Working at the intersection of biology and computing may be the most exciting new spot for technologists at the moment.
That’s the word from Daphne Koller, the founder and chief executive officer of Insitro — the biotech company that’s raised more than $243 million in the two short years since it launched.
Speaking at our virtual TechCrunch Disrupt conference, Koller, a serial entrepreneur who previously co-founded Coursera and briefly served as the chief computing officer for the Alphabet subsidiary focused on human health, Calico, views digital biology as the next big technological revolution.
“Digital biology is an incredible place to be right now,” Koller said in an interview.
It’s certainly been an incredible opportunity for Koller, whose work now spans the development of treatments for potential neurological diseases and a nearer-term research and development effort on hepatitis with Gilead Pharmaceuticals.
Koller’s Insitro takes its name and inspiration from the combination of two different practices in biological research — the in vitro experiments that are done on living samples in labs and the in silico experiments that are done on the computer.
By synthesizing these two disciplines, Koller’s company flips the process of drug discovery on its head, as the company is designed to sift through massive amounts of data to search for patterns in the expression of certain conditions. Once those patterns are determined, the company can examine the pathways or mechanisms associated with that expression to determine targets for potential therapies.
Then Insitro will pursue the development of novel molecules that can be used to intervene and either reverse or stop the progression of an illness by stopping the biological mechanisms associated with it.
“We now have massive amounts of data that is truly relevant to human disease,” Koller said. “Machine learning has given us a bunch of tools to really make sense of data.”
The company can identify new patient segments, new interventions new drugs that may modulate the expression of those conditions. “We view ourselves as being on the first phase of a very long journey using machine learning,” said Koller.
Take the company’s work on hepatitis in conjunction with Gilead. There, Koller and her team were able to take a small, high-quality data set from Gilead’s trials and identify how a disease progressed by looking at the patient data from different points in time. Looking at the progression allowed the company to identify drivers that facilitated the progression of fibrosis that causes tissue damage. Now the company is using those targets as a starting point to find modifiers that could slow down the progression of the disease.
It comes down to using computers to understand the biology, new biotechnology to model that biology in a Petri dish and, from the different models, determine the interventions that will make a difference, Koller said.
“What we’re trying to do is so different and so out of alignment with how these [pharmaceutical] companies do their work,” Koller said. “It’s trying to shift the trajectory of these companies of hundreds or thousands of people and shift the culture to a tech culture that is going to be really a challenge.”
It’s the main reason Koller launched her own company rather than joining a big pharma play, and it’s a classic example of the innovator’s dilemma and the disruptive power of technology laid out in the theories of Clayton Christensen that give the Disrupt conference its name.
“[It’s] the notion of the innovator’s dilemma and coming in with a mindset that says we’re going to do this a completely different way,” said Koller. “The drug discovery effort is becoming increasingly expensive and increasingly prone to failure and if we do this in a different way will it enable us to generate better outcomes.”