LinkedLifeData Inventory Enables Health and Life Sciences Organizations To Fully Control Data Ingestion, Updates
Latest version of Ontotext solution generates deeper insight from data, allowing users to gain a competitive advantage and facilitate innovation.
Note: TDWI's editors carefully choose vendor-issued press releases about new or upgraded products and services. We have edited and/or condensed this release to highlight key features but make no claims as to the accuracy of the vendor's statements.
Ontotext, a leading global provider of enterprise knowledge graph (EKG) technology and semantic database engines, has updated its LinkedLifeData (LLD) Inventory solution, an accelerator for building knowledge graphs. Providing more than 200 semantic-ready biomedical data sets, LinkedLifeData Inventory 1.4 serves as a valuable resource for the scientific community, fostering multidisciplinary exploration and analysis across various facets of life sciences and healthcare research.
Covering data in multiple modalities (such as genomics, proteomics, metabolomics, molecular interactions, and biological processes), LinkedLifeData Inventory allows healthcare and life sciences professionals to access public data sets and ontologies in resource description framework (RDF) format to discover untapped opportunities. The RDF format ensures semantic richness and interoperability, facilitating advanced data integration, semantic querying, and insights generation in alignment with FAIR data principles.
“By identifying relationships in unstructured and structured data, and extending LLD Inventory’s coverage to pharmacological data sets, clinical records, medical information, and a diverse set of scientific publications and patents, organizations can make information-based decisions and significantly increase data quality so they can improve the value for downstream processing,” said Todor Primov, head of life sciences and healthcare solutions at Ontotext. “With the ability to increase data interoperability and reuse legacy knowledge, our customers have seen a decrease in time to market and have generated deeper insights, which has a positive effect on business outcomes.”
LinkedLifeData Inventory decreases data operation costs for delivery and maintenance of customer applications by 50-70% and helps pharma companies discover and repurpose several existing drugs to treat rare and newly identified diseases. Biotech companies leverage LLD Inventory to identify new drug targets and build model data sets; research teams use it to efficiently navigate the huge volume and wide range of data about genes, proteins, compounds, and diseases.
Key enhancements and benefits include:
- Automated data ingestion and updating: Leveraging a dedicated data loader, LLD Inventory ensures the management of data ingestion for all repositories in a single client instance of GraphDB. This latest improvement turns tedious data loading into a more predictable and reliable operation with better workflow management and error handling.
- Entity linking and improved metadata governance: With the ability to serve as a discreet step in natural language processing and extract-transform-load pipelines, LLD Inventory increases data interoperability. It also streamlines the development process for annotation of unstructured content and its normalization to other data sets within the Inventory.
- AI-generated gene-disease link prediction data sets: Based on knowledge graph embedding models such as HAKE, QuatE, and TorusE, the enhanced capabilities empower healthcare teams to innovate and generate deeper insights from data.
- Newly added data sets: Including 19 medical terminologies from UMLS plus 9 independent ones such as Reactome, GWAS, and Hugo LLD Inventory, which can be used to facilitate innovation and gain a competitive advantage.
- Transformation of complex derivative data sets: Allows dynamic mapping between the harmonized data UMLS and source data sets used in the terminology. This approach can be used to significantly increase the recall of identification of biomedical concepts in unstructured text and at the same time allows normalization to a medical code from any of the terminologies included in UMLS.
To learn more, click here.