Culturing Cells Is Surprisingly Tedious. This AI Could Help

Sharing an AI brain between bio labs. Fighting quantum errors. The data center backlash. There’s all that and more in this week’s Prototype. To get it in your inbox, sign up here.

One of the last bastions of hand-made, bespoke craftsmanship is your average biology lab. Around the world, legions of scientists spend tedious hours culturing cell lines and constantly putting them under the microscope to make sure they’re on track. This has some odd side effects–because the process is so hands-on, for example, biologists can sometimes tell at a glance who in the lab grew which cell line. That’s not exactly a formula for easy-to-reproduce results.

Jimmy Sastra wants to get scientists out of the mind-numbing business of growing cells so they can focus on real science. His startup, South San Francisco-based Monomer Bio, is developing an AI-powered platform that enables robots to grow and monitor cell lines instead, with humans in the loop to check their work. Today, the company announced a collaboration with Rorze LifeScience to connect its software to Rorze’s robots around the world, creating a shared “AI brain” to produce cell lines in a more standardized, consistent way across multiple labs simultaneously. “Together we’re making complex cell biology experiments reproducible, so a disease model developed in one lab can be reproduced in another, even on a different continent,” Sastra told me.

That has the potential to free up a lot of time for scientists, Sastra told me. He claimed that in deployments at different customer labs, Monomer’s software was able to bring human verification down from three hours a week to about 10 minutes–for each scientist–which enabled it to grow its cell line production more than six-fold from three cell lines to 20 cell lines per month.

Got questions? Comments? Story tips? TV show recommendations? Email me at: theprototype@forbes.com