Protein Structure Prediction Using String Kernels

Abstract

With recent advances in large-scale sequencing technologies, there has been an exponential growth in protein sequence information. Currently, the ability to produce sequence information far out-paces the rate at which one can produce structural and functional information. Consequently, researchers increasingly rely on computational techniques to extract useful information from known structures contained in large databases, though such approaches remain incomplete. As such, unraveling the relationship between pure sequence information and three-dimensional structure remains one of the great fundamental problems in molecular biology. In this report, the authors aim to show several ways in which researchers try to characterize the structural, functional, and evolutionary nature of proteins. Specifically, they focus on three common prediction problems: secondary structure prediction, remote homology, and fold prediction. They describe a class of methods employing large margin classifiers with novel kernel functions for solving these problems, supplemented with a thorough evaluation study.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 03, 2006
Accession Number
ADA444439

Entities

People

  • George Karypis
  • Huzefa Rangwala
  • Kevin Deronne

Organizations

  • University of Minnesota

Tags

Communities of Interest

  • Autonomy
  • Ground and Sea Platforms

DTIC Thesaurus Topics

  • Algorithms
  • Amino Acids
  • Computational Biology
  • Computational Science
  • Computer Programming
  • Computer Science
  • Databases
  • Hidden Markov Models
  • Information Science
  • Kernel Functions
  • Machine Learning
  • Markov Models
  • Models
  • Network Science
  • Neural Networks
  • Supervised Machine Learning
  • Three Dimensional

Readers

  • Distributed Systems and Data Platform Development
  • Molecular and Cellular Biochemistry
  • Systems Analysis and Design