Profppikernel uses an accelerated version of the original profile kernel to train SVM based protein-protein interaction (PPI) prediction models and to predict new PPIs from sequence alone.
DeNovo is a sequence-based negative sampling and machine learning framework that learns from PPIs of different viruses to predict for a novel one, exploiting the shared host proteins.
The PPI-PS method consists of a representation of each protein sequence by a vector of pairwise similarities against large subsequences of amino acids created by a shifting window which passes over concatenated protein training sequences.
::DEVELOPER
Nazar Zaki , Bioinformatics Laboratory, UAE University.
Strike (String Kernel) is a program which classifies protein-protein interaction into “interacting” and “non-interacting” sets based solely on amino acid sequence information. The classification is made by applying the string kernel technique. Two proteins are classified “interacting” if they contain similar subsequences of amino acids.
::DEVELOPER
Nazar Zaki , Bioinformatics Laboratory, UAE University.
ITI project [Interactome-Transcriptome Integration] is a network-based robust classification of transcription profiles in cancer by large scale data integration of protein-protein interaction with DNA microarray data.
PrePPI is a database of predicted and experimentally determined protein-protein interactions (PPI) for yeast and human. Predicted interactions in the database are determined using a Bayesian framework that combines structural, functional, evolutionary and expression information.
PIPs is a database of predicted human protein-protein interactions. The predictions have been made using a na?ve Bayesian classifier to calculate a Score of interaction.