Active machine learning for transmembrane helix prediction Public Deposited

Downloadable Content

Download PDF
Creator
  • Carbonell, Jaime G
    • Other Affiliation: Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA
  • Osmanbeyoglu, Hatice U
    • Other Affiliation: Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
  • Wehner, Jessica A
    • Affiliation: College of Arts and Sciences, Department of Mathematics
  • Ganapathiraju, Madhavi K
    • Other Affiliation: Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA; Intelligent Systems Program, University of Pittsburgh School of Art and Sciences, Pittsburgh, PA, USA
Abstract
  • Abstract Background About 30% of genes code for membrane proteins, which are involved in a wide variety of crucial biological functions. Despite their importance, experimentally determined structures correspond to only about 1.7% of protein structures deposited in the Protein Data Bank due to the difficulty in crystallizing membrane proteins. Algorithms that can identify proteins whose high-resolution structure can aid in predicting the structure of many previously unresolved proteins are therefore of potentially high value. Active machine learning is a supervised machine learning approach which is suitable for this domain where there are a large number of sequences but only very few have known corresponding structures. In essence, active learning seeks to identify proteins whose structure, if revealed experimentally, is maximally predictive of others. Results An active learning approach is presented for selection of a minimal set of proteins whose structures can aid in the determination of transmembrane helices for the remaining proteins. TMpro, an algorithm for high accuracy TM helix prediction we previously developed, is coupled with active learning. We show that with a well-designed selection procedure, high accuracy can be achieved with only few proteins. TMpro, trained with a single protein achieved an F-score of 94% on benchmark evaluation and 91% on MPtopo dataset, which correspond to the state-of-the-art accuracies on TM helix prediction that are achieved usually by training with over 100 training proteins. Conclusion Active learning is suitable for bioinformatics applications, where manually characterized data are not a comprehensive representation of all possible data, and in fact can be a very sparse subset thereof. It aids in selection of data instances which when characterized experimentally can improve the accuracy of computational characterization of remaining raw data. The results presented here also demonstrate that the feature extraction method of TMpro is well designed, achieving a very good separation between TM and non TM segments.
Date of publication
Identifier
  • doi:10.1186/1471-2105-11-S1-S58
Resource type
  • Article
Rights statement
  • In Copyright
Rights holder
  • Hatice U Osmanbeyoglu et al.; licensee BioMed Central Ltd.
License
Language
  • English
Is the article or chapter peer-reviewed?
  • Yes
Bibliographic citation
  • BMC Bioinformatics. 2010 Jan 18;11(Suppl 1):S58
Access
  • Open Access
Publisher
  • BioMed Central Ltd
Parents:

This work has no parents.

Items