Linguamatics: The Use of Natural Language Processing to Solve Pharma's Biggest Problems

CIO VendorJohn M. Brimacombe, Executive Chairman
The pharmaceutical industry is experiencing a radical change in the ecosystem. The slowing pace of drug Research and development pipelines and the desire to reduce pipeline attrition is driving requirements for better use of data that enables faster decisions. There’s also increasing emphasis on in-licensing of promising therapies, which requires better tools that can gather external intelligence and identify the best opportunities. Headquartered in Cambridge UK, Linguamatics has developed innovative ways to unlock and connect the knowledge buried within internal and external textual data.

“The macro-environment of an ageing population and pressure on healthcare funding means an increased focus on results-based reimbursement. This has driven increased interest in real world evidence and proper analysis of Electronic Health Records (EHRs) to improve patient outcomes and inform early stage drug research,” explains John M. Brimacombe, Executive Chairman of Linguamatics. Linguamatics provides a platform for mining and connecting data and offers a number of cutting edge solutions based on its core product I2E, which enables powerful query strategies over diverse data at scale.

I2E extracts and connects key knowledge buried in sources such as scientific literature patents, news feeds, proprietary content, electronic health records or clinical trials information. It is a flexible, scalable text mining and analytics platform based on Natural Language Processing (NLP) technology. The NLP based text mining is used by organizations for high value-knowledge discovery, information extraction and decision support. The NLP finds relationships between entities, and its flexibility allows any query to be run over any textual data. It’s able to extract high quality answers in a structured form in real time, even when mining millions of documents. It allows the use of ontologies to identify biomedical entities, rather than just keywords, and dramatically increases the speed to insight leading to better informed strategic decisions. Lastly, I2E has the ability to identify and extract other types of entities such as numerical data or chemicals.
The company also offers a number of solutions based on the I2E core platform. I2E’s semantic enrichment capability integrates with enterprise search tools to provide a much richer and more valuable search experience for the end user. “All this is backed by professional services delivered by a highly skilled team with expertise in NLP and biomedical informatics,”adds Brimacombe.

Linguamatics works with companies in Pharma, Biotech and other industries. The company’s growing list of customers includes 17 of the top 20 pharmaceutical companies, healthcare organizations and the FDA in diverse application areas such as identifying potential therapeutic targets, drug repurposing, patent analysis, competitive intelligence, mining electronic health records and mining social media such as twitter. In an interesting case study involving a pharmaceutical company, 12E’s automated text mining was used to extract and synthesize high value information found only in the unstructured text regions of clinical trial reports. I2E enabled information scientists to ask precise questions of the reports, delivering insights to clinical decision makers at a faster rate, including information that would have been missed otherwise. Using visualizers such as Spotfire, business intelligence analytics software, results were tailored to the clinical team’s needs; including Excel tables, network graphs and integration with other third party tools.

Moving forward, the company is continuing to invest in its core NLP technology and in enterprise and cloud architectures to enable customers to extract and connect diverse data from different silos. “We are also building focused, application-specific portals on top of our web services API,” concludes Brimacombe.

I2E extracts and connects key knowledge buried in sources such as scientific literature patents, news feeds,proprietary content, electronic health records or clinical trials information


Cambridge, UK

John M. Brimacombe, Executive Chairman

A company focused on innovative NLP based text mining for knowledge discovery and decision support