Cargando…

Improved functional prediction of proteins by learning kernel combinations in multilabel settings

BACKGROUND: We develop a probabilistic model for combining kernel matrices to predict the function of proteins. It extends previous approaches in that it can handle multiple labels which naturally appear in the context of protein function. RESULTS: Explicit modeling of multilabels significantly impr...

Descripción completa

Detalles Bibliográficos
Autores principales: Roth, Volker, Fischer, Bernd
Formato: Texto
Lenguaje:English
Publicado: BioMed Central 2007
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1892070/
https://www.ncbi.nlm.nih.gov/pubmed/17493250
http://dx.doi.org/10.1186/1471-2105-8-S2-S12
_version_ 1782133820156280832
author Roth, Volker
Fischer, Bernd
author_facet Roth, Volker
Fischer, Bernd
author_sort Roth, Volker
collection PubMed
description BACKGROUND: We develop a probabilistic model for combining kernel matrices to predict the function of proteins. It extends previous approaches in that it can handle multiple labels which naturally appear in the context of protein function. RESULTS: Explicit modeling of multilabels significantly improves the capability of learning protein function from multiple kernels. The performance and the interpretability of the inference model are further improved by simultaneously predicting the subcellular localization of proteins and by combining pairwise classifiers to consistent class membership estimates. CONCLUSION: For the purpose of functional prediction of proteins, multilabels provide valuable information that should be included adequately in the training process of classifiers. Learning of functional categories gains from co-prediction of subcellular localization. Pairwise separation rules allow very detailed insights into the relevance of different measurements like sequence, structure, interaction data, or expression data. A preliminary version of the software can be downloaded from .
format Text
id pubmed-1892070
institution National Center for Biotechnology Information
language English
publishDate 2007
publisher BioMed Central
record_format MEDLINE/PubMed
spelling pubmed-18920702007-06-15 Improved functional prediction of proteins by learning kernel combinations in multilabel settings Roth, Volker Fischer, Bernd BMC Bioinformatics Research BACKGROUND: We develop a probabilistic model for combining kernel matrices to predict the function of proteins. It extends previous approaches in that it can handle multiple labels which naturally appear in the context of protein function. RESULTS: Explicit modeling of multilabels significantly improves the capability of learning protein function from multiple kernels. The performance and the interpretability of the inference model are further improved by simultaneously predicting the subcellular localization of proteins and by combining pairwise classifiers to consistent class membership estimates. CONCLUSION: For the purpose of functional prediction of proteins, multilabels provide valuable information that should be included adequately in the training process of classifiers. Learning of functional categories gains from co-prediction of subcellular localization. Pairwise separation rules allow very detailed insights into the relevance of different measurements like sequence, structure, interaction data, or expression data. A preliminary version of the software can be downloaded from . BioMed Central 2007-05-03 /pmc/articles/PMC1892070/ /pubmed/17493250 http://dx.doi.org/10.1186/1471-2105-8-S2-S12 Text en Copyright © 2007 Roth and Fischer; licensee BioMed Central Ltd. http://creativecommons.org/licenses/by/2.0 This is an open access article distributed under the terms of the Creative Commons Attribution License ( (http://creativecommons.org/licenses/by/2.0) ), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research
Roth, Volker
Fischer, Bernd
Improved functional prediction of proteins by learning kernel combinations in multilabel settings
title Improved functional prediction of proteins by learning kernel combinations in multilabel settings
title_full Improved functional prediction of proteins by learning kernel combinations in multilabel settings
title_fullStr Improved functional prediction of proteins by learning kernel combinations in multilabel settings
title_full_unstemmed Improved functional prediction of proteins by learning kernel combinations in multilabel settings
title_short Improved functional prediction of proteins by learning kernel combinations in multilabel settings
title_sort improved functional prediction of proteins by learning kernel combinations in multilabel settings
topic Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1892070/
https://www.ncbi.nlm.nih.gov/pubmed/17493250
http://dx.doi.org/10.1186/1471-2105-8-S2-S12
work_keys_str_mv AT rothvolker improvedfunctionalpredictionofproteinsbylearningkernelcombinationsinmultilabelsettings
AT fischerbernd improvedfunctionalpredictionofproteinsbylearningkernelcombinationsinmultilabelsettings