Disulfide connectivity prediction using secondary structure information and diresidue frequencies

Bioinformatics. 2005 May 15;21(10):2336-46. doi: 10.1093/bioinformatics/bti328. Epub 2005 Mar 1.


Motivation: 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.

Results: 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.

MeSH terms

  • Algorithms*
  • Artificial Intelligence
  • Binding Sites
  • Computer Simulation
  • Cysteine / chemistry*
  • Disulfides / analysis
  • Disulfides / chemistry*
  • Models, Chemical*
  • Protein Binding
  • Protein Conformation
  • Protein Interaction Mapping / methods*
  • Protein Structure, Secondary
  • Proteins / analysis
  • Proteins / chemistry*
  • Sequence Alignment / methods
  • Sequence Analysis, Protein / methods*
  • Software
  • Structure-Activity Relationship


  • Disulfides
  • Proteins
  • Cysteine