PHENOstruct: Prediction of human phenotype ontology terms using heterogeneous data sources.

摘要: The human phenotype ontology (HPO) was recently developed as a standardized vocabulary for describing the abnormalities associated with diseases. At present, only small fraction of protein coding genes have HPO annotations. But, researchers believe that large portion currently unannotated genes are related to disease phenotypes. Therefore, it is important predict gene-HPO term associations using accurate computational methods. In this work we demonstrate performance advantage structured SVM approach which was shown be highly effective Gene Ontology prediction in comparison to several baseline Furthermore, we highlight collection informative data sources suitable problem predicting associations, including large scale literature mining data.