Semantic Knowledge Drives the Search
Integrate All Your Data
Document management systems in life sciences store many types of documents, drug assessments and other research. But organizations are not able to search all the text while navigating across related data sources to get a complete picture. Ontotext Life Sciences organizes all of the important entities referenced in clinical studies, research projects, product descriptions and target patient profiles inside our semantic repository, GraphDB. We link back to the originating documents to ensure you search the content store and semantically enriched facts at the same time.
Discover Relevant Information
Researchers can find relevant studies along with details on how they were designed. The search process is instantaneous without the need to to filter through thousands of unrelated documents. Your current portfolio of clinical trials and research is optimized for search and reuse. Ontotext Life Sciences applies a comprehensive knowledge base of relevant terms extracted from your most important sources to uncover relevant information.
Text Mining and Annotation
With Ontotext Life Sciences, all of the unstructured and semi-structured data distributed across departmental systems can be processed using industry specific text mining. Documents and sections within those documents contain large numbers of entities which need to be extracted, classified and annotated with additional meta data. By classifying these entities your analysts can develop queries that search, key words, concepts and relationships between the facts. We enrich your data with additional knowledge that powers your search and the results.
Entity Recognition and Semantically Enriched Results
Once entities are extracted from your unstructured data, we match them to comprehensive data dictionaries allowing us to annotate the results with new knowledge. Semantic facts are created and stored in GraphDB. Each entity originally identified in your documents is linked to these facts allowing you to maintain a connection to the original unstructured sources of data. The result is consistency as data changes. Synchronization across data sources equates to greater precision in search. “Semantic Recall” delivers contextual results.
Comprehensive Annotation Types
Ontotext Life Sciences supports many annotation types including genes, malignancies, neoplasms, cell types, cell lines, DNA sequences, RNA sequences, sequence variants and more. We use rules to link the entities to a valid Universal Resource Indicator (URI) inside GraphDB. As we recognize entities, we auto-generate a value that combines the originating entity name with the name stored in GraphDB.
Standalone Applications or Integrated Services
Ontotext Life Sciences can be accessed as a standalone application, integrated into a larger solution, accessed as an annotation service or run in a distributed computing architecture using REST for large scale machine information extraction.