Unlock your biological data


Try: RNA sequencing CRISPR Genomic databases DESeq

Quality assessment software tools | Protein structure data analysis

Protein quality assessment (QA) useful for ranking and selecting protein models has long been viewed as one of the major challenges for protein tertiary structure prediction. Especially, estimating the quality of a single protein model, which is important for selecting a few good models out of a large model pool consisting of mostly low-quality models, is still a largely unsolved problem.

Source text:
(Cao et al., 2016) DeepQA: improving the estimation of single protein model quality with deep belief networks. BMC Bioinformatics.

1 - 37 of 37 results
filter_list Filters
build Technology
healing Disease
settings_input_component Operating System
tv Interface
computer Computer Skill
copyright License
1 - 37 of 37 results
A method for estimating the absolute quality of a single protein structure, i.e. without including additional information from other models or alternative template structures. QMEAN is based on the composite scoring function which evaluates several structural features of proteins. The absolute quality estimate of a model is expressed in terms of how well the model score agrees with the expected values from a representative set of high resolution experimental structures. The resulting QMEAN Z-score is a measure of the ‘degree of nativeness’ of a given protein structure. The Z-scores of the individual components of the composite QMEAN score point to structural descriptors that contribute most to the final score, and thereby indicate potential reasons for ‘bad’ models.
star_border star_border star_border star_border star_border
star star star star star
A single-model quality assessment (QA) method. Different from other single-model QA methods, Qprob estimates the prediction error estimation of several different physicochemical, structural and energy feature scores, and use the combination of probability density distribution of the errors for the global quality assessment. We blindly tested our method in the CASP11 experiment, and it was ranked as one of the best single-model QA method based on the CASP official evaluation and our own evaluations. In particular, the good performance of our method on template free targets demonstrates its good capability of selecting models for hard targets.
RPF / Recall Precision F-measure
Validates ‘R-factor’-like protein structure. RPF calculates a discriminating power (DP) score that estimates how well the query structure satisfies the data relative to a statistical random-coil structure. It is able to analyze homodimeric proteins. The tool can be used for large-scale nuclear magnetic resonance (NMR) structure quality assessments. It provides an effective and convention tool for evaluating and validating protein structures derived from NOESY data.
ProTSAV / Protein Structure Analysis and Validation
star_border star_border star_border star_border star_border
star star star star star
Furnishes the user with a single quality score in case of individual protein structure along with a graphical representation and ranking in case of multiple protein structure assessment. ProTSAV is capable of evaluating predicted model structures based on some popular online servers and standalone tools. It succeeds in predicting quality of protein structures with a specificity of 100% and a sensitivity of 98% on experimentally solved structures.
Apollo / Assessing Protein single or multiple models
star_border star_border star_border star_border star_border
star star star star star
A web server to provide the community with access to all three model quality assessment approaches (i.e. single, clustering and hybrid). Apollo evaluates the absolute global and local qualities of a single protein model using machine learning methods or the global and local qualities of a pool of models using a pair-wise comparison approach. Based on our evaluations on 107 CASP9 (Critical Assessment of Techniques for Protein Structure Prediction) targets, the predicted quality scores generated from our machine learning and pair-wise methods have an average per-target correlation of 0.671 and 0.917, respectively, with the true model quality scores. Based on our test on 92 CASP9 targets, our predicted absolute local qualities have an average difference of 2.60 Å with the actual distances to native structure.
VADAR / Volume Area Dihedral Angle Reporter
Calculates, identifies, graphs, reports and/or evaluates a large number (>30) of key structural parameters both for individual residues and for the entire protein. VADAR is a comprehensive web server for quantitative protein structure evaluation. The web server produces extensive tables and high quality graphs for quantitatively and qualitatively assessing protein structures determined by X-ray crystallography, NMR (Nuclear magnetic resonance) spectroscopy, 3D-threading or homology modelling.
PROSESS / Protein Structure Evaluation Suite & Server
Evaluates and validates protein structures solved by either X-ray crystallography or NMR (Nuclear magnetic resonance) spectroscopy. PROSESS integrates a variety of previously developed, well-known and thoroughly tested methods to evaluate both global and residue-specific: covalent and geometric quality, non-bonded/packing quality, torsion angle quality, chemical shift quality and NOE (Nuclear Overhauser Enhancements) quality. The web application produces detailed tables, explanations, structural images and graphs that summarize the results and compare them to values observed in high-quality or high-resolution protein structures.
Examines the compatibility between the sequence and the structure of a protein by assigning scores to individual residues and their amino acid exchange patterns after considering their local environments. Harmony is a server to assess the compatibility of an amino acid sequence with a proposed three-dimensional structure. Users can submit their protein structure files and, if required, the alignment of homologous sequences. Scores are mapped on the structure for subsequent examination that is useful to also recognize regions of possible local errors in protein structures.
A novel Model Quality Assessment Program that compares 3D models of proteins without the need for CPU intensive structural alignments by utilizing the Q measure for model comparisons. ModFOLDclust carries out clustering of multiple models and provides per-residue local quality assessment. The ModFOLDclustQ method is benchmarked against the top established methods in terms of both accuracy and speed. In addition, the ModFOLDclustQ scores are combined with those from our older ModFOLDclust method to form a new method, ModFOLDclust2, that aims to provide increased prediction accuracy with negligible computational overhead.
A quality assessment program based on the consistency between the model structure and the protein’s conservation pattern. ConQuass can identify problematic structural models, and that the scores it assigns to the server models in CASP8 correlate with the similarity of the models to the native structure. When the conservation information is reliable, the method's performance is comparable and complementary to that of the other single-structure quality assessment methods that participated in CASP8 and that do not use additional structural information from homologs.
Uses a support vector machine (SVM) to predict the quality of a membrane protein model by combining structural and sequence-based features calculated from the model. ProQM-resample is a model quality assessment program (MQAP) that was incorporated as scoring function in the Rosetta modelling framework. This gives in one hand full access to the modelling machinery within Rosetta and allows for easy integration with any Rosetta protocol. In particular, ProQM-resample uses the repack protocol to sample side-chain conformations followed by rescoring using ProQM to improve model selection.
PDBest / PDB enhanced structures toolkit
Aims to help researchers and students to manipulate and treat PDB files in a high-throughput fashion in order to guarantee high quality data for posterior analyses. It has a user-friendly graphical user interface developed to allows even users with no computing background to download and manipulate theirs PDB files without using command line. Among its several features, PDBest is able to identify and correct formatting errors or inconsistencies, adding hydrogens as well as comprehensively filtering/selecting subsets of atoms, residues or chains.
MUGAN / Multi-GPU accelerated AmpliconNoise
Allows users to denoise next generation sequencing (NGS) pyrosequenced reads. MUGAN provides a platform dedicated to the removal of errors by exploiting data-level parallelism. The software merges multiple graphics processing units (GPUs), central processing units (CPUs) to the AmpliconNoise software. It aims to perform a faster denoising of information as well as to provide an improved visualization of error-correction and diversity-estimation results.
GMQ / Graph-based Model Quality assessment method
Predicts local quality of a structure model by considering quality of neighboring residues. GMQ uses conditional random field and performs a binary prediction of the quality of each residue in a model and takes into account target residue as well as the predicted quality of neighboring residues. The software provides a target structure model which shows a graph surrounded by residues that are physically closer than a certain cutoff distance.
RFMQA / Random Forest-Based Protein Model Quality Assessment
Estimates the relative quality of a set of model protein structures. RFMQA combines various scoring functions and consistency terms between predicted values and calculated values from 3D models. It can calculate the relative score of a single model to rank 3D protein models. Then, the tool can identify the best model and can be useful to predict quality assurance component for any protein structure. It was evaluated on the CASP10 target set.
A machine learning model evaluation method to predict the quantitative absolute quality score of a single model using structural features extracted from its 3D coordinates and predicted from its primary sequence. ModelEvaluator compares structural features generated from a 3D model with those predicted from its primary sequence by 1D and 2D structural feature predictors. These features include secondary structure, solvent accessibility, contact map, and beta-sheet topology. This comparison method results in a number of fitness scores used as input features for a support vector machine (SVM) to evaluate the quality of a model. This method shows good performance for both correlation between predicted and true quality scores and model ranking when applied to CASP6 and CASP7 datasets.
A model quality assessment algorithm that uses support vector machines to predict local as well as global quality of protein models. ProQ2 was developed to improve both local and global single-model quality assessment. This was done by training support vector machines to predict the local quality measure, S-score, with a combination of evolutionary and multiple sequence alignment information combined with other structural features on data from CASP7. We show that ProQ2 is superior to its predecessor ProQ in all aspects. ProQ2 is significantly better than the top-performing single-model quality assessment groups in both CASP8 and CASP9. Finally, we also show that ProQ2 combined with the consensus predictor Pcons can improve the selection even further.
GOBA / Gene Ontology-Based Assessment
A protein model quality assessment program. GOBA estimates the compatibility between a model-structure and its expected function. GOBA is based on the assumption that a high quality model is expected to be structurally similar to proteins functionally similar to the prediction target. Whereas DALI is used to measure structure similarity, protein functional similarity is quantified using standardized and hierarchical description of proteins provided by Gene Ontology combined with Wang's algorithm for calculating semantic similarity. Two approaches are proposed to express the quality of protein model-structures. One is a single model quality assessment method, the other is its modification, which provides a relative measure of model quality. The validation shows that the method is able to discriminate between good and bad model-structures.
Predicts the atomic resolution of nuclear magnetic resonance (NMR) protein structures. ResProx estimates, with a correlation coefficient of 0.92 between observed and calculated, the atomic resolution of a protein structure from 25 measurable features that can be derived from its atomic coordinates. The webserver can be used to identify under-restrained, poorly refined or inaccurate NMR structures, and can discover structural defects that the other equivalent resolution methods cannot detect.
A single-model quality assessment method based on deep belief network that utilizes a number of selected features describing the quality of a model from different perspectives, such as energy, physio-chemical characteristics and structural information. DeepQA is a useful deep learning tool for protein single model quality assessment and protein structure prediction. DeepQA is also useful for ranking ab initio protein models and could be further improved by incorporating more relevant features and training on larger datasets.
MQAPRank / Model Quality Assessment Program Rank
Assesses global protein model quality. MQAPRank is based on a learning-to-rank approach and uses single method to sort the decoy models. Models are classified by their similarities with the corresponding native structures. The tool extracts knowledge-based mean force potentials and the evaluation scores of several programs for protein model quality assessment from the decoy models. It was evaluated on the CASP11 (11th Community Wide Experiment on the Critical Assessment of Techniques for Protein Structure Prediction) dataset.
VoroMQA / Voronoi tessellation-based Model Quality Assessment
Allows for the estimation of protein structure quality. VoroMQA combines the idea of statistical potentials with the use of interatomic contact areas instead of distances. Contact areas, derived using Voronoi tessellation of protein structure, are used to describe and seamlessly integrate both explicit interactions between protein atoms and implicit interactions of protein atoms with solvent. VoroMQA produces scores at atomic, residue and global levels, all in the fixed range from 0 to 1. The method was tested on the CASP data and compared to several other single-model quality assessment methods. VoroMQA showed strong performance in the recognition of the native structure and in the structural model selection tests, thus demonstrating the efficacy of interatomic contact areas in estimating protein structure quality. The software implementation of VoroMQA is freely available as a standalone application and as a web server.
0 - 0 of 0 results
1 - 5 of 5 results
filter_list Filters
computer Job seeker
Disable 1
person Position
thumb_up Fields of Interest
public Country
language Programming Language
1 - 5 of 5 results