QMEAN

HelpCAMEO evaluation

Untitled Project (Created: 4 days, 21 hours ago)Project Archive

Total model count : 1.

Uploaded Structure:selected_prediction.pdb
Method:QMEANDisCo
QMEAN Version:4.5.0
SMTL Version:2025-11-12
SEQRES: Not specified - sequence was extracted from coordinates.
Results:JSON

Quality for selected_prediction.pdb

QMEANDisCo Global:0.83 ± 0.05
⚠ During preprocessing, 493 atoms were removed .
removing atoms with zero occupancy
 --> removed 0 atoms with zero occupancy
removing hydrogen atoms
 --> removed 493 hydrogen atoms

Sequence colored by local quality:

Reference for the QMEAN scoring function:
[1]
Benkert P, Biasini M, Schwede T
Toward the estimation of the absolute quality of individual protein structure models.
Bioinformatics 27, 343-350. (2011) PubMed logo21134891DOI logo10.1093/bioinformatics/btq662

Reference for the QMEANDisCo scoring function:
[2]
Studer G, Rempfer C, Waterhouse AM, Gumienny R, Haas J, Schwede T
QMEANDisCo - distance constraints applied on model quality estimation.
Bioinformatics 36, 1765-1771. (2020) PubMed logo31697312DOI logo10.1093/bioinformatics/btz828

Reference for the QMEANBrane scoring function:
[3]
Studer G, Biasini M, Schwede T
Assessing the local structural quality of transmembrane protein models using statistical potentials (QMEANBrane).
Bioinformatics 30, i505–i511. (2014) PubMed logo25161240DOI logo10.1093/bioinformatics/btu457

A single model method combining statistical potentials and agreement terms in a linear manner
A single model method combining statistical potentials and agreement terms with a distance constraints (DisCo) score. DisCo evaluates consistencies of pairwise CA-CA distances from a model with constraints extracted from homologous structures. All scores are combined using a neural network trained to predict per-residue lDDT scores.
QMEANBrane is a combination of statistical potentials targeted at local quality estimation of membrane protein models in their naturally occurring oligomeric state: after identifying the transmembrane region using an implicit solvation model, specifically trained statistical potentials get applied on the different regions of a protein model
Reference sequence (SEQRES) of submitted protein model. This sequence is used for secondary structure and solvent accessibility predictions. If not provided, the sequence gets directly extracted from the model. See the help page for further input information.
The plot relates the obtained global QMEAN4 value to scores calculated from a set of high-resolution X-ray structures.
Local quality is either estimated using the raw QMEAN scoring function or one of the two specialized functions QMEANBrane and QMEANDisCo. They all provide scores in range [0,1] with one being good.
QMEAN4 is a linear combination of four statistical potential terms. It is trained to predict global lDDT score in range [0,1]. The value displayed here is transformed into a Z-score to relate it with what one would expect from high resolution X-ray structures.
The QMEANDisCo global score is the average per-residue score and the provided error estimate is based on global QMEANDisCo scores estimated for a large set of models and represents the root mean squared difference (i.e. standard deviation) between QMEANDisCo global score and lDDT (the ground truth). As the reliability of the prediction heavily depends on model size, the provided error estimate is calculated based on models of similar size to the input.