Name
Title | ||
|---|---|---|
Disulfide connectivity prediction using secondary structure information and diresidue frequencies. |
Abstract | ||
|---|---|---|
We describe a stand-alone algorithm to predict disulfide bond partners in a protein given only the amino acid sequence, using a novel neural network architecture (the diresidue neural network), and given input of symmetric flanking regions of N-terminus and C-terminus half-cystines augmented with residue secondary structure (helix, coil, sheet) as well as evolutionary information. The approach is motivated by the observation of a bias in the secondary structure preferences of free cysteines and half-cystines, and by promising preliminary results we obtained using diresidue position-specific scoring matrices.As calibrated by receiver operating characteristic curves from 4-fold cross-validation, our conditioning on secondary structure allows our novel diresidue neural network to perform as well as, and in some cases better than, the current state-of-the-art method. A slight drop in performance is seen when secondary structure is predicted rather than being derived from three-dimensional protein structures. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1093/bioinformatics/bti328 | Bioinformatics |
Keywords | Field | DocType |
novel diresidue neural network,secondary structure preference,c-terminus half-cystines,disulfide connectivity prediction,novel neural network architecture,secondary structure information,three-dimensional protein structure,secondary structure,diresidue position-specific,residue secondary structure,diresidue neural network,supplementary information,diresidue frequency,disulfide bond | Matrix (mathematics),Computer science,Network architecture,Algorithm,Electromagnetic coil,Helix,Artificial neural network,Protein Data Bank (RCSB PDB),Protein secondary structure,Protein structure | Journal |
Volume | Issue | ISSN |
21 | 10 | 1367-4803 |
Citations | PageRank | References |
20 | 1.50 | 10 |
Authors | ||
2 | ||