NuMedii Uses AI and Knowledge Graph Solutions to Support Research Activities for Identifying Novel Therapies

NuMedii commissioned Ontotext to build an industry-specific knowledge graph and to create an extensive semantically annotated corpora of scientific literature. The semantic data integration services provided by Ontotext enables the ingestion of more than 20 open and commercial public databases as well as proprietary datasets.

  • Increased efficiency in identifying novel therapies
  • Cut time and resources on research activities
  • Improved user experience

The Goal

NuMedii needed a smart solution for analyzing research literature that would facilitate the identification of new therapies for treating idiopathic pulmonary fibrosis (IPF). The required solution had to be able to leverage both structured (from public and proprietary datasets) and unstructured data (from scientific journals).

In 2017, as part of the project, NuMedii commissioned Ontotext to build an industry-specific knowledge graph with concepts from genomics, proteomics, metabolomics, disease conditions, drug products, scientific literature, and various biomedical ontologies that integrated information from more than 20 open data sets. Ontotext was also tasked to create an extensive semantically annotated corpora of scientific literature covering genes, diseases, compounds, and drugs as well as to find generic relationships between them.

The Challenge

There were various challenges in achieving this goal. Significant issues included:

  • Rapidly growing number of data and sources with genomic, molecular, and other biomedical data describing diseases and medicinal drugs
  • Highly fragmented nature of the data coming from multiple sources
  • Frequent occurrences of semantic redundancy (ambiguity)
  • Time- and effort-consuming aspects of data integration processes as well as maintaining such knowledge on a large scale
  • Efficiently extracting relevant meaning from the acquired knowledge
  • Providing provenance for each underlying fact supporting the scientific conclusions

The Solution: an AI-powered KG to Speed Discovery of New IPF Treatment Therapies

The Semantic data integration services provided by Ontotext enable the ingestion of more than 20 open and commercial public databases as well as proprietary datasets. Ontotext’s proven methodology for semantic data modeling normalizes both data schema and instances to concepts from major ontologies and vocabularies used by the industry sector.

The resulting high-quality expert knowledge graph (7.98 billion triples) is used as a referential model by the text analysis pipelines to identify biomedical concepts and relationships in the unstructured texts coming from scientific journals. The extracted and normalized data is fed back to the knowledge graph, further enriching the structured data sources. The knowledge graph paradigm also allows users to define logical rules that, when applied to data at scale, reate additional value by inferring new facts.

Business Benefits

  • Ingesting proprietary data to use in the larger context of supported public datasets
  • Accessing highly normalized and semantically interlinked data in a custom knowledge graph
  • Discovering knowledge locked in disparate documents and using it to fill gaps in the knowledge graph
  • Identifying patterns and correlations between biomedical concepts
  • Testing new hypotheses facilitated by a dynamically enriched knowledge graph
  • Feeding AI and analytical tools with high-quality data and traceable provenance

Why Choose Ontotext?

Empowered by Ontotext’s semantic data integration services, NuMedii teams find it easier and quicker to analyze research literature in their goals of identifying new therapies for treating IPF. These services increase the company’s efficiency and cut time and resources on research activities.

Do you think this case resembles your particular needs?

New call-to-action

Contact Us Now