Rare disease-based scientific annotation knowledge graph

Abstract

Rare diseases (RDs) are naturally associated with a low prevalence rate, which raises a big challenge due to there being less data available for supporting preclinical and clinical studies. There has been a vast improvement in our understanding of RD, largely owing to advanced big data analytic approaches in genetics/genomics. Consequently, a large volume of RD-related publications has been accumulated in recent years, which offers opportunities to utilize these publications for accessing the full spectrum of the scientific research and supporting further investigation in RD. In this study, we systematically analyzed, semantically annotated, and scientifically categorized RD-related PubMed articles, and integrated those semantic annotations in a knowledge graph (KG), which is hosted in Neo4j based on a predefined data model. With the successful demonstration of scientific contribution in RD via the case studies performed by exploring this KG, we propose to extend the current effort by expanding more RD-related publications and more other types of resources as a next step.

Integrative rare disease biomedical profile based network supporting drug repurposing or repositioning, a case study of glioblastoma

“…The findings from Bisulli et al [ 72 ] proved the inference introduced for this particular case. In the future study, we will attach relevant references gathered from the previously developed scientific annotation knowledge graph, [ 73 ] to the merged nodes, as scientific evidence enrichment.…”

“…Additionally, during the step of high-influence node identification, we manually searched for scientific evidence to support our findings. In the future study, we will programmatically query the rare disease-based scientific annotation knowledge graph [ 73 ] for evidence collection. In the future study, we will adopt/extend the strategy of network optimization to apply on the datasets with well-defined data models underneath, then we will be able to generate highly condensed graphs by merging nodes/relationships by different concept types.…”

The division of rare diseases research innovation at the national center for advancing translational sciences, NIH: mission, history, and current research activities

“…In addition to supporting GARD, DRDRI staff members also participate in collaborative rare disease informatics research on topics including rare disease epidemiology [6] and artificial intelligence [7] .…”

Integrative Rare Disease Biomedical Profile based Network Supporting Drug Repurposing, a case study of Glioblastoma

“…The ndings from Bisulli et al [72] proved the inference introduced for this particular case. In the future study, we will attach relevant references gathered from the previously developed scienti c annotation knowledge graph, [73] to the merged nodes, as scienti c evidence enrichment.…”

“…Additionally, during the step of high-in uence node identi cation, we manually searched for scienti c evidence to support our ndings. In the future study, we will programmatically query the rare disease-based scienti c annotation knowledge graph [73] for evidence collection. In the future study, we will adopt/extend the strategy of network optimization to apply on the datasets with well-de ned data models underneath, then we will be able to generate highly condensed graphs by merging nodes/relationships by different concept types.…”