×

Serwis używa ciasteczek ("cookies") i podobnych technologii m.in. do utrzymania sesji i w celach statystycznych. • Ustawienia przeglądarki dotyczące obsługi ciasteczek można swobodnie zmieniać. • Całkowite zablokowanie zapisu ciasteczek na dysku komputera uniemożliwi logowanie się do serwisu. • Więcej informacji: Polityka cookies OPI PIB

×

Regulamin korzystania z serwisu PBN znajduję się pod adresem: Regulamin serwisu

Szukaj wśród:
Dane publikacji

Ensemble learning prediction of protein-protein interactions using proteins functional annotations

Artykuł
Czasopismo : Molecular BioSystems   Tom: 10, Zeszyt: 4, Strony: 820-830
Indrajit Saha [1] , [2] , Julian Zubek [3] , Tomas Klingstrom [4] , Simon Forsberg [5] , Johan Wikander [6] , marcin Kierczak [5] , Ujjwal Maulik [2] , Dariusz Plewczyński [1] , [7] , [8]
  • [1]
  • [2]
    Department of Computer Science and Engineering, Jadavpur University, Kolkata, India
  • [3]
    Institute of Computer Science, Polish Academy of Sciences, Warsaw, Poland
  • [4]
    Department of Animal Breeding and Genetics, SLU Global Bioinformatics Centre, Swedish University of Agricultural Sciences, Uppsala, Sweden
  • [5]
    Department of Clinical Sciences, Computational Genetics Section, Swedish University of Agricultural Sciences, Uppsala, Sweden
  • [6]
    Bioinformatics Program, Faculty of Technology and Natural Sciences, Uppsala University, Sweden
  • [7]
    The Jackson Laboratory for Genomic Medicine, c/o University of Connecticut Health Center, Administrative Services Building – Call Box 901, 263 Farmington Avenue, Farmington, USA
  • [8]
    Yale University, New Haven, USA
2014-01-13 angielski
Link do publicznie dostępnego pełnego tekstu
Identyfikatory
-
Cechy publikacji
-
  • Oryginalny artykuł naukowy
  • Zrecenzowana naukowo
Abstrakty ( angielski )
-
Protein–protein interactions are important for the majority of biological processes. A significant number of computational methods have been developed to predict protein–protein interactions using protein sequence, structural and genomic data. Vast experimental data is publicly available on the Internet, but it is scattered across numerous databases. This fact motivated us to create and evaluate new high-throughput datasets of interacting proteins. We extracted interaction data from DIP, MINT, BioGRID and IntAct databases. Then we constructed descriptive features for machine learning purposes based on data from Gene Ontology and DOMINE. Thereafter, four well-established machine learning methods: Support Vector Machine, Random Forest, Decision Tree and Naïve Bayes, were used on these datasets to build an Ensemble Learning method based on majority voting. In cross-validation experiment, sensitivity exceeded 80% and classification/prediction accuracy reached 90% for the Ensemble Learning method. We extended the experiment to a bigger and more realistic dataset maintaining sensitivity over 70%. These results confirmed that our datasets are suitable for performing PPI prediction and Ensemble Learning method is well suited for this task. Both the processed PPI datasets and the software are available at http://sysbio.icm.edu.pl/indra/EL-PPI/home.html.
Zacytuj dokument
-