It has been a privilege to have recently been involved in an exciting new collaboration with Alexander Tropsha and Denis Fourches at the University of North Carolina. The team carried out a cheminformatics analysis of the assertional metadata (AMD) from BioWisdom’s Safety Intelligence Program (SIP), the world’s largest, ever-expanding collection of the known effects of drugs and other chemicals. SIP makes use of BioWisdom’s collection of key concept metadata and Sofia technology, which translates the varied and diverse language used by scientists into a semantically consistent form. The study has provided a fresh new perspective on historic public domain data, bringing together isolated fragments of toxicology information, spanning decades, to provide new insight into drug safety. The resulting article, entitled “Cheminformatics Analysis of Assertions Mined from Literature That Describe Drug-Induced Liver Injury in Different Species”, was published in Chemical Research in Toxicology on December 16, 2009.

Read the rest of this entry »

19^TH January 2010 Cambridge, UK – BioWisdom. a provider of specialist medical metadata and Intelligence Solutions for Healthcare, is pleased to announce the publication of an exciting new paper in Chem. Res. Toxicol. Using metadata derived from BioWisdom’s Safety Intelligence Program, Alex Tropsha and colleagues at the University of North Carolina have applied QSAR modelling and other chemoinformatics techniques to qualitative assertions abstracted from legacy data.

Read the rest of this entry »

I attended a virtual conference last week, hosted by the Drug Safety Executive Council (DSEC), on “Pre-GLP Safety Strategy Session: Key Areas to Address When Planning a Pre-GLP Safety Evaluation”. It was an excellent session, very well run with good moderators, and some excellent speakers.

Read the rest of this entry »

We have recently come across a great online resource called wordle (http://www.wordle.net/) which makes some really appealing text clouds such as that shown above. The above cloud was generated by copying and pasting a page about metadata from Wikipedia, but you can also generate a cloud from website by pasting in a URL.  While it’s fun to use it to make pretty pictures it also provides a very useful summary of what a document or a website is all about.  Give it a try!

The Assertional Metadata (AMD) contained within our Safety Intelligence Program (SIP) represents the largest ever-expanding collection of known effects of chemicals occurring in the different tissue, drugs effects on clinical biomarkers of tissue injury and drug molecular mechanisms.

The System currently contains almost 300,000 individual ’stated’ assertions relating to hepatic, cardiac and other bio-system responses, induced by over 20,000 different compounds in over 20 different species. These assertions distill the observations and conclusions made across more than 19 million documents and database records, including regulatory documents, drug labels, pre-clinical and clinical research journals.

Using our AMD creation platform Sofia (link) and underlying Key Concept Metadata (KCM), we can automatically ‘read’ millions of documents. AMD is presented in a semantically normalised format which dramatically improves the pace and efficiency of analysis. Although millions of documents are read automatically, a task which would take hundreds of highly trained experts many months to achieve, we are able with rigorous quality control by PhD level scientists to deliver over 97% accuracy.

SRS is a proven and scalable data integration platform that is used at over 300 commercial and academic sites delivering genomic data to thousands of users. SRS facilitates the rapid development of applications and algorithms, as well as bioinformatics portals for the Internet or Intranet, making the data efficiently available to entire organizations.

Read the rest of this entry »

Sofia enables the creation of networks of Assertional Metadata (AMD), a form of Intelligent Metadata that summarises the assertions made within unstructured or poorly formatted text and providing a semantically consistent method of navigation.   Sofia liberates intelligence from structured and unstructured data, regardless of its original format.

Read the rest of this entry »

BioWisdom’s OmniViz Analytics Engine harnesses Intelligent Metadata, powerful algorithms and visual summaries to enabled unparalleled insight over complex data. Millions of records  and billions of data points – no problem.

Read the rest of this entry »

BioWisdom’s Key Concept Metadata (KCM) comprises terms, phrases and other representations that humans and computers use to convey information. KCM always represents one or more critical concept categories, and in life sciences these categories include things like biological process, drugs, drug targets and diseases.

Read the rest of this entry »