Overview of prediction methods
Predict Secondary Structure (PSIPRED)
PSIPRED is a simple and accurate secondary structure prediction method, incorporating two feed-forward neural networks which perform an analysis on output obtained from PSI-BLAST (Position Specific Iterated - BLAST). Using a very stringent cross validation method to evaluate the method's performance, PSIPRED 3.2 achieves an average Q3 score of 81.6%.
Predictions produced by PSIPRED were also submitted to the CASP4 evaluation and assessed during the CASP4 meeting, which took place in December 2000 at Asilomar. PSIPRED 2.0 achieved an average Q3 score of 80.6% across all 40 submitted target domains with no obvious sequence similarity to structures present in PDB, which ranked PSIPRED top out of 20 evaluated methods (an earlier version of PSIPRED was also ranked top in CASP3 held in 1998).
It is important to realise, however, that due to the small sample sizes, the results from CASP are not statistically significant, although they do give a rough guide as to the current "state of the art". For a more reliable evaluation, the EVA web site at Columbia University provides a continuous evaluation. NOTE that at the time of writing, the EVA site is no longer being updated.
Downloads: The PSIPRED V3.2 software can be downloaded from HERE. Please note that you should read the license terms given in the README file if you wish to incorporate PSIPRED in another program or Web server.
Older releases of PSIPRED can be downloaded here HERE.
MEMSAT3 : Transmembrane Topology Prediction
MEMSAT V3 is a widely used all-helical membrane protein prediction method MEMSAT. The method was benchmarked on a test set of transmembrane proteins of known topology. From sequence data MEMSAT was estimated to have an accuracy of over 78% at predicting the structure of all-helical transmembrane proteins and the location of their constituent helical elements within a membrane.
Academic users can download MEMSAT3 code here.
MEMSATSVM : Transmembrane helix prediction
MEMSATSVM is highly accurate predictor of transmembrane helix topology. It is capable to discriminating signal peptides and identifying the cytosolic and extra-cellular loops. Users can download MEMSATSVM from here.
MEMPACK : Transmembrane helix contact prediction
MEMPACK is a membrane helix packing predictor. The process leverages MEMSATSVM predictions to predict possible inter-helix interactions. The final step a helix packing is produced that orients the helices such that the greatest number of predicted interactions face one another .Users can download MEMPACK from here.
GenTHREADER : Fold Recognition
GenTHREADER is a fast and relatively powerful fold recognition method, which can be applied to either whole, translated genomic sequences (proteomes) as in the case of the GTD or individual protein sequences as in the case of the PSIPRED server. It is not as sensitive at mGenTHREADER but is much faster.
pGenTHREADER: Fold Recognition
This method is now our recommended method for fold recognition and identification of distant homologues. Essentially it is the based on the original GenTHREADER method, but makes use of profile-profile alignments and predicted secondary structure (using PSIPRED) as inputs. This increases both the sensitivity of the method and enhances the accuracy of alignments, but also makes it much slower than the normal GenTHREADER method as PSI-BLAST needs to be run on the target sequence before the search can begin.
pDomTHREADER: Domain Recognition
pDomTHREADER is an accurate and sensitive superfamily discrimination, combining information from both sequence and structure to produce highly accurate domain alignments. The method employs the same underlying threading algorithm as pGenTHREADER, however it aligns sequences to a domain-based template library rather than a chain-based template library. The use of smaller regions of structure for templates means that different features of the alignments are required for optimal scoring. The final prediction score results from an SVM trained on a combination of 5 different feature inputs; template coverage, alignment score, template length, solvation and pairwise potentials.
Compared with other superfamily discrimination methods using Hidden Markov Models and PSI-BLAST profile alignments, we found that pDomTHREADER provided higher coverage on the CATH S35 superfamilies. Additionally, pDomTHREADER produced more accurate alignments that can be used to better predict domain boundaries. For more information regarding the method, please consult the reference above.
Please note that the pDomTHREADER method is tuned for performance in fine superfamily discrimination, for fold recognition problems or structural annotation of very distant sequences, pGenTHREADER should be used.
DomPred & DOMSSEA : Domain Boundary Prediction
DomPred is a protein structural domain boundary predictor. The DomPred process runs 2 independent protein domain predictors; DomPred and DOMSSEA. The DomPred process begins by using PSI-BLAST to match a database of Pfam-A domains to the query sequence, where not clear domains can be match it then proceeds to search the nrdb90 sequence database with PSI-BLAST. The final prediction is procduced by analysing the locations of all the N and C boundaries for each hit. For the DOMSSEA process predicted secondary structure patterns in the query sequence are matched to a library of SCOP domain secondary structure patterns.
DISOPRED2 : Native disorder prediction
DISOPRED2 is a highly accurate predictor of natively disordered regions in proteins. The query sequence first has it's PSSM calculated by performing a PSIBLAST search against uniref90. Each residue is analysed in turn by a linear SVM where the input vector represents data in a 15 residue window around the target residue. Users can download the DISOPRED software from our downloads site
FFPRED: GO Term prediction
FFPRED is an SVM predictor of protein GO terms specifically trained to predict terms for Human sequences where GO terms can not be predicted by other means. An incoming protein sequence is analysed by a large suite of protein physio-chemical property predictors covering many features such as signal peptides, membrane helices, secondary structure, disorder. Then these features act as inputs for a large set of SVM models, one for each GO term to be predicted. At the end all high scoring SVMs are aggregated as the user results.
BioSerf
BioSerf is a fully automated homology modelling server. The process runs 3 template selection methods; PSIBLAST against PDB fasta, pGenTHREADER and HHBlits against the PDB. The best scoring matches given conservative cut-offs are then aggregated. All-by-all TM scores are then calculated for the full set of putative templates and the matrix of scores is analysed to remove any possible outlying templates whose structure is too dissimilar to the full set of templates. Finally the best 10 templates are selected from the remaining templates and a model is built using MODELLER.