Server Name (3D) Server Alias Active Since Deactived Since Weblink Server Type
Server 0 server0 2011-07-01 2018-11-08 Devel

Development server - no detailed description available

56.63929833279364 97.0 0_3D ZZZserver 00
Naive AlphaFoldDB 100 server100 2021-07-23 Naive AlphaFoldDB 100 Public

Abstract

The Naive AlphaFoldDB 100 method is a baseline that fetches models with 100% sequence identity to the target sequences from the AlphaFold Protein Structure Database at EMBL-EBI Alignents are retrieved with the FASTA REST API. Models corresponding to the top hits are cut and renumbered according to the target sequence. No remodeling is performed.

Tunyasuvunakool, K., Adler, J., Wu, Z. et al. Highly accurate protein structure prediction for the human proteome. Nature (2021). DOI: 10.1038/s41586-021-03828-1

Madeira F., Pearce M., Tivey A. R. N. et al. Search and sequence analysis tools services from EMBL-EBI in 2022. Nucleic Acids Research (2022) gkac240. DOI: 10.1093/nar/gkac240

84.145029772775 22.0 100_3D Naive AlphaFoldDB 100
PaFold server101 2021-08-27 PaFold Public

Abstract

Protein structure prediction plays an important role in drug discovery. In order to achieve robust performance, PaFold first obtains massive co-evolutional based information from raw sequence via huge protein sequence and template databases. Several layers of deep neural networks are then applied to predict the coarse-grained motifs and decoys. These, together with the previous template based information, can accurately guide the construction of 3D protein structure. The structure then undergoes several rounds of refinement based on energy minimization to achieve a more precise outcome.

73.76410091859363 3612.0 101_3D PaFold
Server 102 server102 2021-10-01 Devel

Development server - no detailed description available

55.55268319852018 62.0 102_3D ZZZserver 102
Server 103 server103 2021-10-15 Devel

Development server - no detailed description available

84.02710992358425 4509.0 103_3D ZZZserver 103
HeliXonAI server104 2021-10-27 HeliXonAI Public

Abstract

To uncover the mystery of the sequence to structure to function relationship is of great significance to the humankind for better understanding our lives. In order to achieve this dream, HeliXonAI, an integrated AI-enabled drug design platform, takes the giant leap to reach the state-of-the-art performance on protein structure prediction leveraging both informative sequence evolutionary features and modern geometric machine learning algorithms.

85.38478597484786 4578.0 104_3D HeliXonAI
PaFold_v2 server105 2021-11-25 2022-03-31 PaFold_v2 Public

Abstract

Following PaFold, PaFold_v2 further accelerates and improves the overall prediction performance by means of Transformer and self-attention mechanism. We also develop a novel selection algorithm based on diversity and distribution to achieve more robust intermediate data. In general, it can still give solid results even without template information and limited input data.

68.75498682634601 1190.0 105_3D PaFold_v2
RocketX server106 2021-11-30 2022-08-15 RocketX Public

Abstract

The successful application of deep learning has promoted a breakthrough progress in protein structure prediction. Generally, deep learning is independently used to predict the contact/distance between residues or to evaluate the accuracy of the model. RocketX integrates model evaluation into geometric constraint prediction and structural modeling to build a feedback mechanism to achieve closed-loop structural optimization. In RocketX, two different deep residual neural networks are designed to predict the inter-residue geometric constraints and evaluate the quality of the folded model, respectively. The predicted geometric constraints are used to guide the structural model folding. The model evaluation network is used to estimate the quality of the folded model, and the results are fed back to the geometric constraint prediction network to re-predict the geometric constraints and fold the new structural model. The final structural model is generated through three closed-loop iterative optimizations.

57.580369062231384 1917.0 106_3D RocketX
Server 107 server107 2022-01-27 Devel

Development server - no detailed description available

75.52637262269855 4832.0 107_3D ZZZserver 107
Server 108 server108 2022-01-27 Devel

Development server - no detailed description available

75.58692032471299 4833.0 108_3D ZZZserver 108
Server 109 server109 2022-01-27 Devel

Development server - no detailed description available

None None 109_3D ZZZserver 109
Server 110 server110 2022-03-10 2022-07-18 Devel

Development server - no detailed description available

86.46069367726645 1329.0 110_3D ZZZserver 110
OpenComplex server111 2022-03-10 OpenComplex Public

Abstract

OpenComplex is an open-source platform for developing protein and RNA complex models.

The code is available on GitHub.

85.25842622754696 960.0 111_3D OpenComplex
SADA server112 2022-03-10 2022-09-05 SADA Public

Abstract

The successful application of deep learning has promoted a breakthrough progress in protein structure prediction, such as AlphaFold2. However, the full-chain modelling appears to be lower on average accuracy than that for the constituent domains and requires higher demand on computing hardware, indicating the performance of full-chain modelling still needs to be improved. In SADA Server, we first used protein domain boundary prediction method DomBpred [1] to predict domain boundary of input sequence. Then, AlphaFold2 is used to predict the structure of each domain sequence. Finally, a protein domain assembly method [2] is used to assemble the predicted domain model to generate the full-length model.

83.6180413311178 4105.0 112_3D SADA
IntFOLD7 server113 2022-03-17 IntFOLD7 Public - 81.1558888029015 2045.0 113_3D IntFOLD7
Server 114 server114 2022-03-18 2024-04-23 Devel

Development server - no detailed description available

83.57152633968441 2724.0 114_3D ZZZserver 114
Server 115 server115 2022-03-18 2024-04-23 Devel

Development server - no detailed description available

83.03555458229272 2752.0 115_3D ZZZserver 115
Server 116 server116 2022-03-18 2024-04-23 Devel

Development server - no detailed description available

82.01481383498553 2668.0 116_3D ZZZserver 116
Server 117 server117 2022-03-18 2024-04-23 Devel

Development server - no detailed description available

81.45781746346019 2697.0 117_3D ZZZserver 117
Server 118 server118 2022-03-18 2024-04-23 Devel

Development server - no detailed description available

80.63600083071543 2671.0 118_3D ZZZserver 118
Server 119 server119 2022-03-18 2024-06-17 Devel

Development server - no detailed description available

85.67884401378468 3228.0 119_3D ZZZserver 119
Robetta server11 2012-03-16 Robetta Public

Abstract

The Robetta server (http://robetta.bakerlab.org) provides automated tools for protein structure prediction and analysis. For structure prediction, sequences submitted to the server are parsed into putative domains and structural models are generated using either comparative modeling or de novo structure prediction methods. If a confident match to a protein of known structure is found using BLAST, PSI-BLAST, FFAS03 or 3D-Jury, it is used as a template for comparative modeling. If no match is found, structure predictions are made using the de novo Rosetta fragment insertion method. Experimental nuclear magnetic resonance (NMR) constraints data can also be submitted with a query sequence for RosettaNMR de novo structure determination. Other current capabilities include the prediction of the effects of mutations on protein–protein interactions using computational interface alanine scanning. The Rosetta protein design and protein–protein docking methodologies will soon be available through the server as well.

  • Kim DE, Chivian D, Baker D. Protein structure prediction and analysis using the Robetta server. (2004) Nucleic Acids Res. 32(Web Server issue):W526-31. (DOI: 10.1093/nar/gkh468)
  • Raman S, Vernon R, et al. Structure prediction for CASP8 with all-atom refinement using Rosetta. (2009) Proteins 77 Suppl 9:89-99.i (DOI: 10.1002/prot.22540)
  • Song Y, DiMaio F, et al. High resolution comparative modeling with RosettaCM. (2013) Structure 21(10):1735-42. (DOI: 10.1016/j.str.2013.08.005)
  • Yang, J, Anishchenko I, et al. Improved Protein Structure Prediction Using Predicted Interresidue Orientations. (2020) Proceedings of the National Academy of Sciences of the United States of America 117 (3):1496–1503. (DOI: 10.1073/pnas.1914677117)
68.6499565974782 1717.0 11_3D Robetta
ZJUT-DeepAssembly server120 2022-03-24 2024-06-17 ZJUT-DeepAssembly Public

Abstract

DeepAssembly uses a multi-domain assembly approach to predict full-length protein structures. In DeepAssembly, we first constructed a deep learning model, AffineNet, which is specially used to predict the affine transformations of inter-domain residues. Then, an energy function called Atomic Coordinate Deviation potential was designed according to the predicted affine transformations. Finally, in domain assembly module, the energy function was optimized by population-based optimization method, and the single-domain structures was assembled, so as to obtain the full-length model.

84.50587763886759 4332.0 120_3D ZJUT-DeepAssembly
MultiDFold server121 2022-03-25 MultiDFold Public

Abstract

The successful application of deep learning has promoted a breakthrough progress in protein structure prediction, such as AlphaFold2, RoseTTAFold, trRosetta. The MultiDFold server is an attempt to fuse multiple information for structure prediction based on the multi-objective optimization method.

79.638942593389 4422.0 121_3D MultiDFold
MEGA-EvoGen server122 2022-03-25 2024-06-17 Public - 85.08044496664535 4085.0 122_3D MEGA-EvoGen
Server 123 server123 2022-03-25 2024-06-17 Devel

Development server - no detailed description available

85.3638298219105 4248.0 123_3D ZZZserver 123
Server 124 server124 2022-03-25 2024-06-17 Devel

Development server - no detailed description available

85.00014608725905 3842.0 124_3D ZZZserver 124
Server 125 server125 2022-03-25 2024-06-17 Devel

Development server - no detailed description available

85.85930821388516 3454.0 125_3D ZZZserver 125
Server 126 server126 2022-03-25 2024-06-17 Devel

Development server - no detailed description available

85.17993898233782 3756.0 126_3D ZZZserver 126
AIRFold server127 2022-03-25 AIRFold Public

Abstract

Advanced protein structure prediction models are sensitive to the co-evolution inputs. AirFold, an automated participating server, aims to improve efficiency and performance of protein structure prediction module by exploring better representation of sequence evolutionary features.

85.57717077122278 1431.0 127_3D AIRFold
Server 128 server128 2022-03-31 2024-07-19 Devel

Development server - no detailed description available

84.45670233206815 1724.0 128_3D ZZZserver 128
ManiFold server129 2022-04-07 2024-04-23 ManiFold Public - 84.68757534472641 2748.0 129_3D ManiFold
IntFOLD2-TS server12 2012-03-02 2017-12-05 IntFOLD2-TS Public

Abstract

Modelling the 3D structures of proteins can often be enhanced if more than one fold template is used during the modelling process. However, in many cases, this may also result in poorer model quality for a given target or alignment method. There is a need for modelling protocols that can both consistently and significantly improve 3D models and provide an indication of when models might not benefit from the use of multiple target-template alignments. Here, we investigate the use of both global and local model quality prediction scores produced by ModFOLDclust2, to improve the selection of target-template alignments for the construction of multiple-template models. Additionally, we evaluate clustering the resulting population of multi- and single-template models for the improvement of our IntFOLD-TS tertiary structure prediction method.

Buenavista, M. T., Roche, D. B. & McGuffin, L. J. (2012) Improvement of 3D protein models using multiple templates guided by single-template model quality assessment.

Bioinformatics, 28, 1851-1857.

http://dx.doi.org/10.1093/bioinformatics/bts292

63.99523550326388 1679.0 12_3D IntFOLD2-TS
PAthreader server130 2022-04-15 2024-06-17 PAthreader Public

Abstract

PAthreader is a high-precision remote template detection method by threading the PDB and AFDB libraries. AlphaFold2 is improved by PAthreader by providing better template alignment.

84.77238764863215 3771.0 130_3D PAthreader
PAthreader2 server131 2022-04-29 2024-06-17 PAthreader2 Public - 84.54825745059306 4013.0 131_3D PAthreader2
Server 132 server132 2022-07-02 Devel

Development server - no detailed description available

85.58010687168795 827.0 132_3D ZZZserver 132
Server 133 server133 2022-11-04 2023-06-23 Devel

Development server - no detailed description available

61.38684836855569 1209.0 133_3D ZZZserver 133
Server 134 server134 2024-03-06 2024-06-17 Devel

Development server - no detailed description available

85.67481778169933 2928.0 134_3D ZZZserver 134
Server 135 server135 2024-03-08 2024-06-17 Devel

Development server - no detailed description available

85.38197124082791 1972.0 135_3D ZZZserver 135
SAIS-Fold server136 2024-03-28 SAIS-Fold Public

Abstract

The SAIS-Fold server strives to seamlessly integrate a wide range of information sources for accurate structure prediction. It achieves this by synergistically combining an expertise-driven approach with the Protein Language Model (PLM) method.

85.71545720939905 1756.0 136_3D SAIS-Fold
ZJUT-DeepSHFold server137 2024-03-29 ZJUT-DeepSHFold Public

Abstract

DeepSHfold is a structure prediction method based on various MSA sampling. In particular, a search for structural homologous sequences based on protein language models is proposed. And for complexes, a pair-MSA strategy based on sequence structure homology scores was designed to enhance sampling.

87.35328162323215 3564.0 137_3D ZJUT-DeepSHFold
Server 138 server138 2024-04-09 Devel

Development server - no detailed description available

84.10152579857925 4574.0 138_3D ZZZserver 138
Server 139 server139 2024-10-18 Devel

Development server - no detailed description available

81.36699115452559 204.0 139_3D ZZZserver 139
M4T server13 2012-03-02 2017-08-18 M4T Public

Abstract

Improvements in comparative protein structure modeling for the remote target-template sequence similarity cases are possible through the optimal combination of multiple template structures and by improving the quality of target-template alignment. Recently developed MMM and M4T methods were designed to address these problems. Here we describe new developments in both the alignment generation and the template selection parts of the modeling algorithms. We set up a new scoring function in MMM to deliver more accurate target-template alignments. This was achieved by developing and incorporating into the composite scoring function a novel statistical pairwise potential that combines local and non-local terms. The non-local term of the statistical potential utilizes a shuffled reference state definition that helped to eliminate most of the false positive signal from the background distribution of pairwise contacts. The accuracy of the scoring function was further increased by using BLOSUM mutation table scores.

Rykunov D, Steinberger E, Madrid-Aliste CJ, Fiser A Improved scoring function for comparative modeling using the M4T method.

J Struct Funct Genomics (2009) 10(1) : 95-9.

http://dx.doi.org/10.1007/s10969-008-9044-9

68.53486413105777 747.0 13_3D M4T
Server 140 server140 2024-11-17 Devel

Development server - no detailed description available

None None 140_3D ZZZserver 140
Server 141 server141 2024-11-17 Devel

Development server - no detailed description available

None None 141_3D ZZZserver 141
Server 14 server14 2012-11-28 2013-02-03 Devel

Development server - no detailed description available

None None 14_3D ZZZserver 14
Server 16 server16 2012-07-16 2013-06-12 Devel

Development server - no detailed description available

None None 16_3D ZZZserver 16
Phyre2 server17 2013-03-22 Phyre2 Public

Abstract

Determining the structure and function of a novel protein is a cornerstone of many aspects of modern biology. Over the past decades, a number of computational tools for structure prediction have been developed. It is critical that the biological community is aware of such tools and is able to interpret their results in an informed way. This protocol provides a guide to interpreting the output of structure prediction servers in general and one such tool in particular, the protein homology/analogy recognition engine (Phyre). New profile-profile matching algorithms have improved structure prediction considerably in recent years. Although the performance of Phyre is typical of many structure prediction systems using such algorithms, all these systems can reliably detect up to twice as many remote homologies as standard sequence-profile searching. Phyre is widely used by the biological community, with >150 submissions per day, and provides a simple interface to results. Phyre takes 30 min to predict the structure of a 250-residue protein.

Kelley LA, Sternberg MJ. Protein structure prediction on the Web: a case study using the Phyre server.

Nat Protoc. 2009;4(3):363-71

http://dx.doi.org/10.1038/nprot.2009.2

52.7019595362079 91.0 17_3D Phyre2
Server 18 server18 2013-04-12 2013-10-03 Devel

Development server - no detailed description available

None None 18_3D ZZZserver 18
RoseTTAFold server19 2013-06-13 RoseTTAFold Public

Abstract

DeepMind presented remarkably accurate protein structure predictions at the CASP14 conference. We explored network architectures incorporating related ideas and obtained the best performance with a three-track attention-based network in which information at the 1D sequence level, the 2D distance map level, and the 3D coordinate level is successively transformed and integrated. The 3-track network produces high accuracy structure predictions, enables rapid solution of challenging X-ray crystallography and cryo-EM structure modeling problems, and provides insights into the functions of proteins of currently unknown structure.

70.97752482901909 1219.0 19_3D RoseTTAFold
SWISS-MODEL server20 2013-07-05 SWISS-MODEL Public

Abstract

Protein structure homology modelling has become a routine technique to generate 3D models for proteins when experimental structures are not available. Fully automated servers such as SWISS-MODEL with user-friendly web interfaces generate reliable models without the need for complex software packages or downloading large databases. Here, we describe the latest version of the SWISS-MODEL expert system for protein structure modelling. The SWISS-MODEL template library provides annotation of quaternary structure and essential ligands and co-factors to allow for building of complete structural models, including their oligomeric structure. The improved SWISS-MODEL pipeline makes extensive use of model quality estimation for selection of the most suitable templates and provides estimates of the expected accuracy of the resulting models. The accuracy of the models generated by SWISS-MODEL is continuously evaluated by the CAMEO system. The new web site allows users to interactively search for templates, cluster them by sequence similarity, structurally compare alternative templates and select the ones to be used for model building. In cases where multiple alternative template structures are available for a protein of interest, a user-guided template selection step allows building models in different functional states. SWISS-MODEL is available at http://swissmodel.expasy.org/.

Biasini, M. et.al. Nucleic Acids Research; (1 July 2014) 42 (W1): W252-W258

64.38322274825975 33.0 20_3D SWISS-MODEL
Server 21 server21 2013-09-06 2013-09-08 Devel

Development server - no detailed description available

None None 21_3D ZZZserver 21
RaptorX server22 2013-09-06 RaptorX Public

Abstract

A key challenge of modern biology is to uncover the functional role of the protein entities that compose cellular proteomes. To this end, the availability of reliable three-dimensional atomic models of proteins is often crucial. This protocol presents a community-wide web-based method using RaptorX (http://raptorx.uchicago.edu/) for protein secondary structure prediction, template-based tertiary structure modeling, alignment quality assessment and sophisticated probabilistic alignment sampling. RaptorX distinguishes itself from other servers by the quality of the alignment between a target sequence and one or multiple distantly related template proteins (especially those with sparse sequence profiles) and by a novel nonlinear scoring function and a probabilistic-consistency algorithm. Consequently, RaptorX delivers high-quality structural models for many targets with only remote templates. At present, it takes RaptorX ∼35 min to finish processing a sequence of 200 amino acids.

Källberg M, Wang H, Wang S, Peng J, Wang Z, Lu H, Xu J. Template-based protein structure modeling using the RaptorX web server.

Nature Protocols 7, 1511–1522, 2012.

http://dx.doi.org/10.1038/nprot.2012.085

66.08485556570682 757.0 22_3D RaptorX
Server 23 server23 2013-09-24 2014-03-12 Devel

Development server - no detailed description available

47.03160062458616 589.0 23_3D ZZZserver 23
Server 24 server24 2013-09-24 2014-03-12 Devel

Development server - no detailed description available

44.51219048646708 490.0 24_3D ZZZserver 24
Server 25 server25 2013-09-24 2014-03-02 Devel

Development server - no detailed description available

56.49946289678366 1161.0 25_3D ZZZserver 25
Server 26 server26 2013-09-24 2014-03-02 Devel

Development server - no detailed description available

57.77398540417929 1080.0 26_3D ZZZserver 26
Princeton_TEMPLATE server27 2013-09-23 2019-10-18 Princeton_TEMPLATE Public

Abstract

The Princeton_TEMPLATE (ProTEin geoMetry Prediction using simuLAtions and supporT vEctor machines) webserver is an automated template-assisted structure prediction method that produces 5 model predictions for targets with sufficient homology to a template. First, the method does single or multiple domain alignments to template structures contained in our newly constructed template library. Next, sequence alignments are generated using the SPARKS-X Fold Recognition Software developed by the Yaoqi Zhou Lab. Next, the method generates many local minima based on the constraints generated using torsion-angle dynamics in Cyana. Each of these local minima are next relaxed using Rosetta Fast Relax with constraints on the coordinates to remain near the start in order to repack the side-chains and to make movements that will enhance the number of hyrogen bonds. This ensemble of structures is refined using components of the Princeton_TIGRESS refinement protocol. Namely, the structures are passed through a support vector machines based function evaluation that is capable of identifying models that are improved relative to the naive lowest-energy model. The model selected by the SVM is then refined via all atom molecular dynamics simulatons in CHARMM using the FACTS implicit solvent model. The final prediction and refined structure is sent to the user. The methodology has been benchmarked on all CASP10 targets.

Khoury, G. A. et.al. Proteins: Structure, Function, and Bioinformatics 2014, 82 (5), 794-814.

57.37828218265193 290.0 27_3D Princeton_TEMPLATE
Server 28 server28 2013-10-02 2013-10-11 Devel

Development server - no detailed description available

None None 28_3D ZZZserver 28
Server 29 server29 2013-10-02 2013-10-11 Devel

Development server - no detailed description available

None None 29_3D ZZZserver 29
Server 2 server2 2011-07-01 2013-07-02 Devel

Development server - no detailed description available

None None 2_3D ZZZserver 02
SPARKS-X server30 2013-10-24 SPARKS-X Public

Abstract

In recent years, development of a single-method fold-recognition server lags behind consensus and multiple template techniques. However, a good consensus prediction relies on the accuracy of individual methods. This article reports our efforts to further improve a single-method fold recognition technique called SPARKS by changing the alignment scoring function and incorporating the SPINE-X techniques that make improved prediction of secondary structure, backbone torsion angle and solvent accessible surface area.

Yang Y, Faraggi E, Zhao H, Zhou Y. Improving protein fold recognition and template-based modeling by employing probabilistic-based matching between predicted one-dimensional structural properties of query and corresponding native properties of templates.Bioinformatics.

2011 Aug 1;27(15):2076-82.

http://dx.doi.org/10.1093/bioinformatics/btr350

59.28810607378706 319.0 30_3D SPARKS-X
NaiveBlits server31 2013-12-20 2013-12-20 Public

Abstract

The NaiveBlits method servers as baseline by relying on the first hit found by HHblits as template and predicting the protein structure by calling MODELLER.

54.47554566076892 140.0 31_3D NaiveBlits
RBO Aleph server32 2014-01-07 2017-08-14 RBO Aleph Public

Abstract

RBO Aleph is a novel protein structure prediction web server for template-based modeling, protein contact prediction and ab initio structure prediction. The server has a strong emphasis on modeling difficult protein targets for which templates cannot be detected. RBO Aleph's unique features are (i) the use of combined evolutionary and physicochemical information to perform residue–residue contact prediction and (ii) leveraging this contact information effectively in conformational space search. RBO Aleph emerged as one of the leading approaches to ab initio protein structure prediction and contact prediction during the most recent Critical Assessment of Protein Structure Prediction experiment (CASP11, 2014). In addition to RBO Aleph's main focus on ab initio modeling, the server also provides state-of-the-art template-based modeling services. Based on template availability, RBO Aleph switches automatically between template-based modeling and ab initio prediction based on the target protein sequence, facilitating use especially for non-expert users. The RBO Aleph web server offers a range of tools for visualization and data analysis, such as the visualization of predicted models, predicted contacts and the estimated prediction error along the model's backbone. The server is accessible at http://compbio.robotics.tu-berlin.de/rbo_aleph/.

Mabrouk, M., Putz, I., Werner, T., Schneider, M., Neeb, M., Bartels, P. and Brock, O., 2015. RBO Aleph: leveraging novel information sources for protein structure prediction. Nucleic acids research, 43(W1), pp.W343-W348.

dx.doi.org/10.1093/nar/gkv357

60.15063366076969 1284.0 32_3D RBO Aleph
IntFOLD3-TS server33 2014-03-06 2023-12-14 IntFOLD3-TS Public

Abstract

Modelling the 3D structures of proteins can often be enhanced if more than one fold template is used during the modelling process. However, in many cases, this may also result in poorer model quality for a given target or alignment method. There is a need for modelling protocols that can both consistently and significantly improve 3D models and provide an indication of when models might not benefit from the use of multiple target-template alignments. Here, we investigate the use of both global and local model quality prediction scores produced by ModFOLDclust3, to improve the selection of target-template alignments for the construction of multiple-template models. Additionally, we evaluate clustering the resulting population of multi- and single-template models for the improvement of our IntFOLD-TS tertiary structure prediction method.

McGuffin, L.J., Atkins, J., Salehe, B.R., Shuid, A.N. & Roche, D.B. (2015) IntFOLD: an integrated server for modelling protein structures and functions from amino acid sequences. Nucleic Acids Research, 43, W169-73.

64.28501280116731 2115.0 33_3D IntFOLD3-TS
Server 34 server34 2014-03-06 2014-03-08 Devel

Development server - no detailed description available

None None 34_3D ZZZserver 34
Server 35 server35 2014-03-06 2014-03-08 Devel

Development server - no detailed description available

None None 35_3D ZZZserver 35
NaiveBLAST server36 2012-01-06 NaiveBLAST Public

Abstract

The NaiveBlast method servers as baseline by relying on the first hit found by BLAST as template and predicting the protein structure by calling MODELLER.

56.56122375337957 102.0 36_3D NaiveBLAST
Server 37 server37 2014-03-05 2014-03-13 Devel

Development server - no detailed description available

None None 37_3D ZZZserver 37
Server 38 server38 2014-04-10 2014-04-11 Devel

Development server - no detailed description available

None None 38_3D ZZZserver 38
Server 39 server39 2014-04-10 2014-04-11 Devel

Development server - no detailed description available

None None 39_3D ZZZserver 39
Server 40 server40 2014-04-10 2014-04-11 Devel

Development server - no detailed description available

None None 40_3D ZZZserver 40
Server 41 server41 2014-04-10 2014-04-11 Devel

Development server - no detailed description available

None None 41_3D ZZZserver 41
Server 42 server42 2014-04-16 2016-03-24 Devel

Development server - no detailed description available

62.844128930438906 2254.0 42_3D ZZZserver 42
Server 43 server43 2014-07-01 2015-01-27 Devel

Development server - no detailed description available

59.73826558073739 415.0 43_3D ZZZserver 43
Server 44 server44 2014-06-19 2015-05-14 Devel

Development server - no detailed description available

60.69658702070063 1346.0 44_3D ZZZserver 44
Server 45 server45 2014-07-04 2020-08-24 Devel

Development server - no detailed description available

65.94995814607229 1185.0 45_3D ZZZserver 45
Server 46 server46 2014-09-24 2017-03-14 Devel

Development server - no detailed description available

58.972407330473 274.0 46_3D ZZZserver 46
Server 47 server47 2014-10-24 2015-12-18 Devel

Development server - no detailed description available

57.454842620529234 51.0 47_3D ZZZserver 47
Server 48 server48 2014-02-12 2017-11-30 Devel

Development server - no detailed description available

59.838523960616016 32.0 48_3D ZZZserver 48
Server 49 server49 2016-11-18 Devel

Development server - no detailed description available

62.96905602189761 58.0 49_3D ZZZserver 49
HHpredB server4 2011-07-01 2019-08-02 HHpredB Public

Abstract

Automated protein structure prediction is becoming a mainstream tool for biological research. This has been fueled by steady improvements of publicly available automated servers over the last decade, in particular their ability to build good homology models for an increasing number of targets by reliably detecting and aligning more and more remotely homologous templates. Here, we describe the three fully automated versions of the HHpred server that participated in the community-wide blind protein structure prediction competition CASP8. What makes HHpred unique is the combination of usability, short response times (typically under 15 min) and a model accuracy that is competitive with those of the best servers in CASP8.

Hildebrand A., Remmert M., Biegert A., and Söding J. Fast and accurate automatic structure prediction with HHpred.

Proteins. 77 Suppl 9:128-132 (2009).

dx.doi.org/10.1002/prot.22499

60.12724563689078 382.0 4_3D HHpredB
Server 50 server50 2015-06-12 Devel

Development server - no detailed description available

64.41673158444074 2886.0 50_3D ZZZserver 50
Server 51 server51 2015-12-04 2016-07-04 Devel

Development server - no detailed description available

61.20074182172364 139.0 51_3D ZZZserver 51
Server 52 server52 2015-12-11 2016-03-10 Devel

Development server - no detailed description available

64.48519987054169 30.0 52_3D ZZZserver 52
Server 53 server53 2016-01-21 2016-04-13 Devel

Development server - no detailed description available

60.41403512159983 2790.0 53_3D ZZZserver 53
Server 54 server54 2016-02-26 2023-05-23 Devel

Development server - no detailed description available

63.08782721888612 30.0 54_3D ZZZserver 54
Server 55 server55 2016-04-07 2023-05-23 Devel

Development server - no detailed description available

65.72995505301147 42.0 55_3D ZZZserver 55
Server 56 server56 2016-04-16 2017-06-30 Devel

Development server - no detailed description available

65.84651650257514 1761.0 56_3D ZZZserver 56
Server 57 server57 2016-04-22 2017-06-30 Devel

Development server - no detailed description available

64.70009995977473 1773.0 57_3D ZZZserver 57
IntFOLD4-TS server58 2016-04-29 2023-12-14 IntFOLD4-TS Public

Abstract

For our automated predictions we developed the IntFOLD4-TS protocol, which integrates the ModFOLD6_rank method for scoring the multiple-template models that were generated using a number of alternative sequence-structure alignments. Overall, our selection of top models and Accuracy Self Estimate (ASE) scores using ModFOLD6_rank was an improvement on our previous approaches. Our IntFOLD4-TS method was developed with the aim of identifying, and then attempting to fix, the local errors in an initial pool of single template models via iterative multi-template modeling. The method attempts to exploit our previous CASP successes in accurately predicting local errors in our models by taking the global and local per-residue errors into consideration during the multiple template selection stage.The pipeline can be broken down into two major stages: (1) single template modeling with ASE scoring and (2) QA guided multiple template modeling with ASE scoring.

McGuffin, L.J., Shuid, A.M., Kempster, R., Maghrabi, A.H.A., Nealon J.O., Salehe, B.R., Atkins, J.D. & Roche, D.B. (2017) Accurate Template Based Modelling in CASP12 using the IntFOLD4-TS, ModFOLD6 and ReFOLD methods. Proteins: Structure, Function, and Bioinformatics, 86 Suppl 1, 335-344. McGuffin, L.J., Atkins, J., Salehe, B.R., Shuid, A.N. & Roche, D.B. (2015) IntFOLD: an integrated server for modelling protein structures and functions from amino acid sequences. Nucleic Acids Research, 43, W169-73.

66.04786115340963 2740.0 58_3D IntFOLD4-TS
Server 59 server59 2012-03-02 2017-08-18 Devel

Development server - no detailed description available

63.522968082055456 1203.0 59_3D ZZZserver 59
IntFOLD-TS server5 2011-12-01 2015-07-16 IntFOLD-TS Public

Abstract

The IntFOLD-TS method was developed according to the guiding principle that the model quality assessment (QA) would be the most critical stage for our template-based modeling pipeline. Thus, the IntFOLD-TS method firstly generates numerous alternate models, using in-house versions of several different sequence-structure alignment methods, which are then ranked in terms of global quality using our top performing QA method-ModFOLDclust2. In addition to the predicted global quality scores, the predictions of local errors are also provided in the resulting coordinate files, using scores that represent the predicted deviation of each residue in the model from the equivalent residue in the native structure. The IntFOLD-TS method was found to generate high quality 3D models for many of the CASP9 targets, whilst also providing highly accurate predictions of their per-residue errors. This important information may help to make the 3D models that are produced by the IntFOLD-TS method more useful for guiding future experimental work

Roche, D. B., Buenavista, M. T., Tetchner, S. J. & McGuffin, L. J.

(2011) The IntFOLD server: an integrated web resource for protein fold recognition, 3D model quality assessment, intrinsic disorder prediction, domain prediction and ligand binding site prediction. Nucleic Acids Res., 39, W171-6.

http://www.ncbi.nlm.nih.gov/pubmed/21459847

61.29348834543835 1743.0 5_3D IntFOLD-TS
Server 60 server60 2016-09-06 Devel

Development server - no detailed description available

50.57450257275137 789.0 60_3D ZZZserver 60
PRIMO server61 2016-09-26 PRIMO Public

Abstract

The development of automated servers to predict the three-dimensional structure of proteins has seen much progress over the years. These servers make calculations simpler, but largely exclude users from the process. In this study, we present the PRotein Interactive MOdeling (PRIMO) pipeline for homology modeling of protein monomers. The pipeline eases the multi-step modeling process, and reduces the workload required by the user, while still allowing engagement from the user during every step. Default parameters are given for each step, which can either be modified or supplemented with additional external input. PRIMO has been designed for users of varying levels of experience with homology modeling. The pipeline incorporates a user-friendly interface that makes it easy to alter parameters used during modeling. During each stage of the modeling process, the site provides suggestions for novice users to improve the quality of their models. PRIMO provides functionality that allows users to also model ligands and ions in complex with their protein targets. Herein, we assess the accuracy of the fully automated capabilities of the server, including a comparative analysis of the available alignment programs, as well as of the refinement levels used during modeling. The tests presented here demonstrate the reliability of the PRIMO server when producing a large number of protein models. While PRIMO does focus on user involvement in the homology modeling process, the results indicate that in the presence of suitable templates, good quality models can be produced even without user intervention. This gives an idea of the base level accuracy of PRIMO, which users can improve upon by adjusting parameters in their modeling runs. The accuracy of PRIMO’s automated scripts is being continuously evaluated by the CAMEO (Continuous Automated Model EvaluatiOn) project.

Hatherley R, Brown DK, Glenister M, Tastan Bishop Ö (2016) PRIMO: An Interactive Homology Modeling Pipeline. PLOS ONE 11(11): e0166698.

https://doi.org/10.1371/journal.pone.0166698

57.13137374680096 89.0 61_3D PRIMO
PRIMO_BST_3D server62 2016-10-16 PRIMO_BST_3D Public - 55.26334400167857 90.0 62_3D PRIMO_BST_3D
PRIMO_HHS_3D server63 2016-10-16 PRIMO_HHS_3D Public - 54.81293976048101 97.0 63_3D PRIMO_HHS_3D
PRIMO_HHS_CL server64 2016-10-16 PRIMO_HHS_CL Public - 54.912185952475156 90.0 64_3D PRIMO_HHS_CL
PRIMO_BST_CL server65 2016-10-16 PRIMO_BST_CL Public - 57.120324842193796 86.0 65_3D PRIMO_BST_CL
Server 66 server66 2017-02-06 2018-10-01 Devel

Development server - no detailed description available

22.747500091791153 4601.0 66_3D ZZZserver 66
Server 67 server67 2017-05-02 2022-09-06 Devel

Development server - no detailed description available

61.40288552445061 1061.0 67_3D ZZZserver 67
SWISS-MODEL Beta server68 2017-05-10 2017-11-16 SWISS-MODEL Beta Public - 61.34405929009764 41.0 68_3D SWISS-MODEL Beta
Server 69 server69 2017-08-14 2022-09-12 Devel

Development server - no detailed description available

58.206684603714024 694.0 69_3D ZZZserver 69
Server 6 server6 2011-12-10 Devel

Development server - no detailed description available

53.45226352662217 591.0 6_3D ZZZserver 06
M4T-SMOTIF-TF server70 2017-08-18 2021-08-05 M4T-SMOTIF-TF Public - 63.96192896507752 873.0 70_3D M4T-SMOTIF-TF
Server 71 server71 2017-10-06 2020-10-26 Devel

Development server - no detailed description available

39.0346750645519 3007.0 71_3D ZZZserver 71
Server 72 server72 2017-10-26 2020-10-26 Devel

Development server - no detailed description available

51.54575922299479 1946.0 72_3D ZZZserver 72
Server 73 server73 2017-12-09 2020-03-23 Devel

Development server - no detailed description available

48.52390794575899 2374.0 73_3D ZZZserver 73
Server 74 server74 2018-03-14 2020-03-23 Devel

Development server - no detailed description available

None None 74_3D ZZZserver 74
IntFOLD5-TS server75 2018-03-21 IntFOLD5-TS Public - 66.83114747104267 2198.0 75_3D IntFOLD5-TS
Server 76 server76 2018-05-22 2018-07-03 Devel

Development server - no detailed description available

62.25234601551142 8.0 76_3D ZZZserver 76
Server 77 server77 2018-10-12 2024-08-12 Devel

Development server - no detailed description available

54.44697697731016 567.0 77_3D ZZZserver 77
Server 78 server78 2018-11-08 2024-08-12 Devel

Development server - no detailed description available

56.85487904385298 197.0 78_3D ZZZserver 78
Server 79 server79 2018-12-08 2022-02-21 Devel

Development server - no detailed description available

45.72434781230882 1044.0 79_3D ZZZserver 79
Server 7 server7 2011-12-10 Devel

Development server - no detailed description available

52.316138479510485 754.0 7_3D ZZZserver 07
Server 80 server80 2019-05-23 2022-02-17 Devel

Development server - no detailed description available

63.515566557885684 410.0 80_3D ZZZserver 80
Server 81 server81 2019-05-23 2022-02-17 Devel

Development server - no detailed description available

59.309304480190896 106.0 81_3D ZZZserver 81
Server 82 server82 2019-06-01 Devel

Development server - no detailed description available

69.00686647225204 19.0 82_3D ZZZserver 82
Server 83 server83 2019-08-23 2020-12-18 Devel

Development server - no detailed description available

61.52068755390915 2047.0 83_3D ZZZserver 83
Server 84 server84 2019-12-06 2020-12-18 Devel

Development server - no detailed description available

69.82649179411105 1201.0 84_3D ZZZserver 84
Server 85 server85 2019-12-06 2020-12-18 Devel

Development server - no detailed description available

69.25880212096725 2591.0 85_3D ZZZserver 85
Server 86 server86 2019-12-06 2020-12-18 Devel

Development server - no detailed description available

68.27859888984779 3306.0 86_3D ZZZserver 86
Server 87 server87 2019-12-16 2020-12-18 Devel

Development server - no detailed description available

70.15829256709 2653.0 87_3D ZZZserver 87
Server 88 server88 2019-12-16 2020-12-18 Devel

Development server - no detailed description available

68.70760284463302 3507.0 88_3D ZZZserver 88
TFold server89 2020-01-10 2020-12-18 tFold Public

Abstract

The tFold server integrates three innovative techniques for high-accuracy protein structure prediction. We adopt the “multi-source fusion” strategy to fully exploit co-evolution patterns embedded in multiple groups of MSA data. An ultra-deep criss-cross attention residual network is developed to accurately predict both inter-residue distance and orientation relationships. We further develop the “template-based free modeling - TBFM” framework to combine both TBM-based tertiary structure information and FM-based distance and orientation predictions to generate high-quality structure predictions.

Han, Y., Zhuang, Q., Sun, B. et al. Crystal structure of steroid reductase SRD5A reveals conserved steroid reduction mechanism. Nat Commun 12, 449 (2021). DOI: 10.1038/s41467-020-20675-2.

70.08415085757339 2880.0 89_3D tFold
Server 8 server8 2011-12-10 2017-06-01 Devel

Development server - no detailed description available

55.736519902974614 1957.0 8_3D ZZZserver 08
IntFOLD6-TS server90 2020-02-20 IntFOLD6-TS Public - 67.21130421537735 1831.0 90_3D IntFOLD6-TS
Server 91 server91 2020-08-18 2022-07-15 Devel

Development server - no detailed description available

66.08631086267164 666.0 91_3D ZZZserver 91
Server 92 server92 2020-10-23 2020-12-31 Devel

Development server - no detailed description available

None None 92_3D ZZZserver 92
Server 93 server93 2020-10-23 2022-08-08 Devel

Development server - no detailed description available

None None 93_3D ZZZserver 93
Server 94 server94 2020-11-27 2022-09-05 Devel

Development server - no detailed description available

63.807651800641295 2155.0 94_3D ZZZserver 94
Server 95 server95 2020-12-02 2024-04-23 Devel

Development server - no detailed description available

57.821119267766065 3489.0 95_3D ZZZserver 95
PureAF2_orig server96 2021-07-23 2022-12-20 Public - 85.9411205518447 2096.0 96_3D pureAF2_orig
PureAF2_notemp server97 2021-07-23 2022-12-20 Public - 85.11075270283331 2427.0 97_3D pureAF2_notemp
ZlxFold server98 2021-07-23 2022-12-20 Public - 83.64024620237608 3471.0 98_3D ZlxFold
BestSingleStructuralTemplate server999 2020-02-07 BestSingleStructuralTemplate Public

Abstract

The BestSingleStructuralTemplate method serves as "post-diction" baseline, representing an upper limit for single template models. The best templates are discovered by structural superposition of the target reference structures with all PDB structures using TM‐align. The top 20 of the obtained structural alignments serve as input for the subsequent template‐based modeling. Modeling is performed with SWISS‐MODEL's modeling engine ProMod3. Termini beyond the region covered by the template structure are modeled by a low‐complexity Monte Carlo sampling approach. The final models are ranked by lDDT, and the top scoring model is selected for that particular target.

Haas, J, Gumienny, R, Barbato, A, et al. Introducing “best single template” models as reference baseline for the Continuous Automated Model Evaluation (CAMEO). Proteins. 2019; 87: 1378–1387.

https://doi.org/10.1002/prot.25815

71.16715276488833 282.0 999_3D BestSingleStructuralTemplate
Naive AlphaFoldDB 90 server99 2021-07-23 Naive AlphaFoldDB 90 Public

Abstract

The Naive AlphaFoldDB 90 method is a baseline that fetches models with at least 90% sequence identity to the target sequences from the AlphaFold Protein Structure Database at EMBL-EBI. Alignents are retrieved with the FASTA REST API. Models corresponding to the top hits are downloaded and minimal modelling required to map the AlphaFold model to the target sequence is performed with ProMod3 using its default modelling pipeline.

Tunyasuvunakool, K., Adler, J., Wu, Z. et al. Highly accurate protein structure prediction for the human proteome. Nature (2021). DOI: 10.1038/s41586-021-03828-1

Studer, G., Tauriello, G., Bienert S. et al. ProMod3—A versatile homology modelling toolbox. PLOS Computational Biology (2021) 17(1): e1008667. DOI: 10.1371/journal.pcbi.1008667

Madeira F., Pearce M., Tivey A. R. N. et al. Search and sequence analysis tools services from EMBL-EBI in 2022. Nucleic Acids Research (2022) gkac240. DOI: 10.1093/nar/gkac240

83.17602421084696 20.0 99_3D Naive AlphaFoldDB 90
Server 9 server9 2012-01-13 2015-01-12 Devel

Development server - no detailed description available

59.6175534696201 151.0 9_3D ZZZserver 09
Server Name (QE) Server Alias Active Since Deactived Since Weblink Predictor Type Server Type
Verify3d smoothed server0 2014-02-07 2019-06-22 Public - 0 0_QE Verify3d smoothed
Server 10 server10 2014-05-16 2018-04-24 Devel

Development server - no detailed description available

0 10_QE ZZZserver 10
Server 11 server11 2014-05-23 2018-04-24 Devel

Development server - no detailed description available

0 11_QE ZZZserver 11
Server 12 server12 2014-10-16 2016-08-31 Devel

Development server - no detailed description available

0 12_QE ZZZserver 12
Server 13 server13 2014-12-04 2015-06-11 Devel

Development server - no detailed description available

0 13_QE ZZZserver 13
Server 14 server14 2014-12-18 2015-06-11 Devel

Development server - no detailed description available

0 14_QE ZZZserver 14
VoroMQA_sw5 server15 2014-12-18 VoroMQA_sw5 Public

Abstract

VoroMQA_sw5 server uses the first version of VoroMQA ("Voronoi diagram­-based Model Quality Assessment"), a new method for the estimation of protein structure quality. It combines the idea of statistical potentials with the advanced use of the Voronoi tessellation of atomic balls. The new method uses contact areas instead of distances for describing and seamlessly integrating both explicit interactions between protein atoms and implicit interactions of protein atoms with solvent. The method produces scores at atomic, residue and global levels. The VoroMQA version used by the VoroMQA_sw5 server is generally identical to the version that participated in CASP11 with one important modification: local residue scores are smoothed along the sequence using a triangular window of 5 residues on each side of a central residue position.

Kliment Olechnovič and Česlovas Venclovas. VoroMQA: Assessment of protein structure quality using interatomic contact areas. Proteins 2017; 85:1131–1145. DOI: 10.1002/prot.25278.

0 15_QE VoroMQA_sw5
EQuant 2 server16 2015-06-12 2020-05-19 eQuant 2 Public - 0 16_QE eQuant 2
VoroMQA_v2 server17 2015-07-23 VoroMQA_v2 Public

Abstract

VoroMQA_v2 server uses the second version of VoroMQA ("Voronoi diagram­-based Model Quality Assessment"), a new method for the estimation of protein structure quality. It combines the idea of statistical potentials with the advanced use of the Voronoi tessellation of atomic balls. The new method uses contact areas instead of distances for describing and seamlessly integrating both explicit interactions between protein atoms and implicit interactions of protein atoms with solvent. In addition, the second version of VoroMQA utilizes the Voronoi tessellation of balls to describe the orientation of contacts. The method produces scores at atomic, residue and global levels. The web server is available at bioinformatics.ibt.lt/wtsam/voromqa. The VoroMQA version used by the VoroMQA_v2 server is generally identical to the version that participated in CASP12.

0 17_QE VoroMQA_v2
ModFOLD6 server18 2016-02-02 2018-02-23 ModFOLD6 Public - 0 18_QE ModFOLD6
QMEANDisCo 2 server19 2016-02-02 2019-05-24 QMEANDisCo 2 Public - 0 19_QE QMEANDisCo 2
Dfire v1.1 server1 2014-02-07 2019-06-22 Dfire v1.1 Public

Abstract

Proteins fold into unique three-dimensional structures by specific, orientation-dependent interactions between amino acid residues. Here, we extract orientation-dependent interactions from protein structures by treating each polar atom as a dipole with a direction. The resulting statistical energy function successfully refolds 13 out of 16 fully unfolded secondary-structure terminal regions of 10–23 amino acid residues in 15 small proteins. Dissecting the orientation-dependent energy function reveals that the orientation preference between hydrogen-bonded atoms is not enough to account for the structural specificity of proteins. The result has significant implications on the theoretical and experimental searches for specific interactions involved in protein folding and molecular recognition between proteins and other biologically active molecules.

Yang Y., Zhou Y.. Specific interactions for ab initio folding of protein terminal regions with secondary structures.

Proteins. 2008 Aug;72(2):793-803.

dx.doi.org/10.1002/prot.21968

0 1_QE Dfire v1.1
QMEAN 3 server20 2017-08-24 QMEAN 3 Public

Abstract

Motivation: Quality assessment of protein structures is an important part of experimental structure validation and plays a crucial role in protein structure prediction, where the predicted models may contain substantial errors. Most current scoring functions are primarily designed to rank alternative models of the same sequence supporting model selection, whereas the prediction of the absolute quality of an individual protein model has received little attention in the field. However, reliable absolute quality estimates are crucial to assess the suitability of a model for specific biomedical applications.

Results: In this work, we present a new absolute measure for the quality of protein models, which provides an estimate of the ‘degree of nativeness’ of the structural features observed in a model and describes the likelihood that a given model is of comparable quality to experimental structures. Model quality estimates based on the QMEAN scoring function were normalized with respect to the number of interactions. The resulting scoring function is independent of the size of the protein and may therefore be used to assess both monomers and entire oligomeric assemblies. Model quality scores for individual models are then expressed as ‘Z-scores’ in comparison to scores obtained for high-resolution crystal structures. We demonstrate the ability of the newly introduced QMEAN Z-score to detect experimentally solved protein structures containing significant errors, as well as to evaluate theoretical protein models.

In a comprehensive QMEAN Z-score analysis of all experimental structures in the PDB, membrane proteins accumulate on one side of the score spectrum and thermostable proteins on the other. Proteins from the thermophilic organism Thermatoga maritima received significantly higher QMEAN Z-scores in a pairwise comparison with their homologous mesophilic counterparts, underlining the significance of the QMEAN Z-score as an estimate of protein stability.

Benkert, P., Biasini, M., Schwede, T. Toward the estimation of the absolute quality of individual protein structure models. Bioinformatics 27, 343-350 (2011).

10.1093/bioinformatics/btq662

0 20_QE QMEAN 3
ModFOLD6 server21 2016-04-22 2023-12-14 ModFOLD6 Public - 0 21_QE ModFOLD6
Server 22 server22 2016-08-05 Devel

Development server - no detailed description available

0 22_QE ZZZserver 22
Baseline Potential server23 2016-10-24 Public

Abstract

The “BaselinePotential” server implements a classical distance based statistical potential as described by Sippl and coworkers. Statistics have been extracted for pairwise distances between all chemically distinguishable heavy atoms in the 20 naturally occurring amino acids. Histograms have been built with a bin size of 0.5 Å and maximal distance of 10 Å, neglecting all interactions from residues being closer than 4 in sequence. The underlying data is composed of a non-redundant set of experimentally determined protein structures (2995 culled chains from the PISCES webserver with max pairwise sequence identity of 20% and X-Ray resolution better than 1.6 Å). The resulting potential functions are applied on all pairwise interactions and per residue scores are estimated by averaging all outcomes of interactions a residue is involved in. A subsequent sequential smoothing applies a Gaussian filter with a standard deviation of 4 residues to reduce noise. To avoid amino acid specific biases, a linear model is trained for all 20 naturally occurring amino acids to predict per-residue lDDT scores.

0 23_QE Baseline Potential
QMEANDISCO beta server24 2017-06-18 2017-08-24 QMEANDISCO beta Public

Abstract

Estimating the quality of a protein model is crucial to determine its utility and potential applications. Global quality estimates can already give a general impression of a model’s applicability or allow selecting a model in a set of alternatives. Extending this concept to a local per residue scale gives much more detailed insights to a protein model and opens a full range of possible applications. We have therefore extend the local quality estimation capabilities of QMEAN by harnessing distance constraints from the rapidly increasing amount of experimentally determined structural information. We improved the established quality estimation tool QMEAN and enhanced its local quality estimation capabilities with a new term based on distance constraints - DisCo. QMEAN and QME-ANDisCo have been successfully tested and compared to other state of the art local quality estimation tools on a wide variety of test sets. The careful data analysis revealed that both methods particularly stand out in distinguishing wrongly from correctly modelled residues in models of reasonable overall fold.

0 24_QE QMEANDISCO beta
Server 25 server25 2017-08-24 2017-11-02 Devel

Development server - no detailed description available

0 25_QE ZZZserver 25
Server 26 server26 2017-08-24 2019-07-01 Devel

Development server - no detailed description available

0 26_QE ZZZserver 26
Server 27 server27 2018-02-09 2019-05-16 Devel

Development server - no detailed description available

0 27_QE ZZZserver 27
ModFOLD7_lDDT server28 2018-02-22 ModFOLD7_lDDT Public - 0 28_QE ModFOLD7_lDDT
QMEANDisCo 3 server29 2018-04-20 QMEANDisCo 3 Public

Abstract

Motivation

Methods that estimate the quality of a 3D protein structure model in absence of an experimental reference structure are crucial to determine a model’s utility and potential applications. Single model methods assess individual models whereas consensus methods require an ensemble of models as input. In this work, we extend the single model composite score QMEAN that employs statistical potentials of mean force and agreement terms by introducing a consensus-based distance constraint (DisCo) score.

Results

DisCo exploits distance distributions from experimentally determined protein structures that are homologous to the model being assessed. Feed-forward neural networks are trained to adaptively weigh contributions by the multi-template DisCo score and classical single model QMEAN parameters. The result is the composite score QMEANDisCo, which combines the accuracy of consensus methods with the broad applicability of single model approaches. We also demonstrate that, despite being the de-facto standard for structure prediction benchmarking, CASP models are not the ideal data source to train predictive methods for model quality estimation. For performance assessment, QMEANDisCo is continuously benchmarked within the CAMEO project and participated in CASP13. For both, it ranks among the top performers and excels with low response times.

Studer, G., Rempfer, C., Waterhouse, A.M., Gumienny, G., Haas, J., Schwede, T. QMEANDisCo - distance constraints applied on model quality estimation. Bioinformatics 36, 1765-1771 (2020).

10.1093/bioinformatics/btz828

0 29_QE QMEANDisCo 3
Prosa2003 server2 2014-02-07 2019-06-22 Prosa2003 Public - 0 2_QE Prosa2003
Server 30 server30 2018-05-04 2018-11-17 Devel

Development server - no detailed description available

0 30_QE ZZZserver 30
ProQ3D_LDDT server31 2018-11-18 ProQ3D_LDDT Public - 0 31_QE ProQ3D_LDDT
ProQ3 server32 2018-11-18 ProQ3 Public - 0 32_QE ProQ3
ProQ3D server33 2018-11-18 ProQ3D Public - 0 33_QE ProQ3D
Server 34 server34 2020-01-15 Devel

Development server - no detailed description available

0 34_QE ZZZserver 34
Server 35 server35 2020-02-20 2021-01-08 Devel

Development server - no detailed description available

0 35_QE ZZZserver 35
Server 36 server36 2020-04-22 2022-07-19 Devel

Development server - no detailed description available

0 36_QE ZZZserver 36
Server 37 server37 2020-09-11 2022-07-19 Devel

Development server - no detailed description available

0 37_QE ZZZserver 37
Server 38 server38 2020-09-11 2022-07-19 Devel

Development server - no detailed description available

0 38_QE ZZZserver 38
ModFOLD8 server39 2021-01-08 ModFOLD8 Public - 0 39_QE ModFOLD8
Naive PSIBlast server3 2014-02-07 2019-06-22 Public

Abstract

The Baseline predictor runs PSI-BLAST with the most recent version of the NCBI "NR" database. Then, from the generated PSI-BLAST profiles, we consider the PSSM score of the target sequence residues as naive indicator of local quality. Specifically, PSI-BLAST is launched as follows:

blastpgp -d [nr database] -i [target FASTA sequence] -e 1e-10 -J t -u 1 -j 3

0 3_QE Naive PSIBlast
DeepUMQA server40 2021-11-26 2024-06-17 DeepUMQA Public

Abstract

Protein model quality assessment is a key component of protein structure prediction. In recent research, the voxelization feature was used to characterize the local structural information of residues, but it may be insufficient for describing residue-level topological information. Design features that can further reflect residue-level topology when combined with deep learning methods are therefore crucial to improve the performance of model quality assessment.

We developed an Ultrafast Shape Recognition (USR)-based residue-level single model quality assessment method, termed DeepUMQA. The residue-level USR feature is used to map the topological information of the model to each residue, thereby characterizing the relationship between the residue and the topological structure (i.e. the topological information of the residue), which is combined with the residue voxelization feature (i.e. the local structure information of the residue), secondary structure, distances and Rosetta energy terms, and use three-dimensional convo- lution, two-dimensional convolution and residual networks to predict the quality of the protein model. Experimental results show that the USR feature is complementary to the voxelization feature in describing residues from local and topological aspects, and it can thus significantly improve the performance of model quality assessment.

Sai-Sai Guo#, Jun Liu#, Xiao-Gen Zhou, Gui-Jun Zhang*, DeepUMQA: ultrafast shape recognition-based protein model quality assessment using deep learning, Bioinformatics, Volume 38, Issue 7, 1 April 2022, Pages 1895–1903.

10.1093/bioinformatics/btac056

0 40_QE DeepUMQA
Atom_ProteinQA server41 2021-12-17 2022-12-20 Atom_ProteinQA Public

Abstract

Protein model quality assessment (ProteinQA) is a fundamental task, which is essential for biologically relevant applications, i.e., protein structure refinement, protein design, etc. Previous works aim to conduct the ProteinQA only in the global whole structure or per-residue levels, ignoring potentially usable and precise cues from a fine-grained per-atom perspective. In this study, we propose an atom-level ProteinQA model, named Atom-ProteinQA, in which two innovative modules are designed to extract geometric and topological atom-level relationships respectively. Extensive experiments show that our proposed Atom-ProteinQA outperforms previous methods by a large margin, regardless of residue-level or atom-level assessment.

0 41_QE Atom_ProteinQA
Server 42 server42 2022-02-25 2022-12-20 Devel

Development server - no detailed description available

0 42_QE ZZZserver 42
DeepUMQA2 server43 2022-03-04 2024-06-17 DeepUMQA2 Public - 0 43_QE DeepUMQA2
ModFOLD9 server44 2022-03-17 ModFOLD9 Public - 0 44_QE ModFOLD9
ModFOLD9_pure server45 2022-03-17 ModFOLD9_pure Public - 0 45_QE ModFOLD9_pure
ZJUT-GraphCPLMQA server46 2022-04-08 ZJUT-GraphCPLMQA Public

GraphCPLMQA: Assessing protein model quality based on deep graph coupling networks using protein language model.

0 46_QE ZJUT-GraphCPLMQA
MEGA-Assessment server47 2022-05-27 2024-06-17 Public - 0 47_QE MEGA-Assessment
Server 48 server48 2022-06-10 2024-04-22 Devel

Development server - no detailed description available

0 48_QE ZZZserver 48
Server 49 server49 2022-07-01 2024-06-17 Devel

Development server - no detailed description available

0 49_QE ZZZserver 49
Qmean 7.11 server4 2014-02-07 2017-08-31 Qmean 7.11 Public

Abstract

QMEAN, which stands for Qualitative Model Energy ANalysis, is a composite scoring function describing the major geometrical aspects of protein structures. Five different structural descriptors are used. The local geometry is analyzed by a new kind of torsion angle potential over three consecutive amino acids. A secondary structure-specific distance-dependent pairwise residue-level potential is used to assess long-range interactions. A solvation potential describes the burial status of the residues. Two simple terms describing the agreement of predicted and calculated secondary structure and solvent accessibility, respectively, are also included.

Benkert P, Tosatto SC, Schomburg D. QMEAN: A comprehensive scoring function for model quality assessment.

Proteins. 2008 Apr;71(1):261-77.

dx.doi.org/10.1002/prot.21715

0 4_QE Qmean 7.11
Server 50 server50 2022-10-28 2023-01-09 Devel

Development server - no detailed description available

0 50_QE ZZZserver 50
Server 51 server51 2023-11-10 Devel

Development server - no detailed description available

0 51_QE ZZZserver 51
Server 52 server52 2023-11-17 Devel

Development server - no detailed description available

0 52_QE ZZZserver 52
Server 53 server53 2023-12-01 Devel

Development server - no detailed description available

0 53_QE ZZZserver 53
Server 54 server54 2023-12-01 Devel

Development server - no detailed description available

0 54_QE ZZZserver 54
Server 55 server55 2023-12-01 Devel

Development server - no detailed description available

0 55_QE ZZZserver 55
Server 56 server56 2023-12-01 Devel

Development server - no detailed description available

0 56_QE ZZZserver 56
Server 57 server57 2023-12-01 Devel

Development server - no detailed description available

0 57_QE ZZZserver 57
Server 58 server58 2023-12-01 Devel

Development server - no detailed description available

0 58_QE ZZZserver 58
Server 59 server59 2023-12-01 Devel

Development server - no detailed description available

0 59_QE ZZZserver 59
Server 5 server5 2014-02-07 2020-03-02 Devel

Development server - no detailed description available

0 5_QE ZZZserver 05
ZJUT-MultiViewMQA server60 2024-04-12 ZJUT-MultiViewMQA Public

MultiViewMQA is a protein model quality evaluation method based on a multi-view network. It employs graph attention networks, Transformer, and 3D CNNs to process features of different dimensions of proteins individually, thus capturing better protein feature representations and evaluating protein model quality.

0 60_QE ZJUT-MultiViewMQA
Server 6 server6 2014-02-07 2019-06-22 Devel

Development server - no detailed description available

0 6_QE ZZZserver 06
ModFOLD4 server7 2014-04-11 2021-10-22 ModFOLD4 Public

Abstract

The ModFOLD4 server deploys a quasi-single-model QA algorithm. This means that the method preserves the predictive power of pure clustering-based methods while also being capable of making predictions for a single model at a time. If the server receives multiple models then it will make use of a full clustering approach; however, if only a single model is submitted, then it will operate in quasi-single-model mode with comparable accuracy.

McGuffin L.J., Buenavista M.T. and Roche D.B. The ModFOLD4 server for the quality assessment of 3D protein models.

Nucleic Acids Res. 2013 Jul;41(Web Server issue):W368-72.

10.1093/nar/gkt294

0 7_QE ModFOLD4
ProQ2 server8 2014-04-25 ProQ2 Public

Abstract

ProQ2 is a model quality assessment algorithm that uses support vector machines to predict local as well as global quality of protein models. Improved performance is obtained by combining previously used features with updated structural and predicted features. The most important contribution can be attributed to the use of profile weighting of the residue specific features and the use features averaged over the whole model even though the prediction is still local.

Ray A., Lindahl E. and Wallner B. Improved model quality assessment using ProQ2.

BMC Bioinformatics 2012, 13:224

dx.doi.org/10.1186/1471-2105-13-224

0 8_QE ProQ2
Server 9 server9 2014-05-09 2016-03-24 Devel

Development server - no detailed description available

0 9_QE ZZZserver 09
Server Name (CP) Server Alias Active Since Deactived Since Weblink Server Type
Server 0 server0 2016-03-14 2020-02-14 devel

Development server - no detailed description available

None 0_CP ZZZserver 00
Server 10 server10 2018-09-14 2020-02-14 devel

Development server - no detailed description available

115.0 10_CP ZZZserver 10
Server 11 server11 2018-09-14 2020-02-14 devel

Development server - no detailed description available

171.0 11_CP ZZZserver 11
Server 12 server12 2018-11-01 2020-02-14 devel

Development server - no detailed description available

44.0 12_CP ZZZserver 12
NaiveContactMI server1 2016-03-14 2020-02-14 public

As a baseline for the contact prediction, we use mutual information (MI) to predict the most likely contacts from a multiple sequence alignment (MSA) obtained with HHblits. Specifically the MSA for the target protein is obtained from a search against the UniProt nr20 database. For our calculation of MI, we use the small number correction introduced by Buslje et al. [Bulsje et al, Bioinformatics 25:1125-1131, 2009], which simply consists in adding a small number (here 0.05) to the number of observations of any residue pair when calculating the probabilities. Gaps are not counted as an amino acid type and are therefore not included in the calculation of MI, whereas we always use the total number of sequences in the alignment as normalisation factor in the calculation of the probabilities. This effectively penalises columns with gaps in the calculation of MI.

1.0 1_CP NaiveContactMI
NaiveContactMIp server2 2016-04-14 2020-02-14 public - 1.0 2_CP NaiveContactMIp
NaiveContactMIpz server3 2016-04-14 2020-02-14 public - 1.0 3_CP NaiveContactMIpz
CevoMI server4 2016-04-14 2020-02-14 public - 1.0 4_CP cevoMI
Server 5 server5 2016-04-25 2020-02-14 devel

Development server - no detailed description available

None 5_CP ZZZserver 05
DeepCDpred-deactivated server6 2017-09-25 2017-11-03 DeepCDpred-deactivated public - None 6_CP DeepCDpred-deactivated
Server 7 server7 2017-09-25 2020-02-14 devel

Development server - no detailed description available

1239.0 7_CP ZZZserver 07
DeepCDpred server8 2017-11-03 2020-02-14 DeepCDpred public - None 8_CP DeepCDpred
Server 9 server9 2018-03-14 2020-02-14 devel

Development server - no detailed description available

3113.0 9_CP ZZZserver 09