To ‘rethink drug design,’ AI star Koller eyes machine learning venture

Daphne Koller has been busy.

Just two months since the high profile AI expert exited Google’s anti-aging biotech Calico Labs, where she was chief computing officer, Koller has gathered a group of marquee investors to back a tech upstart — insitro — with plans to develop a machine learning platform equipped with custom-built datasets to create a new and far more efficient approach to drug discovery and development.

AI circles have been buzzing with speculation and queries about what the former Stanford professor planned to do after exiting Calico, where she had been developing computational methods for analyzing biological data sets. She answered at least some of those questions with a blog post late Tuesday that spelled out her commitment to “invest heavily” in creating new datasets that can accelerate the use of machine learning in biopharma.

Koller has some high rollers backing the startup, including some venture groups well known for blockbuster fundraising and a yen for transformational ventures. They are: Arch Venture Partners, Foresite Capital, a16z, GV (formerly Google Ventures) and Third Rock.

Insitro, she says, will “collect and use a range of very large data sets to train ML models that will help address key problems in the drug discovery and development process. To enable the machine learning, we will use high-quality data that has already been collected, but we will also invest heavily in the creation of our own datasets using high throughput experimental approaches, datasets that are designed explicitly with machine learning in mind from the very start. The ML models that are developed will then help guide subsequent experiments, providing a tight, closed loop integration of in silico and in vitro methods (an insitro paradigm).”

According to Koller, the low hanging fruit in drug discovery has been picked. Reaching higher, going for much better drugs, will require “a different approach to drug development.” Spending billions to develop new drugs — and then passing the cost to patients — is not sustainable.

In launching insitro with a group of hyper connected backers, Koller is instantly making herself a top player in a field that has Big Pharma’s rapt attention. Streamlining R&D and improving the odds of success finding high impact therapies are considered keys to longterm profitability. But now the focus is on which outfits can actually deliver.

There will be plenty of people watching to see if Koller and the team she’s now recruiting can perform. And she knows it won’t be easy. She writes:

There is a lot of hype today around machine learning, with hyperbolic promises that it will magically solve all of humankind’s problems (and dire warnings that it will lead to the destruction of humankind). We at insitro don’t expect ML to be the solution to all of the problems in drug development, nor to be the magic bullet that helps find a treatment for every disease. However, we do believe that the time is right to rethink the drug design process using a different and more modern toolkit, in the hope that a new paradigm may help us cure more people, sooner, and at a much lower cost.

I’d queried Koller recently after hearing word about insitro. For now, she tells me in a message, her blog post goes about as deep into this as she wants to go right now. But more is coming.

https://bit.ly/2JMGO4j