Find. Extract. Predict.

Boehringer-Ingelheim and OntoChem cooperate

27 February 2020

Boehringer-Ingelheim & OntoChem press release

The German pharma company Boehringer-Ingelheim (BI) and life and material science information company OntoChem from Halle (Saale), Germany, have announced their Collaboration on tasks around the extraction and normalization of knowledge from unstructured text as well as database sources. Boehringer-Ingelheim licenses OntoChem’s text processing pipeline OC|processor together with related ontologies and certain data streams from life science relevant data sources.
“Too much – didn´t read”, that´s what scientists tell us when looking upon the long List of search results from our expert searchers, explains Dr. Karlheinz Spenny, Head of the Scientific Information Center at Boehringer Ingelheim´s Research Site in Germany. Even information Professionals can no longer limit search results to a “readable and digestible amount of information”. No wonder. The output of the global scientific community is exploding. In drug discovery research, project-relevant information is hidden in patents or somewhere in the full-text of articles from scientific journals. “Finding, Extracting and transforming this information into actionable knowledge is our primary goal.” Pharma Companies need state-of-the-art Retrieval systems to cope with the information overflow in life-sciences. To combine external knowledge with internal own research data is key for Big Pharma Companies.
OC|processor allows the processing of both structured and unstructured information from any document, web page, database or text-based data streams. Comprehensive ontologies built from authoritative public sources are used by OC|processor to extract and index the needed data points and their relationships. This is done using industry standard normalized output formats such as RDF/Knowledge Graphs. This enables a FAIR (findable, accessible, interoperable, reusable) treatment of data to allow integration into end user applications and derivative relational or graph databases. A key benefit of OntoChem’s platform is also that it is accessible through a RESTful application programming interface, serving as a backend to complex customizable queries from various personalized Boehringer internal user applications.
“Data integration and normalization has become an exciting field of our activities in the domain of life sciences,” says Dr. Lutz Weber, cofounder of OntoChem. “Instead of manual processing efforts using multiple inputs and data sources in parallel, we are automating data normalization, delivery and integration. This data is channeled into semantic enterprise platforms for clinical data, biomarker knowledge, chemistry and biology data as well as intellectual property.”
Details of the deal have not been disclosed.

About Boehringer Ingelheim
Boehringer Ingelheim with its three business areas human pharmaceuticals, animal health and biopharmaceuticals is one of the top 20 innovative Pharma companies worldwide and family-owned since 1885. Some 50,000 employees create value on diseases for which no satisfactory treatment option exists to date. The company concentrates on developing innovative therapies that can extend or improve patients’ lives. More information about Boehringer Ingelheim can be found on or in our annual report:

About OntoChem
OntoChem GmbH is a German based company, which is specialized in chemo- and bio-IT services. As a data-driven company OntoChem is using AI techniques to answer project specific questions and is supporting scientists to discover knowledge in the Life Sciences eco-system. OntoChem is located in Halle (Saale) and Stuttgart. Having started in 2005, the team has a long history of developing and applying ontologies, software tools and data streams for life and material science customers. More on OntoChem at, e-mail:

Felix Berthelmann