Large-Scale Discovery of Disease-Disease and Disease-Gene Associations

• DOI: 10.1038/srep32404
• Publication Date: 2016-08-31T16:36:25Z
• Authors: Djordje Gligorijevic; Jelena Stojanovic; Nemanja Djuric; Vladan Radosavljevic; Mihajlo Grbovic; Rob J. Kulathinal; Zoran Obradovic
• Keywords: Genome-wide Association Study

Abstract Data-driven phenotype analyses on Electronic Health Record (EHR) data have recently drawn benefits across many areas of clinical practice, uncovering new links in the medical sciences that can potentially affect well-being millions patients. In this paper, EHR is used to discover novel relationships between diseases by studying their comorbidities (co-occurrences patients). A embedding model designed extract knowledge from disease learning a large-scale database comprising more than 35 million inpatient cases spanning nearly decade, revealing significant improvements phenotyping over current computational approaches. addition, use proposed methodology extended disease-gene associations including valuable domain genome-wide association studies. To evaluate our approach, its effectiveness compared against held-out set where, again, it revealed very compelling results. For selected diseases, we further identify candidate gene lists for which were not studied previously. Thus, approach provides biomedical researchers with tools filter genes interest, thus, reducing costly lab