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

Distill's single-query interface. The multi-query interface is identical, except that the query name box is missing (names are extracted directly from the FASTA format).
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 1: Distill's single-query interface. The multi-query interface is identical, except that the query name box is missing (names are extracted directly from the FASTA format).

Mentions: Input into the servers is handled by two simple HTML forms: one for submissions of single queries (see Figure 1); the other for submitting multiple queries. In both forms the user must provide an email address, to which the response will be sent. In the single-query form the user has also the option of providing a query name, that will be reported in the server response. In the single-query form the user needs to provide the query sequence in plain 1-letter code, with no headers. New-line, tab and space characters are ignored. In the multi-query form the user may provide the queries in FASTA format, with each query name preceded by the > symbol on a line and the corresponding protein sequence on the following line or lines (space and tab characters are ignored). If the user adopts the multi-query form, a separate email will be sent for each query. The query name quoted in the response will be the query name as parsed from the FASTA format. In both forms the user can select any combination of the servers via a set of tick-boxes. Submissions of up to 32,768 characters (roughly 100 average proteins) are accepted by the multi-query form, making medium- to large-scale predictions possible with only a small number of manual submissions.


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)

Distill's single-query interface. The multi-query interface is identical, except that the query name box is missing (names are extracted directly from the FASTA format).
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 1: Distill's single-query interface. The multi-query interface is identical, except that the query name box is missing (names are extracted directly from the FASTA format).
Mentions: Input into the servers is handled by two simple HTML forms: one for submissions of single queries (see Figure 1); the other for submitting multiple queries. In both forms the user must provide an email address, to which the response will be sent. In the single-query form the user has also the option of providing a query name, that will be reported in the server response. In the single-query form the user needs to provide the query sequence in plain 1-letter code, with no headers. New-line, tab and space characters are ignored. In the multi-query form the user may provide the queries in FASTA format, with each query name preceded by the > symbol on a line and the corresponding protein sequence on the following line or lines (space and tab characters are ignored). If the user adopts the multi-query form, a separate email will be sent for each query. The query name quoted in the response will be the query name as parsed from the FASTA format. In both forms the user can select any combination of the servers via a set of tick-boxes. Submissions of up to 32,768 characters (roughly 100 average proteins) are accepted by the multi-query form, making medium- to large-scale predictions possible with only a small number of manual submissions.

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