A novel one-class SVM based negative data sampling method for reconstructing proteome-wide HTLV-human protein interaction networks

Protein-protein interaction (PPI) prediction is generally treated as a problem of binary classification wherein negative data sampling is still an open problem to be addressed. The commonly used random sampling is prone to yield less representative negative data with considerable false negatives. Me...

Descripción completa

Detalles Bibliográficos
Autores principales: Mei, Suyu, Zhu, Hao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group 2015
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5379509/
https://www.ncbi.nlm.nih.gov/pubmed/25620466
http://dx.doi.org/10.1038/srep08034

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5379509/
https://www.ncbi.nlm.nih.gov/pubmed/25620466
http://dx.doi.org/10.1038/srep08034

Ejemplares similares