Posted on November 6th, 2018 by Jabe Wilson in Pharma R&D
The stats on the increasingly high cost (and low success rates) in drug discovery are always jarring. As Phee Waterfield of Binary District Journal reports:
- Bringing a new drug to market is estimated to cost major pharma firms more than $4 billion
- The process can take 10-15 years
- Fewer than 10% actually make it to market
Those are dire numbers. With the deck seemingly stacked against success, pharmaceutical companies are exploring and embracing any technologies that might be able to speed up the drug discovery process, lower costs or help increase the chances of selecting and developing more promising candidates. Machine learning is one such technology, and it’s likely to help with all three of those goals. As a result, it is creating a lot of excitement in the industry, leading to another very interesting stat, courtesy of McKinsey:
- Big data and machine learning in pharma and medicine could soon generate value as high as $100 billion annually
While machines cannot be expected to be smarter or show more ingenuity than scientists, they do have the ability to process large amounts of data at rapid speeds. Being able to use them to process mountains of information, and to automate time-consuming processes that help researchers determine which drugs are most likely to succeed could be transformative.
To find out more about how machine learning can help overcome drug discovery challenges, the potential pitfalls and to learn about the “players” who are advancing machine learning in this arena, read the Binary District Journal article.
R&D Solutions for Pharma & Life Sciences
We’re happy to discuss your needs and show you how Elsevier’s Solution can help.