SSpro is a server for protein secondary structure prediction based on an ensemble of 100 1D-RNNs (one dimensional recurrent neural networks). For a detailed explanation of the methods see in the references. SSpro version 1 was online on 3/13/2000. In one year it handled more than 10,000 queries from 60 domains, at least 50 countries all over the world.
From the very beginning SSpro 3.0 was tested by the independent assessor EVA, and showed a performance constantly exceeding 76% correctly classified residues on structures with no homologues in PDB, thus ranking always in first position among the servers tested. SSpro v4.0 currently achieves an accuracy of 78.7% on the independent evaluator server EVA. SSpro v4.5 includes the direct incorporation of homologous protein's secondary structure and probablistic methods to improve the SOV score.
SSpro8 is an experimental extension to SSpro. Instead of using three classes (helix, strand and the rest) to assign the secondary structure of a protein, SSpro8 adopts the full DSSP 8-class output classification:
For a detailed description of the tests performed on SSpro8, see the references. The overall performance (Q8) of the system currently online (based on PSI-BLAST profiles) is approximately 63%. NOTE: SSpro8 is a completely different system from SSpro. Their results may not match.
ABTMpro is a server that predicts whether a given protein sequence is a transmembrane protein. If the given protein sequence is a transmembrane protein, ABTMpro further predicts the probabilities of the protein being an alpha helical transmembrane protein or a Beta Barrel transmembrane protein. The prediction framework consists of a Support Vector Machine, which utilizes features such as amino acid composition and properties, reduced alphabet composition, predicted secondary structure, evolutionary information etc. The overall accuracy of ABTMpro is upwards of 97%, and achieves MCC values of 0.93 and 0.94 on smaller data sets and MCC values of 0.85 and 0.63 on much larger tests for alpha helical and beta barrel transmembrane proteins respectively.
CONpro is a server that predicts whether the number of contacts of each residue in a protein is above or below the average for that residue. The prediction of CONpro is based on 1D-RNNs, adopting as input a multiple alignment of homologues generated by PSI-BLAST. The threshold radius at which residues are considered in contact is at 12Å. The accuracy of CONpro is 73%. The complete system is an ensemble of 10 1D-RNNs. For a more detailed explanation, see in the references.
ACCpro is a server for the prediction of the relative solvent accessibility of protein residues. The prediction of ACCpro is based on 1D-RNNs, adopting as input a multiple alignment of homologues generated by PSI-BLAST. Each residue in a protein is predicted as buried or exposed, i.e. less or more accessible than a specified threshold. All thresholds between 0% and 95% at steps of 5% are available. For a 25% threshold, the 'hard' case corresponding to practically identical numbers of buried and exposed residues, ACCpro classifies correctly 77.2% of the residues, better than any other system previously described. For a more detailed explanation, see in the references.
ACCpro20 predicts the relative solvent accessiblity at all thresholds between 0% and 100% at 5% increments.
DOMpro predicts domain locations using a 1D-RNN. DOMpro takes an input the sequence profile, predicted secondary structure, and predicted relative solvent accessiblity. The output of the 1D-RNN is a classification for each residue as being in a domain boundary region or not. The domains are then infered from this output. For a more detailed explanation, see the manuscript in references.Download DOMpro 1.0 executable for Linux (free for academic use) and the datasets used to train DOMpro.
DISpro uses a 1D-RNN to predict the probablity that residues are
disorder. The probabilities are also thresholded at probablity .5 to
make a hard classification. The input to DISpro is the sequence
profile, predicted secondary structure, and predicted relative solvent
For a more detailed explanation, see the manuscript in references.
Download the dataset used in training DISpro here.
DIpro is a cysteine disulfide bond predictor based on 2D recurrent neural network, support vector machine, graph matching and regression algorithms. It can predict if the sequence has disulfide bonds or not, estimate the number of disulfide bonds, and predict the bonding state of each cysteine and the bonded pairs. It yields the best accuracy on the benchmark dataset Sp39. It can handle any number of disulfide bonds where most of methods available so far only can handle less than 6 disulfide bonds.
Procedure: The seqeunce is processed in two steps. Step 1, use support
vector machine to classify if the sequence has disulfide bonds or
not. Step 2, use neural network and graph algorithm to predict the
number of bonds, bond pattern.
For a more detailed explanation, see in references.
Download DIpro 2.0 software(free for academic use)
Download the dataset used in training DIpro here.
CMAPpro is a server for the prediction of maps of contacts between protein residues. The prediction of CMAPpro is based on ensembles of Deep Neural Networks, which take into account the spatial dependencies of contact occurrences in local neighborhoods. The input of the system consists of two-dimensional profiles extracted from multiple alignments of homologues generated by PSI-BLAST, secondary structure and solvent accessibility predictions obtained respectively from SSpro and ACCpro, and predicted coarse contacts and orientations between secondary structure elements using two-dimensional Recurrent Neural Networks. Maps at 8Å are available, meaning that two amino acids are defined as being in contact if their C-β atoms (C-α for glycines ) are closer than 8Å. For a description of the tests performed on CMAPpro, see the references.
SVMcon predicts medium- to long-range residue-residue contacts using
Support Vector Machines. The contact predictions are in the CASP
format (residue index 1, residue index 2, 0, 8, contact probability).
The contact distance threshold is 8 angstrom. The sequence separation
between two residues is at least 6 residues. For information, see the references.
[Download SVMcon 1.0]
[Download SVMcon Training Set]
[Download SVMcon Test Set]
For commercial license, please contact firstname.lastname@example.org
3Dpro is a server that predicts protein tertiary structure. 3Dpro uses predicted structural features, and PDB knowledge based statistical terms in the energy function. The conformational search uses a move set consisting of fragment replacement (using a fragment library built from the PDB) as well as random perturbations to the model. Moves are selected or rejected based on a simulated annealing method with linear cooling. Multiple models are constructed using random seeds and the model with the lowest energy is selected as the final prediction. 3Dpro is currently a de nuvo method (structural templates are not used).
The results of 3Dpro's performance at CASP6 can be found here.
SOLpro predicts the propensity of a protein to be soluble upon overexpression in E. coli using a two-stage SVM architecture based on multiple representations of the primary sequence. Each classifier of the first layer takes as input a distinct set of features describing the sequence. A final SVM classifier summarizes the resulting predictions and predicts if the protein is soluble or not as well as the corresponding probability.Download SOLpro (free for academic, non commercial, use).
ANTIGENpro is a sequence-based, alignment-free and pathogen-independant predictor of protein antigenicity. The predictions are made by a two-stage architecture based on multiple representations of the primary sequence and five machine learning algorithms. A final SVM classifier summarizes the resulting predictions and predicts if the protein is likely to be antigenic or not as well as the corresponding probability. ANTIGENpro is the first predictor of the whole protein antigenicity trained using reactivity data obtained by protein microarray analysis for five pathogens.
Your email address, the place where the prediction will be delivered. NOTE: Check that you typed your address correctly. Approximately 5% of the queries handled by SSpro 1.0 didn't receive an answer because of incorrect typing.
An optional name for your query. We strongly suggest that you use one, especially if sending more than one query. The order in which you send your queries may not correspond to the order in which you receive the answers.
The sequence of amino acids:
Replies are sent by email. SSpro, SSpro8, ACCpro, ACCpro20, DOMpro, DISpro, DIpro, CONpro and SOLpro replies come as text, embedded in the body of the email. Here you have an example of prediction:
Predicted Secondary Structure:
Predicted Secondary Structure (8 Class):
Predicted Relative Solvent Accessiblity (at 25% exposed threshold):
Predicted Relative Solvent Accessiblity (20 Class):
Predicted Contact Number:
Predicted Disordered Residues:
Predicted Disorder Probability:
0.16 0.07 0.04 0.04 0.03 0.02 0.02 0.01 0.02 0.02 0.02 0.01 0.01 0.01 0.02 0.02 0.03 0.04 0.06 0.06 0.12 0.13 0.20 0.17 0.18 0.20 0.23 0.48 0.55 0.58
Domain 1: 1 - 30
Predicted Disulfide Bonds:
Input sequence has LESS THAN TWO cysteins and therefore cannot form disulfide bonds.
Predicted Contact Maps:
Predicted Solubility upon Overexpression:
SOLUBLE with probability 0.901803
The predictions have the following meaning:
Note: Since CMAPpro and 3Dpro predictions are computationally intensive only proteins of length at most 400 amino acids will be accepted if CMAPpro or 3Dpro predictions are selected.
For the server and SSpro/ACCpro4.0 software package, please refer to:
J. Cheng, A. Randall, M. Sweredoski, P. Baldi, SCRATCH: a Protein Structure and Structural Feature Prediction Server, Nucleic Acids Research, vol. 33 (web server issue), w72-76, 2005. [PDF] [PDF at NAR website] [Download SSpro/ACCpro 4.0]
For an explanation of the methods used in SSpro and SSpro8 see:
G.Pollastri, D.Przybylski, B.Rost, P.Baldi, "Improving the Prediction of Protein Secondary Structure in Three and Eight Classes Using Recurrent Neural Networks and Profiles", Proteins, 47, 228-235, 2002.
Download PDF, Abstract and HTML (Proteins web site).
For an explanation of the methods used in ACCpro and CONpro see:
G.Pollastri, P.Baldi, P.Fariselli, R.Casadio, "Prediction of Coordination Number and
Relative Solvent Accessibility in Proteins", Proteins, 47, 142-153, 2002.
Download PDF, Abstract and HTML (Proteins web site)
For an explanation of the methods used in DOMpro see:
J. Cheng, M. Sweredoski, P. Baldi, "DOMpro: Protein Domain Prediction Using Profiles, Secondary Structure, Relative Solvent Accessibility, and Recursive Neural Networks", Knowledge Discovery and Data Mining, vol. 13, no. 1, pp. 1-10, 2006.
For an explanation of the methods used in DISpro see:
J. Cheng, M. Sweredoski, P. Baldi, "Accurate Prediction of Protein Disordered Regions by Mining Protein Structure Data", Data Mining and Knowledge Discovery, vol. 11, no. 3, pp. 213-222, 2005.
Download PDF, PDF at DAMI web site
For an explanation of the methods used in DIpro see:
J. Cheng, H. Saigo, P. Baldi, "Large-Scale Prediction of Disulphide Bridges Using Kernel Methods, Two-Dimensional Recursive Neural Networks, and Weighted Graph Matching", Proteins, vol. 62, no. 3, pp. 617-629, 2006. [PDF][PDF at Proteins website] [Download DIpro 2.0]
P.Baldi, J. Cheng, A. Vullo, "Large-Scale Prediction of Disulphide Bond Connectivity", Advances in Neural Information Processing Systems (NIPS 2004) 17,L. Saul ,Y. Weiss, and L. Bottou editors, MIT press, pp.97-104, Cambridge, MA, 2005.
For an explanation of the methods used in CMAPpro see:
P. Di Lena, K. Nagata, P. Baldi, "Deep Architectures for Protein Contact Map Prediction", Bioinformatics, 2012. In press
Download PDF,HTML abstract (Bioinformatics web site)
P. Di Lena, K. Nagata, P. Baldi, "Deep Spatio-Temporal Architectures and Learning for Protein Structure Prediction", Neural Information Processing Systems (NIPS), 2012. Accepted for presentation.
G.Pollastri, P.Baldi, "Prediction of Contact Maps by Recurrent Neural Network Architectures and Hidden Context Propagation from All Four Cardinal Corners", Bioinformatics, 18 Suppl 1, S62-S70 (2002).
Download PDF, HTML abstract (Bioinformatics web site).
For an explanation of the methods used in SVMcon see:
J. Cheng and P. Baldi. "Improved Residue Contact Prediction Using Support Vector Machines and a Large Feature Set." BMC Bioinfomatics. 8:113, 2007.
Download [Download SVMcon 1.0]
For an explanation of the methods used in COBEpro:
Michael J. Sweredoski and Pierre Baldi. "COBEpro: a novel system for predicting continuous B-cell epitopes." Protein Engineering Design and Selection 2008; doi: 10.1093/protein/gzn075
Download PDF, HTML (Bioinformatics website)