GENIES: Gene network inference engine based on supervised analysis

Masaaki Kotera, Yoshihiro Yamanishi, Yuki Moriya, Minoru Kanehisa, Susumu Goto

Research output: Contribution to journalArticlepeer-review

34 Citations (Scopus)


Gene network inference engine based on supervised analysis (GENIES) is a web server to predict unknown part of gene network from various types of genome-wide data in the framework of supervised network inference. The originality of GENIES lies in the construction of a predictive model using partially known network information and in the integration of heterogeneous data with kernel methods. The GENIES server accepts any 'profiles' of genes or proteins (e.g. gene expression profiles, protein subcellular localization profiles and phylogenetic profiles) or pre-calculated gene-gene similarity matrices (or 'kernels') in the tab-delimited file format. As a training data set to learn a predictive model, the users can choose either known molecular network information in the KEGG PATHWAY database or their own gene network data. The user can also select an algorithm of supervised network inference, choose various parameters in the method, and control the weights of heterogeneous data integration. The server provides the list of newly predicted gene pairs, maps the predicted gene pairs onto the associated pathway diagrams in KEGG PATHWAY and indicates candidate genes for missing enzymes in organism-specific metabolic pathways. GENIES ( is publicly available as one of the genome analysis tools in GenomeNet.

Original languageEnglish
Pages (from-to)W162-W167
JournalNucleic acids research
Issue numberW1
Publication statusPublished - Jul 2012

All Science Journal Classification (ASJC) codes

  • Genetics


Dive into the research topics of 'GENIES: Gene network inference engine based on supervised analysis'. Together they form a unique fingerprint.

Cite this