BlOMIND-protein property prediction by property proximity profiles

  • Authors:
  • Deendayal Dinakarpandian;Vijay Kumar

  • Affiliations:
  • University of Missouri-Kansas City, SICE Computer Networking, Kansas City, MO;University of Missouri-Kansas City, SICE Computer Networking, Kansas City, MO

  • Venue:
  • Proceedings of the 2002 ACM symposium on Applied computing
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present the infrastructure of a bioinformation system called BIOMIND, which exploits the close relationship between the structural and functional properties of proteins. The scheme presented here views proteins as composite entities with structural and functional properties, and searches are based on distances along each property axis. Explicitly, this allows one to frame complex queries using quantitative criteria that confer more discerning power than systems based on a text-matching approach. Implicitly, and more importantly, this has the potential to reveal patterns of convergence in properties of proteins and improve our ability to approximate the unknown properties of a protein, given a set of known properties.