Better drugs through AI? Insitro CEO on what machine learning can teach Big Pharma

Article content

WASHINGTON (AP) — Artificial intelligence is changing the way companies do business — helping programmers write code and make customer service calls using chatbots.

Article content

Article content

But the pharmaceutical industry is still waiting to see whether AI can meet its biggest challenge: finding faster and cheaper ways to develop new drugs.

Despite billions spent on research, new drugs still typically take a decade or more to develop.

Article content

Founded in 2018, Insitro is part of a growing field of AI companies that promise to accelerate drug discovery by using machine learning to analyze massive datasets of chemical and biological markers. The South San Francisco-based company has signed deals with drugmakers such as Eli Lilly and Bristol Myers Squibb to help develop drugs for metabolic diseases, neurological conditions and degenerative disorders.

CEO and founder Daphne Koller spoke with the AP about what AI brings to the challenges of drug discovery. The conversation has been edited for length and clarity.

Q: Why is drug development so difficult?

A: I think the problem with drug discovery is that we’re trying to interfere with a system that we understand very little. Many of the successes we’ve seen in the last 15 to 20 years have been when we came to understand enough of the system that we could really design interventions to go with it.

So one of the things we’re trying to do at Insitro is to unravel the complexity behind heterogeneous diseases and identify new intervention approaches that can help, maybe not the entire population, but maybe just a subset of them. In this way we can truly identify the right therapeutic hypothesis for intervention in a given group of patients. I think this is the core of the industry’s lack of success.

Article content

Article content

Q: Companies like Eli Lilly employ thousands of medical scientists and researchers. What can your technology do that these experts can’t?

A: One of the things that has happened in parallel with the AI ​​revolution is the quieter revolution in what I call quantitative biology, which is the ability to measure biological systems with unprecedented precision. You can measure systems such as proteins and cells using increasingly better measurements and techniques.

But if you gave this data to someone, their eyes would light up because there are only so many cells that a person can look at and so many fine details that they can see in these images. People are only limited in their ability to perceive subtle differences.

So you end up with a very reductionist view of a very complex and multifaceted system which is really important for unraveling the differences between patients and revealing where intervention can really make a difference.

Q: How did you become interested in this field?

A: I got my PhD in computer science. But I started getting into machine learning in service of biomedical problems in 1998 or 1999.

Article content

At the time, the problems that machine learning was able to address were, frankly, uninspiring. How inspired are you about classifying spam versus non-spam in a dataset of emails?

I was looking for something richer. My first experience in this field was not because I was particularly interested in becoming a biologist, but because I was looking for more technically challenging questions. Then, when I started researching it, I became interested in biology itself.

Q: Insitro is hiring computer scientists and medical researchers. Was there any cultural clash in getting these two groups to work together?

A: This is probably one of the most important things we have achieved as an organization.

You could take the most advanced and best scientists from either side and put them in the same room together and maybe speaking Thai and Swahili to each other.

When you’re an engineer, you look for the strongest and most consistent patterns that will allow you to predict the majority of cells or individuals. When you are a biologist, you often look for exceptions, because these are the clues that can lead to new discoveries.

So we have put in place a number of cultural and organizational elements to help people deal with each other openly, constructively and with respect.

Article content