AstraZeneca has chosen big data and analytics services provider Sinequa, to index millions of R&D documents for use in a search platform providing “sub-second” answers to research questions.
Sinequa will provide the biotech giant with “a scalable solution to pull out relevant information from unstructured data in many languages,” said Alexandre Bilger, Sinequa CEO.
“Large, multinational biotechs, such as AstraZeneca, can have thousands of people working globally on one topic and need to analyse millions of documents to support their work. R&D intelligence supplied by Sinequa can help organizations identify new connections.”
A Sinequa spokeswoman told Outsourcing-pharma.com the project will capture all information about a topic requested by AstraZeneca researchers, “instantly” ranking specialist professionals and related studies.
Next, “a dashboard is generated, featuring key scientific documents and experts on the given topic,” and an automated system will relay the information back to AstraZeneca.
The response is “sub-second” both for “standard queries but also for any sentence level searches,” she added, making the platform “simple and intuitive for R&D scientists to use.”
Harnessing AstraZeneca’s big data infrastructure will speed the pharmaceutical firm’s drug development, said Sinequa. The company said the project will allow greater collaboration, fewer duplicate studies and opportunities to find new disease indications for existing treatments. “In a few clicks, R&D investments are maximized.”
Sinequa will work with AstraZeneca’s computer infrastructure, with multiple servers across several regions load-balancing traffic surges.
Big data sharing
AstraZeneca, Pfizer, Sanofi and other big pharma companies provided data to a platform launched last week to bring together information from oncology studies. Project Data Sphere, run by the CEO Roundtable on Cancer’s Life Sciences Consortium, pools data sets from Phase III clinical cancer trials and makes them available to researchers.