Limits...
Distill: a suite of web servers for the prediction of one-, two- and three-dimensional structural features of proteins.

Baú D, Martin AJ, Mooney C, Vullo A, Walsh I, Pollastri G - BMC Bioinformatics (2006)

Bottom Line: The majority of the servers, including the Calpha trace predictor, now take into account homology information from the PDB, when available, resulting in greatly improved reliability.All predictions are freely available through a simple joint web interface and the results are returned by email.In a single submission the user can send protein sequences for a total of up to 32k residues to all or a selection of the servers.

View Article: PubMed Central - HTML - PubMed

Affiliation: School of Computer Science and Informatics, University College Dublin, Belfield, Dublin 4, Ireland. davide.bau@ucd.ie

ABSTRACT

Background: We describe Distill, a suite of servers for the prediction of protein structural features: secondary structure; relative solvent accessibility; contact density; backbone structural motifs; residue contact maps at 6, 8 and 12 Angstrom; coarse protein topology. The servers are based on large-scale ensembles of recursive neural networks and trained on large, up-to-date, non-redundant subsets of the Protein Data Bank. Together with structural feature predictions, Distill includes a server for prediction of Calpha traces for short proteins (up to 200 amino acids).

Results: The servers are state-of-the-art, with secondary structure predicted correctly for nearly 80% of residues (currently the top performance on EVA), 2-class solvent accessibility nearly 80% correct, and contact maps exceeding 50% precision on the top non-diagonal contacts. A preliminary implementation of the predictor of protein Calpha traces featured among the top 20 Novel Fold predictors at the last CASP6 experiment as group Distill (ID 0348). The majority of the servers, including the Calpha trace predictor, now take into account homology information from the PDB, when available, resulting in greatly improved reliability.

Conclusion: All predictions are freely available through a simple joint web interface and the results are returned by email. In a single submission the user can send protein sequences for a total of up to 32k residues to all or a selection of the servers. Distill is accessible at the address: http://distill.ucd.ie/distill/.

Show MeSH

Related in: MedlinePlus

Expected performances of 3Distill. 3D reconstruction performances measured as average TM scores against the correct structure. Tested on the S258 set (see text for details). Maximum sequence similarity allowed to homologues in the PDB: 95%.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC1574355&req=5

Figure 4: Expected performances of 3Distill. 3D reconstruction performances measured as average TM scores against the correct structure. Tested on the S258 set (see text for details). Maximum sequence similarity allowed to homologues in the PDB: 95%.

Mentions: Figure 4 shows the expected accuracy of the Cα trace reconstructor, as a function of sequence similarity to the closest homologue in the PDB, measured on the S258 set. The accuracy is measured as the TM score to the Cα trace of the experimental structure. For sequence similarity above 30% the predictions' TM score is on average slightly above 0.7 indicating high reliability, is approximately 0.45 in the 20–30% interval, and 0.27 in the region below 20%. If reconstruction performances are measured on the S258 set without allowing homology information at any stage (pure ab initio predictions) the average TM score is 0.27, with 43 of the 258 structures above a TM score of 0.4 [11]. The reliability score reported in the remarks field of the PDB file has an average correlation of 0.7 with the TM score against the true structure, and thus provides a good estimate of the quality of the prediction.


Distill: a suite of web servers for the prediction of one-, two- and three-dimensional structural features of proteins.

Baú D, Martin AJ, Mooney C, Vullo A, Walsh I, Pollastri G - BMC Bioinformatics (2006)

Expected performances of 3Distill. 3D reconstruction performances measured as average TM scores against the correct structure. Tested on the S258 set (see text for details). Maximum sequence similarity allowed to homologues in the PDB: 95%.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC1574355&req=5

Figure 4: Expected performances of 3Distill. 3D reconstruction performances measured as average TM scores against the correct structure. Tested on the S258 set (see text for details). Maximum sequence similarity allowed to homologues in the PDB: 95%.
Mentions: Figure 4 shows the expected accuracy of the Cα trace reconstructor, as a function of sequence similarity to the closest homologue in the PDB, measured on the S258 set. The accuracy is measured as the TM score to the Cα trace of the experimental structure. For sequence similarity above 30% the predictions' TM score is on average slightly above 0.7 indicating high reliability, is approximately 0.45 in the 20–30% interval, and 0.27 in the region below 20%. If reconstruction performances are measured on the S258 set without allowing homology information at any stage (pure ab initio predictions) the average TM score is 0.27, with 43 of the 258 structures above a TM score of 0.4 [11]. The reliability score reported in the remarks field of the PDB file has an average correlation of 0.7 with the TM score against the true structure, and thus provides a good estimate of the quality of the prediction.

Bottom Line: The majority of the servers, including the Calpha trace predictor, now take into account homology information from the PDB, when available, resulting in greatly improved reliability.All predictions are freely available through a simple joint web interface and the results are returned by email.In a single submission the user can send protein sequences for a total of up to 32k residues to all or a selection of the servers.

View Article: PubMed Central - HTML - PubMed

Affiliation: School of Computer Science and Informatics, University College Dublin, Belfield, Dublin 4, Ireland. davide.bau@ucd.ie

ABSTRACT

Background: We describe Distill, a suite of servers for the prediction of protein structural features: secondary structure; relative solvent accessibility; contact density; backbone structural motifs; residue contact maps at 6, 8 and 12 Angstrom; coarse protein topology. The servers are based on large-scale ensembles of recursive neural networks and trained on large, up-to-date, non-redundant subsets of the Protein Data Bank. Together with structural feature predictions, Distill includes a server for prediction of Calpha traces for short proteins (up to 200 amino acids).

Results: The servers are state-of-the-art, with secondary structure predicted correctly for nearly 80% of residues (currently the top performance on EVA), 2-class solvent accessibility nearly 80% correct, and contact maps exceeding 50% precision on the top non-diagonal contacts. A preliminary implementation of the predictor of protein Calpha traces featured among the top 20 Novel Fold predictors at the last CASP6 experiment as group Distill (ID 0348). The majority of the servers, including the Calpha trace predictor, now take into account homology information from the PDB, when available, resulting in greatly improved reliability.

Conclusion: All predictions are freely available through a simple joint web interface and the results are returned by email. In a single submission the user can send protein sequences for a total of up to 32k residues to all or a selection of the servers. Distill is accessible at the address: http://distill.ucd.ie/distill/.

Show MeSH
Related in: MedlinePlus