Last week I attended the Cambridge Rare Disease Network (CRDN) 2016 SummitCRDN is a newly established charity working to build a community of people in Cambridge to address the unmet needs in rare disease research and treatment. As last year, there was a great set of speakers, from patient groups, academia, pharma/biotech and vendors.

There has been a step-change in awareness within the pharma industry in the last decade, with an increasing interest and investment in tackling rare diseases. I blogged last year about an interview with Patrick Vallance on this same topic.  He gave several reasons why GSK are interested in rare disease, and these three reasons all were echoed by the CRDN speakers.

The topmost of these reasons was given most clearly by speakers from patient groups, such as Daniel Lewi from the Cure & Action for Tay-Sachs (CATS) Foundation, Karen Harrison from ALD Life, and Emily Kramer-Kolingoff, from Emily’s Entourage. They spoke of the huge impact that rare disease has on individuals and families, and the urgent need for research into new or repurposed treatments for the 1 in 17 people affected by a rare disease.


Linguamatics are delighted once more to sponsor the Findacure Student Voice Essay Competition. Findacure is a UK charity that is building the rare disease community to drive research and develop treatments.   

The winning essay will be published in the Orphanet Journal of Rare Diseases, and the essay topics are:

  1. The impact of a rare disease is much more widespread than its direct symptoms. Discuss how, with particular reference to the patient experience.
  2. How can rare diseases lead the way in medical research and clinical innovation?
  3. How can clinicians and researchers, including students, help to deliver the UK Strategy for Rare Diseases?

One of the big challenges for the development of treatments for rare disease is the need for a thorough understanding of the natural history of each of the 7000 currently known rare diseases. It’s critical to have detailed systematic information on both the genotypic aspect (the genes and mutations), and the phenotypic aspect (pathways involved or disrupted, symptom severities, etc.).


How ready are you for IDMP?

IDMP (IDentification of Medicinal Products) is a set of international standards developed by ISO that will become mandatory in Europe in a phased approach, effective from 2018, and will also be adopted by the FDA and globally over the next few years. As with any new regulatory change, it is valuable to hear about others' experiences and ideally understand and learn from industry best practice. 

Joining the IRISS Forum is the best way of keeping track of IDMP. I joined IRISS this year - it is an excellent source for up-to-date IDMP information and also valuable input from industry experts (such as Andrew Marr, Vada Perkins, and others).

The IRISS (Implementation of Regulatory Information Submission Standards) Forum was created to address the need for a single central forum for open and broad stakeholder discussion of evolving standards, user requirements and practical, global implementation issues of these standards for the mutual benefit of both industry, government agencies and ultimately, public health.

IRISS recently (September 2016) surveyed its members, both pharmaceutical and vendor, across the current state of readiness around IDMP compliance. The companies that took part in the industry survey covered a wide range of organizational sizes, from small companies those with less than 100 EU authorizations to larger ones with more than 5000 (or, less than 10 active ingredients to more than 250). Over 80% of those in the survey had a global reach. 

 


Drug safety and pharmacovigilance are critical aspects of drug development. To understand and monitor potential risks for pharmaceuticals, researchers use many different strategies to uncover evidence of real-world reports of adverse events and patient-reported outcomes.

At the upcoming Linguamatics Text Mining Summit, there are three talks on text mining strategies that improve our understanding of drug-related adverse reactions.

Nina Mian from AstraZeneca will present research on text mining adverse event data both from FDA drug labels (derived from clinical trial data), and also from real world data from PatientsLikeMe. Eric Lewis from GSK will discuss applications of I2E for clinical safety and pharmacovigilance – particularly the problems of identifying potential “new signals” and distinguishing signal from noise. And Stuart Murray from Agios will present workflows for automated identification of potential drug safety events.

These talks, from industry specialists, demonstrate the value of text mining to access and understand the complex world of drug safety and safety signals.


We are always enthused to read about new ways to utilize text mining in the drug discovery and development process, and very much enjoyed the recent paper by Heinemann et al., “Reflection of successful anticancer drug development processes in the literature”. In this study, the researchers develop tools that allow the prediction of the approval or failure of a targeted cancer drug, using models based on information mined from MEDLINE abstracts, along with a slew of other quantitative metadata (e.g. MeSH headings, author counts, fraction of authors with industry affiliation, and more). 

I2E, Linguamatics text mining platform, enabled the researchers to sytematically identify all MEDLINE abstracts containing both the protein target and the specific disease indication of a known set of successfully approved or failed cancer therapeutics; for example, abstracts containing both Her2 and breast cancer, or c-Kit and gastrointestinal stromal tumor (GIST). I2E enables the use of large vocabularies or ontologies of genes and diseases to extract key information, and the researchers used I2E for the rapid retrieval of publications containing any one of the many synonyms of a protein target or indication. 

The researchers found that the set of approved target-indication pairs showed a significantly higher publication count, from 9 years before FDA approval, compared to the eventually-failing pairs. 

Taking the study further, they applied machine learning classifiers and found that the extracted data features could be used to predict success or failure of target-indication pairs, and hence, approved or failed drugs. They conclude: