity.…”
Section: Methodsmentioning
confidence: 99%
“…The dome‐shaped reconstruction that was retrieved (Figure 2F) could not be built with current refinement tools; due to the resolution of ∼8 Å, AI tools like FindMySequence [42], DeepTracer [43], or ModelAngelo [44] are not applicable. To address this issue, the 150 most abundant proteins were selected, ribosomal proteins were excluded, and modeling was focused on less abundant protein signatures.…”
Section: Resultsmentioning
confidence: 99%
“…This suggests that the parallel ridge of unidentified densities outside this segment is only present in some of the fibrils. Model building using Model Angelo 49 suggests that these unidentified densities may correspond to R2 residues K281-Q288, with a correlation coefficient of 0.3 between the map and the model ( Fig. S8 ).…”
Section: Resultsmentioning
confidence: 99%