NEW YORK — Drug discovery and development firm Insitro said Wednesday that it will embed its machine learning-powered search capabilities into Genomics England's phenotypic and genomic database.
Under this new collaboration, South San Francisco, California-based Insitro will apply its machine learning technology to histopathology images and related genomic data in the Genomics England database to create a multimodal representation of clinical data. This will allow users to search for images, biopsies, and cases based on semantic similarity rather than visual similarity, the company said.
Insitro will offer this embedded technology to all Genomics England research partners within the biobank's secure research environment.
"We believe that cutting-edge machine learning methods can go beyond automating predefined prediction tasks and enable clinicians and scientists to derive novel insights that might give rise to new discoveries and treatments," Daphne Koller, founder and CEO of Insitro, said in a statement. "We believe this collaboration can be an exemplar of future collaborations that unlock the power of high-content data towards improved therapeutics and outcomes"
Parker Moss, chief commercial officer at Genomics England, said that this collaboration represents a "key step forward to help our research partners maximize discovery in our research environment and enable our shared vision for the future." This vision includes Genomics England "enabling deeper genomic research through multimodal data, bringing genomic healthcare to all who need it," Moss explained.
In 2020, Insitro formed a five-year collaboration with Bristol Myers Squibb to discover and develop new treatments for amyotrophic lateral sclerosis and frontotemporal dementia. The firm also acquired Haystack Sciences, a developer of machine learning-based drug discovery technologies.
A year ago, the firm raised $400 million in a Series C financing round.