Predicting the functions of proteins in Protein-Protein Interaction networks from global information

Hossein Rahmani, Hendrik Blockeel, Andreas Bender
Proceedings of the third International Workshop on Machine Learning in Systems Biology, PMLR 8:82-97, 2009.

Abstract

In this work we present a novel approach to predict the function of proteins in protein-protein interaction (PPI) networks. We classify existing approaches into inductive and transductive approaches, and into local and global approaches. As of yet, among the group of inductive approaches, only local ones have been proposed for protein function prediction. We here introduce a protein description formalism that also includes global information, namely information that locates a protein relative to specific important proteins in the network. We analyze the effect on function prediction accuracy of selecting a different number of important proteins. With around 70 important proteins, even in large graphs, our method makes good and stable predictions. Furthermore, we investigate whether our method also classifies proteins accurately on more detailed function levels. We examined up to five different function levels. The method is benchmarked on four datasets where we found classification performance according to F-measure values indeed improves by 9 percent over the benchmark methods employed.

Cite this Paper

BibTeX
@InProceedings{pmlr-v8-rahmani10a, title = {Predicting the functions of proteins in Protein-Protein Interaction networks from global information}, author = {Rahmani, Hossein and Blockeel, Hendrik and Bender, Andreas}, booktitle = {Proceedings of the third International Workshop on Machine Learning in Systems Biology}, pages = {82--97}, year = {2009}, editor = {Džeroski, Sašo and Guerts, Pierre and Rousu, Juho}, volume = {8}, series = {Proceedings of Machine Learning Research}, address = {Ljubljana, Slovenia}, month = {05--06 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v8/rahmani10a/rahmani10a.pdf}, url = {https://proceedings.mlr.press/v8/rahmani10a.html}, abstract = {In this work we present a novel approach to predict the function of proteins in protein-protein interaction (PPI) networks. We classify existing approaches into inductive and transductive approaches, and into local and global approaches. As of yet, among the group of inductive approaches, only local ones have been proposed for protein function prediction. We here introduce a protein description formalism that also includes global information, namely information that locates a protein relative to specific important proteins in the network. We analyze the effect on function prediction accuracy of selecting a different number of important proteins. With around 70 important proteins, even in large graphs, our method makes good and stable predictions. Furthermore, we investigate whether our method also classifies proteins accurately on more detailed function levels. We examined up to five different function levels. The method is benchmarked on four datasets where we found classification performance according to F-measure values indeed improves by 9 percent over the benchmark methods employed.} }
Endnote
%0 Conference Paper %T Predicting the functions of proteins in Protein-Protein Interaction networks from global information %A Hossein Rahmani %A Hendrik Blockeel %A Andreas Bender %B Proceedings of the third International Workshop on Machine Learning in Systems Biology %C Proceedings of Machine Learning Research %D 2009 %E Sašo Džeroski %E Pierre Guerts %E Juho Rousu %F pmlr-v8-rahmani10a %I PMLR %P 82--97 %U https://proceedings.mlr.press/v8/rahmani10a.html %V 8 %X In this work we present a novel approach to predict the function of proteins in protein-protein interaction (PPI) networks. We classify existing approaches into inductive and transductive approaches, and into local and global approaches. As of yet, among the group of inductive approaches, only local ones have been proposed for protein function prediction. We here introduce a protein description formalism that also includes global information, namely information that locates a protein relative to specific important proteins in the network. We analyze the effect on function prediction accuracy of selecting a different number of important proteins. With around 70 important proteins, even in large graphs, our method makes good and stable predictions. Furthermore, we investigate whether our method also classifies proteins accurately on more detailed function levels. We examined up to five different function levels. The method is benchmarked on four datasets where we found classification performance according to F-measure values indeed improves by 9 percent over the benchmark methods employed.
RIS
TY - CPAPER TI - Predicting the functions of proteins in Protein-Protein Interaction networks from global information AU - Hossein Rahmani AU - Hendrik Blockeel AU - Andreas Bender BT - Proceedings of the third International Workshop on Machine Learning in Systems Biology DA - 2009/03/02 ED - Sašo Džeroski ED - Pierre Guerts ED - Juho Rousu ID - pmlr-v8-rahmani10a PB - PMLR DP - Proceedings of Machine Learning Research VL - 8 SP - 82 EP - 97 L1 - http://proceedings.mlr.press/v8/rahmani10a/rahmani10a.pdf UR - https://proceedings.mlr.press/v8/rahmani10a.html AB - In this work we present a novel approach to predict the function of proteins in protein-protein interaction (PPI) networks. We classify existing approaches into inductive and transductive approaches, and into local and global approaches. As of yet, among the group of inductive approaches, only local ones have been proposed for protein function prediction. We here introduce a protein description formalism that also includes global information, namely information that locates a protein relative to specific important proteins in the network. We analyze the effect on function prediction accuracy of selecting a different number of important proteins. With around 70 important proteins, even in large graphs, our method makes good and stable predictions. Furthermore, we investigate whether our method also classifies proteins accurately on more detailed function levels. We examined up to five different function levels. The method is benchmarked on four datasets where we found classification performance according to F-measure values indeed improves by 9 percent over the benchmark methods employed. ER -
APA
Rahmani, H., Blockeel, H. & Bender, A.. (2009). Predicting the functions of proteins in Protein-Protein Interaction networks from global information. Proceedings of the third International Workshop on Machine Learning in Systems Biology, in Proceedings of Machine Learning Research 8:82-97 Available from https://proceedings.mlr.press/v8/rahmani10a.html.

Related Material