Multi-label multi-instance transfer learning for simultaneous reconstruction and cross-talk modeling of multiple human signaling pathways

• DOI: 10.1186/s12859-015-0841-4
• Publication Date: 2015-12-30T17:25:03Z
• Authors: Suyu Mei; Hao Zhu
• Keywords: Cell Signaling; Biological pathway

Signaling pathways play important roles in the life processes of cell growth, apoptosis and organism development. At present signal transduction networks are far from complete. As an effective complement to experimental methods, computational modeling is suited rapidly reconstruct signaling at low cost. To our knowledge, existing methods seldom simultaneously exploit more than three into one predictive model for discovery novel components cross-talk between pathways.In this work, we propose a multi-label multi-instance transfer learning method 27 human their cross-talks. Computational results show that proposed demonstrates satisfactory performance rational proteome-wide predictions. Some predicted or pathway targeted proteins have been validated by recent literature. The further linked using experimentally derived PPIs (protein-protein interactions) pathways. Thus map cross-talks via common conveniently inferred provide valuable insights regulatory cooperative relationships Lastly, gene ontology enrichment analysis conducted gain statistical knowledge about reconstructed pathways.Multi-label framework has demonstrated work phenomena protein belongs pathway. results, multiple static biomedical research.