I spent an informative and enjoyable day at the Findacure Scientific Conference last week, on Rare Disease Day, 29th February 2016. One of the aims of the charity Findacure is to find new cures for rare diseases by repurposing of existing medicines, and Dr Rick Thompson gave an excellent introduction to the problem, with an example of cost of illness modelling for Congenital Hyperinsulinism (CHI). This brought up some of the key challenges for disease modelling and understanding of rare diseases that were repeated again and again across the day:

  • Limited background information e.g. epidemiology and clinical burden of the disease
  • Paucity of knowledge of natural history of disease, and understanding of the disease heterogeneity
  • Little or no data on economic burden of the disease

The talks were varied, ranging from the cost effectiveness of potential drug repurposing programmes, the promise of big data and the ‘omics revolution in identifying suitable candidates for rare diseases, to how collaborations between academia, patient bodies, the pharma industry and rare disease charities are progressing discoveries and developments in certain areas.


Much of the work of researchers builds on previous discoveries, possibly best expressed by Isaac Newton: "If I have seen further, it is by standing on the shoulders of giants". In fact, one definition of research is: "a systematic investigation of sources in order to establish facts and reach new conclusions". To some extent, then, text analytics is a key tool for research, to enable users to see further and to reach new conclusions, by gaining a comprehensive and systematic view of what has already been found.

Clinical research is surely an area where re-use of data is of great scientific value. Using existing data to see further can bring benefits in speeding up drug development, and thereby enhancing patient care. Linguamatics have many customers using I2E to extract existing information from past and on-going clinical trials.

One example of data re-use is shown by Eric Su, Principal Research Scientist at Eli Lilly and Company. Eric uses I2E to extract summary statistics on clinical endpoints for therapeutic areas such as oncology and diabetes, to feed into clinical trial design and competitive environment analysis.


Faster, better, cheaper... how often have we heard these words, in the context of any process along the long path of drug development? There are a myriad of solutions that can help at different stages, enabling more comprehensive target assessment, more rapid lead optimization, and so on.  One of the most expensive parts of the drug development process is clinical trials, with bottlenecks including access to knowledge for site selection, patient populations, principal investigators and key opinion leaders. 

Researchers naturally look to utilize information from current and past trials but manually extracting the relevant information can be resource-intensive, repetitive and, therefore, prone to errors.  Time is money, so reducing costs and errors is critical.  

One of our customers, Merck, use Linguamatics I2E for text analytics over public domain clinical trial data, to improve clinical trial site selection. 

One example of the benefits of text analytics is a site selection project for Merck Experimental Medicine division (EMS). They needed to locate a clinical trial site that would be able to conduct gastric bypass trials with the ability to measure gut peptides before and after surgery. The ideal trial site needed to fit many different characteristics - over a dozen - which would be hugely time-consuming to find using the public domain search interface to ClinicalTrials.gov. 


Animal models are crucial in the understanding of disease, the underlying pathways and the gene targets that play a role. One tool that has shown great value is the knockout mouse model.

The number of KO mouse models has increased massively since the first one in 1989, and mice models have been used successfully in increasing our understanding of diseases as varied as different cancers, diabetes, obesity, blindness, Huntington's disease, aggressive behaviour, and even drug addiction.

Understanding the landscape of KO mouse models for any particular disease area is important, and curated databases (e.g. IMPC or MGI) provide valuable data, but keeping track of new KO mouse models published in the scientific literature is challenging.

Peng Zhang, ‎Senior Staff Scientist at Regeneron Pharmaceuticals, uses Linguamatics I2E to tackle this challenge, and he presented on “Text Mining for Knockout Mice and Phenotypes” earlier this year.

 Diagram showing the set of KO genes involved in autoimmune phenotypes. All hits from both I2E and MGI were manually curated and only 479 unique KO genes were considered “true positive”. 61% true positives only came from I2E query and were not covered by MGI.


Earlier this year, Linguamatics announced our new Connected Data Technology for federated search, and in our newest version, I2E 4.4, we build on this to take another step along the path of better data interoperability. I2E 4.4 introduces a more powerful way to customize your text analytics results using enhanced linkouts in the HTML output, enabling you, for example, to connect your text-mined data to structured content.

Linkouts enable you to link out to, or pull in, additional information relating to the preferred terms (PTs) or concept identifiers (NodeIDs) in your query results. They can be hyperlinks, images or customized output. For example, you can configure linkouts to see information from an external website by clicking on the concept in the text-mined query results. Alternatively, it is possible to enable the interface to display an image in the query results, such as a chemical structure, instead of the preferred term.

This new functionality means you can use linkouts to enhance query results, by enabling you to access additional related information to provide more context or metadata for your search. So, for example, a search for chemicals from ChEBI could link directly from the preferred term in your results to the webpage for that concept on the EBI web site (e.g. Cyclosporine), whilst a gene name in the same result links to EntrezGene (e.g. ICAM1).