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

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/.

Figure 2

Distill's flowchart. Information flows from the top of the chart to the bottom.

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).

Figure 3

XXStout PNG example output. The 12Å contact map predicted for the example given in the "output format" section.

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%.