Prediction of boundaries between intrinsically ordered and disordered protein regions.

Predrag Radivojac, Zoran Obradović, Celeste J. Brown, A. Keith Dunker

Research output: Contribution to journalArticle

54 Scopus citations


Using proteins with both disordered and ordered regions collected through literature searches and database scanning, we assembled a set of 24-residue long segments centered on their order/disorder boundaries as well as a larger set of non-boundary segments consisting of either order or disorder. We analyzed position-specific amino acid compositions around the order/disorder boundaries and found more than thirty significant (p < 0.05) compositional differences between boundary and non-boundary data. From this analysis, we constructed several logistic regression predictors of order/disorder boundaries using slightly different data modeling approaches. Exact boundary prediction accuracies were estimated to be in the range from 74% to 80% for the different predictors.

Original languageEnglish (US)
Pages (from-to)216-227
Number of pages12
JournalPacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
StatePublished - 2003
Externally publishedYes

ASJC Scopus subject areas

  • Medicine(all)

Fingerprint Dive into the research topics of 'Prediction of boundaries between intrinsically ordered and disordered protein regions.'. Together they form a unique fingerprint.

  • Cite this