Koller is bringing together a cutting edge bio lab, scientists, and AI for faster drug discovery.

Fast Company’s Ruth Reader interviewed Daphne Koller on how Insitro, her startup, was making a difference in drug discovery and development.

Insitro has brought together a high-throughput lab (“beyond the frontier on multiple levels,” according to Koller), top-flight biologists, and machine learning and data science people who are at the cutting edge of their profession. The objective is to accelerate decision-making during drug discovery and to assess faster whether the drug could succeed.

Failing fast

“I think part of the problem biopharma has had is that it’s really difficult to fail fast,” said Koller. “You oftentimes make a 5-10 year investment in something before you realize that it’s not looking so good.”

Unfortunately, by that time, sunk investments are already very substantial.

At Insitro, Koller is building predictive models for use during drug discovery that help answer “fork-in-the-road” questions.

“Do I go down path A or B or C or D? And if you’re lucky, one path in 99 will lead you to success. If you go down the wrong one, then it’s years and tens of millions of dollars in wasted spend,” Koller explains.

According to Koller, machine learning has become more sophisticated and better predictive. On the other hand, bioengineering and cell biology have advanced enough to produce vast amounts of data that can be analyzed by AI and machine learning algorithms.

By combining the high-throughput biology functionality with machine learning, Insitro seeks to “build these predictive models that make better predictions in pharma research and development.”

By Koller’s reasoning, the biggest reason that drugs fail is that they frequently target the wrong target.

Artificial intelligence, however, can help to focus efforts on where they are most likely to succeed because it can “look holistically at many, many different attributes of those cells and say which of them are the most predictive of human clinical outcome.”

A treatment or vaccine for COVID-19

Koller said Insitro was looking at the various vaccine approaches from different companies and “putting them in with a bunch of viral protein and hoping for the best,” – because techniques do not currently exist to predict vaccine efficacy.

New areas of human health

Koller feels that mankind may soon be able to understand the complex genetics of the Central Nervous System diseases.

“The unmet need is huge, and the animal models are particularly untranslatable.”

Recent fundraising

Last month, Insitro raised $143 million to boost its drug development capacities.

Andreessen Horowitz led the round. New investors who participated included T. Rowe Price Associate, BlackRock, Casdin Capital, and CPP Investments. Current investors including ARCH Venture Partners, GV, and Third Rock Ventures also invested.

Insitro has therefore raised $243 million to date.

Related Story:  Daphne Koller Raises $143M For Insitro, Her AI-Bio Startup