Separating true positive predicted residue contacts from false positive ones in mainly α proteins, using constrained Metropolis MC simulations

Spyridon Vicatos, Yiannis N. Kaznessis

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

We present a method that significantly improves the accuracy of predicted proximal residue pairs in protein molecules. Computational methods for predicting pairs of amino acids that are distant in the protein sequence but close in the protein 3D structure can benefit attempts to in silico recognize the fold of a protein molecule. Unfortunately, currently available methods suffer from low predictive accuracy. In this work, we use Monte Carlo simulions to fold protein molecules with proximal pair predictions used as additional energy constraints. To test our methods, we study molecules with known tertiary structures. With Monte Carlo, we generate ensembles of structures for each set of residues constraints. The distribution of the root mean square deviation of the folded structures from the known native structure reveals clear information about the accuracy of the constraint sets used. With recursive substitutions of constraints, false positive predictions are identified and filtered out and significant improvements in accuracy are observed.

Original languageEnglish (US)
Pages (from-to)539-552
Number of pages14
JournalProteins: Structure, Function and Genetics
Volume70
Issue number2
DOIs
StatePublished - Feb 1 2008

Keywords

  • Contact map
  • Fold prediction
  • Metropolis Monte Carlo
  • Proximal residues
  • Residue constraints

Fingerprint Dive into the research topics of 'Separating true positive predicted residue contacts from false positive ones in mainly α proteins, using constrained Metropolis MC simulations'. Together they form a unique fingerprint.

Cite this