“For the past 10 years I have been given a medicine called mildronate by my family doctor and a few days ago after I received the ITF letter I found out that it also has another name of meldonium which I did not know …”
Should’ve gone to SciBite…
There’s been a lot in the news this week about Maria Sharapova’s failed drug test. The above quote in particular caught our attention here at SciBite Towers.
SciBite’s best-in-class named entity recognition software can scan up to 1 million words per second for mentions of genes, diseases, drugs, adverse events, companies and many more key biomedical terms and their associated synonyms.
Most importantly for Maria, this means it doesn’t matter to us whether her emails and documents from the World Anti-Doping Agency included the same drug written as “mildronate” or “meldonium” or even “N-trimethylhydrazine-3-propionate”. We’d find them all!
A quick scan of the news using our SciNav annotator neatly demonstrates how our named entity recognition technology can be applied to identify terms from unstructured text documents.
Entities extracted from the text are displayed in the browser pop up and are linked to additional sources of information through their unique identifiers.
Advantage, Miss Sharapova
Once we have identified all the scientific entities in your text, it opens up a world of information for further research. Just take a look at some of the links that SciNav has discovered for Meldonium:
Articles picked up by SciBite Pharma Intelligence (see above link) highlight a number of research papers that could be used to back up Maria’s comments about other off-label uses for the drug. For example, Shotnikov et. al. (2013) states:
“Meldonium therapy showed positive effects in delaying the progression of dyslipidemia, diminishing insulin resistance, improving blood rheological properties, and suppressing chronic systemic inflammation”
This is how the same article looks in our document browser with all the key concepts highlighted:
One of the key aims of SciBite is to help our customers work with public ontologies in text mining applications. While these ontologies are very valuable resources, they are often built for the purpose of data organisation, not text mining. The reliance on vanilla public ontologies in text-mining will often lead to very poor results.Read
Over the 50 years how we collect and play music has changed dramatically from physical copies on Vinyl through to electronic mp3s. Each new technology often requires a new device and format to play yet it is still essentially just music.Read
Get in touch with us to find out how we can transform your data.
© SciBite Limited / Registered in England & Wales No. 07778456