Vaccines & Formula 1: The future of BigData

formula 1

There has been numerous articles in the industry regarding Big Data analytics in pharmaceutical R&D – particularly searching for new therapeutic candidates in drug discovery and ‘real world’ post approval vigilance. What has not being reviewed in depth is the use of Big Data in manufacturing solutions. However Pharma, like many sports science, engineering and retail sectors, are now harnessing the knowledge of Formula 1 race teams (Motorsport has truly revolutionized the application of Big Data) to sort Manufacturingthrough thousands of data sources in real time to make on-the-spot decisions (shall we compare winning a race to the finish line of getting a drug to the patient?). For example, since 2011, GlaxoSmithKline has been working with McLaren Applied Technologies, part of its Formula 1 racing organization, and it has claimed the partnership has allowed the company to achieve a 50% production improvement on its Breo Ellipta inhaler plant in the U.K.

Merck & Co recently highlighted issues with yield rates on a vaccine in 2012 (according to InformationWeek) in particular the ‘painful process of analyzing spreadsheets of process histories & other data to solve problems. Essentially this meant the company could only compare a couple of batches at one time, leading to extensive delays. That was until Jerry Megaro, Merck’s director of manufacturing advanced analytics and innovation, integrated the data from vaccine production into the cloud-based Hadoop computer (which was being utilizing by the R&D department).

George Llado, vice president of information technology at Merck explained to InformationWeek “We took all of our data on one vaccine, whether from the labs or the process historians or the environmental systems, and just dropped it into a data lake,” .

Merck was able to do 15 billion calculations and more than 5.5 million batch-to-batch comparisons in 3 months, which allowed the company to discover challenges in the fermentation phase of vaccine production, especially in the final purification step. Megaro commented on this step; “That was pretty powerful, and we came up with a model that demonstrated, quantifiably, that specific fermentation performance traits are very important to yield”.

Reposted from Total

Leave a Reply

Your email address will not be published. Required fields are marked *