Metric Labeling and Semi-metric Embedding for Protein Annotation Prediction

  • Emre Sefer
  • Carl Kingsford
Conference paper

DOI: 10.1007/978-3-642-20036-6_37

Part of the Lecture Notes in Computer Science book series (LNCS, volume 6577)
Cite this paper as:
Sefer E., Kingsford C. (2011) Metric Labeling and Semi-metric Embedding for Protein Annotation Prediction. In: Bafna V., Sahinalp S.C. (eds) Research in Computational Molecular Biology. RECOMB 2011. Lecture Notes in Computer Science, vol 6577. Springer, Berlin, Heidelberg

Abstract

Computational techniques have been successful at predicting protein function from relational data (functional or physical interactions). These techniques have been used to generate hypotheses and to direct experimental validation. With few exceptions, the task is modeled as multi-label classification problems where the labels (functions) are treated independently or semi-independently. However, databases such as the Gene Ontology provide information about the similarities between functions. We explore the use of the Metric Labeling combinatorial optimization problem to make use of heuristically computed distances between functions to make more accurate predictions of protein function in networks derived from both physical interactions and a combination of other data types. To do this, we give a new technique (based on convex optimization) for converting heuristic semimetric distances into a metric with minimum least-squared distortion (LSD). The Metric Labeling approach is shown to outperform five existing techniques for inferring function from networks. These results suggest Metric Labeling is useful for protein function prediction, and that LSD minimization can help solve the problem of converting heuristic distances to a metric.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Emre Sefer
    • 1
    • 2
  • Carl Kingsford
    • 1
    • 2
  1. 1.Department of Computer ScienceUniversity of MarylandCollege Park
  2. 2.Center for Bioinformatics and Computational Biology, Institute for Advanced Computer StudiesUniversity of MarylandCollege Park

Personalised recommendations