For the pharmaceutical and biotech industries, the Human Genome Project has proved to be a double-edged sword. Where potential drug targets were once hard to find, the industry now has thousands of potential targets. This has left researchers with the challenge of reviewing vast amounts of data in search of the proteins instrumental in human disease.
Despite the fact that the industry has invested heavily in the identification of potential new targets for drug discovery, it remains the case that the majority of new targets are still first identified within the scientific literature. However, the exponential growth in the amount of scientific literature makes this process an increasingly challenging one.
For commercial organisations, there are additional pressures as early recognition of a target opportunity may provide a business advantage and – more significantly – that new information about the target of a late-stage trial may have a huge economic impact.
However, the sheer volume of publications is not the end of the challenges faced by researchers. It is now understood that narrowly focusing on a pharmaceutical target in isolation can lead to problems and that it is necessary to consider the action of drugs and their targets in an overall pathway and systems context.
This expands the scope of literature mining considerably since biological networks are notoriously densely connected and exhibit “small world” properties.
Rare diseases affect around 6-7% of the population in the developed world. While the cost of developing new (or orphan) drugs for this audience can be prohibitively expensive, legislation in the United States (FDA Orphan Drug Act, 1983), Japan, Australia and Europe incentivises their development.
One solution to this dilemma is for pharmaceutical companies to repurpose existing drugs. On the surface, drug repurposing has great potential: the known safety profiles of existing drugs shortens development timelines leading to a significant reduction in an organisation’s cost to market.
However, there’s still a great deal of research to undertake: a time-consuming and resource-intensive task. This is an important factor driving pharmaceuticals companies to focus on automated literature analysis.
Drug repurposing relies on making connections, but this is not a simple task when you’re faced with millions of documents, all with unstructured text. Wouldn’t it be helpful if a computer could recognise key scientific information in unstructured text, such as scientific papers? While the answer to this question is obviously “yes”, one of the main hurdles is getting the computer to do this quickly, whilst being able to process scientific synonyms and ambiguity.
Semantic Analytics: A Systematic, Data-Driven Approach to Drug Repositioning Whitepaper
Get in touch with us to find out how we can transform your data
© SciBite Limited / Registered in England & Wales No. 07778456