NEEL MADHUKAR: I think my defining moment was when my grandfather passed away from cancer while I was an undergrad and seeing how much there's still left to be done to understand cancer and how to treat patients.
KATIE GAYVERT: The defining moment was when my mom actually developed a rapidly growing brain tumor. They had to treat it with this high-dose burst of radiation. I was taking applied math course, where they actually talked about how they do the optimization to minimize tissue damage. That personal connection really drew me to the medical field.
Hi, I'm Katie Gayvert.
NEEL MADHUKAR: Hi. I'm Neel Madhukar.
KATIE GAYVERT: And we are PhD candidates here at the Weill Cornell Graduate School of Medical Sciences.
NEEL MADHUKAR: Yes! Katie and my's collaboration has been incredibly unique. I almost joke that sometimes we're two people doing one combined PhD.
KATIE GAYVERT: Collaboration is one of the most critical parts about research. When you're working together in a team, it gives you power to do a lot more than you could ever do on your own.
When I first saw the timeline about how long it takes a drug to get approved-- over a decade, and over $1 billion-- it blew my mind. The ultimate goal is to impact the drug-development process and to get the right drugs to the right patients faster. About 20 years ago now, they trained a machine they called Deep Blue, which beat the world champion in chess.
NARRATOR: 256 processors that can examine 200 million possible moves, every second.
NEEL MADHUKAR: Machine learning fundamentally is a relatively simple idea. It's taking a bunch of data, feeding that data into a computer, and telling the computer to learn from it.
KATIE GAYVERT: And today you're seeing self-driving cars. You're seeing Siri on your phone. Machine learning is able to take advantage of the data that's already out there, so we don't have to repeat previous mistakes. But, so far, people haven't really applied this too much in the biomedical field.
NEEL MADHUKAR: We've actually taken drugs that were approved and then later pulled from markets because of severe side effects and run our models on them and shown that, for many of these drugs, we could have actually predicted that side effect before they were even approved
Katie and I were both incredibly honored to be featured on the Forbes 30 under 30 list. And it's been great, being on that list, how the greater community, both pharma and business, was ready and willing to accept these disruptive ideas that Katie and I were proposing in the lab.
KATIE GAYVERT: Neel and I have both been very fortunate to be members of the lab of Dr. Olivier Elemento, who leads a Cancer Systems Biology Lab.
NEEL MADHUKAR: The opportunity to have that constant feedback and constant advisorship from Dr. Elemento, I think, has been crucial to both Katie and I's development.
KATIE GAYVERT: Mhm. Now that I'm graduating, I am going to take on a position as a leader of a new bioinformatics team, trying to bring data-driven approaches to drug discovery.
NEEL MADHUKAR: After graduation, Dr. Elemento and I are actually trying to create a start-up of our own. Which really speaks to how great of a mentor he is. I can't seem to let him go. [LAUGH]
KATIE GAYVERT: I probably won't get the opportunity again to have a life quite like this. Weill Cornell Graduate School of Medical Sciences has been a journey of a lifetime.
We've received your request
You will be notified by email when the transcript and captions are available. The process may take up to 5 business days. Please contact email@example.com if you have any questions about this request.
Neel Madhukar and Katie Gayvert are driven by similar experiences of close family members developing tumors. Now close friends, their award-winning, co-authored studies focus on applying machine learning techniques to predict drug efficacy to maximize benefits for patients.