Code-N has recently added three distinguished executives to its advisory board. We’ll be introducing them and their specific takes on Code-N in upcoming blog posts. First up is Christian Fibiger, chief scientific officer at MedGenesis Therapeutix.
We began by asking Chris about what he sees as the primary challenges impeding modern drug discovery and development.
Databases are getting so enormous that it’s beyond the comprehension of any single individual brain or group of brains to properly collect and analyze the data with sufficient depth and breadth to get a complete understanding of what the data say and how to manage them in a meaningful and thoughtful way.
Additionally, the data explosion is forcing scientists to become more and more specialized. Years ago it was possible to track research discoveries in two or three areas at a time. Now, you’re lucky if you can even stay current on a single, focused area. An intelligent data analytic capability that can help scientists mine these rich datasets has a real prospect of generating insights and discoveries that might not have otherwise been seen, let alone capitalized on.
Sounds like an idea that’s firmly in Code-N’s wheelhouse.
Code-N’s technology really has the potential to help pull all of these data together and make them searchable, which in turn could help scientists and their organizations find new biological relationships and ultimately new targets.
What are some of the opportunities you see for a technology like Code-N’s?
When I learned about Code-N’s technology, my first thought was that here was a way to provide access to an untapped trove of data—the information every pharma company has accumulated on failed compounds. All these companies keep their own records on molecules that never made it to market. Sharing these data precompetitively and applying Code-N’s technology to them would help everyone avoid making the same mistakes again and again. Imagine being able to search on an idea and quickly see it’s a non-starter because the drug class is associated with, say, kidney damage. Information like that would make drug discovery smarter and lead the field in more productive directions. And that’s important—because failure rates are so high, even a reduction of 10% would be a huge cost savings for the industry.
What impressed you most about Code-N’s approach?
I liked Code-N’s laser focus on pharma. There are a lot of companies in the big data space, but many of those have focused on other industries. Or, if they are in life science, they are looking at genetics. Code-N’s focus on applying its technology to issues across pharma R&D is what’s needed, and I think they have a good shot since they have generated some early intellectual property specific to working with this type of data.
Why is this technology important?
There is still so much we don’t know. I’m reading a book right now, called Whole: Rethinking the Science of Nutrition, in which a Ph.D. nutritionist from Cornell writes about the application of reductionist scientific techniques to nutrition. He points how hard it is to calculate or understand the specific influence any single molecule may have within our bodies, what with all the various intracellular mechanisms, let alone the intercellular possibilities. It’s just so complex, so intertwined, with so many interactions. Charting all the potential pathways, plotting all of the potential interactions that occur by tweaking one variable or another—it’s beyond the capability of the human brain, but is exactly the type of task suited to computers. If Code-N can find a way to tap into computational power to make these connections more obvious, it will empower humans to explore the natural world with a new vigor that can’t help but lead to insights and innovation.