Deep learning and machine vision help to identify possible new drug treatments

Recursion Pharmaceuticals has developed a novel drug screening platform that utilizes deep learning and machine vision technologies to efficiently reposition known drugs and shelved pharmaceutical assets to treat rare genetic diseases and other conditions.

Based in Salt Lake City, UT, USA, the 40-person startup company takes advantage of advanced imaging techniques to provide ample datasets.

"Just as patients with certain genetic diseases may have a specific phenotype, cells modeling genetic disease often display specific structural signatures. For many diseases, these phenotypes are accessible via cellular images," according to Recursion Pharmaceuticals. "We use the latest biological tools to build hundreds of unique cellular disease models, imaging tens of thousands of cells per model, and extracting nearly 1,000 structural features from every cell. With this disease-specific cellular "phenoprint" in hand, we can ask whether any drug rescues the diseased phenoprint back to health."

An MIT Technology Review article notes that automated microscopes feed image recognition software that analyzes hundreds of thousands of images each week of human cells modified to model genetic diseases. The software is looking for any indication that one of the more than 2,000 compounds Recursion is testing on sick cells can make them look more like healthy ones.

Utilizing deep learning technology, the proprietary, interactive data visualization software enables the company’s biologists to query and understand the results of phenotypic screens, drug screens, and target discovery screens with immediate access to raw images and underlying data. In-depth analysis, according to the company, enables interrogation of complex biological interactions for drug repurposing, new chemical entity discovery, and target discovery.

"Traditional drug discovery can take more than a decade and billions of dollars per approved compound," said Chris Gibson, co-founder and CEO of Recursion in a press release. "Recursion’s platform can radically increase the scale at which drugs are discovered, saving years of development time and the associated costs."

Recursion has reportedly already identified 15 potential treatments for rare diseases, defined as those afflicting fewer than 200,000 people in the U.S.

To date, the company has received $19 million in investments from funders including Obvious Ventures, the venture capital firm that was co-founded by Twitter co-founder and former CEO Evan Williams.

View more information on Recursion Pharmaceuticals.
View the MIT Technology Review article.

Share your vision-related news by contacting James Carroll, Senior Web Editor, Vision Systems Design

To receive news like this in your inbox, click here.

Join our LinkedIn group | Like us on Facebook | Follow us on Twitter

Learn more: search the Vision Systems Design Buyer's Guide for companies, new products, press releases, and videos