Drug safety is, of course, one of the central concerns of any drug development project. Right from the start, project teams want to know whether the target they are interested in has any links to adverse events. Or, when they get to lead series or lead compound, is there any evidence that similar compounds or compound classes have been shown to have side effects. If unexpected adverse events occur in clinical trials, again, project teams turn to literature and other sources to see if they can unearth a reason, mechanism, other evidence for this effect. And of course, post-market, pharmaceutical companies must regularly screen the worldwide scientific literature for potential adverse drug reactions, at least every two weeks.
Finding useful information from public sources can be daunting. There are so many different names for any particular gene target, or compound, or disease process, adverse event, side effect. Comprehensive search means using strings and strings of key words. And of course, what is really needed is evidence that a compound is causing an effect, not treating the disease. So, again, key word search doesn’t work well. And then, there are so many different data sources to search.
NLP-Powered search for scientists and clinicians
At a recent webinar, we demonstrated how iScite, Linguamatics’ new easy-to-use AI-based text analytics tool, enables bench scientists and clinicians to rapidly search three key public domain sources for safety information. With one query, users can search MEDLINE, ClinicalTrials.gov and FDA Drug Labels for drug liability and adverse event data, from research, clinical trials, and regulatory drug listing information. The screenshots below give a flavour of what’s possible.
If you’d like to know more:
iScite's ADR query enables rapid effective retrieval of information from MEDLINE, ClinicalTrials.gov and FDA Drug Labels. In MEDLINE, I2E’s NLP-based text mining looks for specific relations between drugs and mentions of any particular adverse event or disease. In ClinicalTrials.gov, the search pulls out associations from the Serious Adverse Event section of the results tables. And in FDA Drug Labels, the user can filter the results to see mentions of adverse reactions in the Boxed Warning section, Adverse events table, Precautions section, or more. The screenshots below show some of the results for searches for compounds with associations to cardiac toxicity, from ClinicalTrials.gov. The results are normalized and structured, enabling easy visualization of the results, or export to Excel for further analysis.
For all sources, you can click through to the marked-up copy of the document, rapidly accessing the evidence for the assertion. This is a snapshot of the Serious Adverse Event results tables from ClinicalTrials.gov. Using the native ClinicalTrials.gov search, it's very difficult to easily surface these data.
Learn more about drug development safety
