Deepcell, a Silicon Valley life sciences company using artificial intelligence (AI) to identify and isolate single cells based on their morphology, has raised $73 million in Series B funding to continue to progress its unique platform.

Koch Disruptive Technologies led the round, which brings the company’s overall funding to almost $100 million. New investors Bridger Healthcare, Horizons Ventures and Casdin Capital joined the round, as well as previous investors Andreessen Horowitz and Bow Capital as well as Jeff Dean, Head of Google Brain, and Matt Mcllwain, Managing Director at Madrona Venture Group.

Spun out of Stanford University in 2017, Deepcell’s technology combines AI, microfluidics and high-resolution optics that allow isolation and collection of a vast array of single cell types. Since it was founded, the company has developed a cell atlas with over 1 billion images to analyze and sort cells based on visual morphological features.

“The new funding will help us to accelerate our growth, develop our platform, and take a major step toward full commercialization,” said Maddison Masaeli, CEO and Co-founder of Deepcell.

“The support we are receiving highlights the potential of Deepcell’s AI-powered single cell morphology analysis, and enables us to expand the team, transition to late-stage development and accelerate towards introducing our platform to a present and growing list of potential customers.”

Unlike many other cell imaging technologies, Deepcell’s platform can isolate very specific types of cells and keep them intact and label free for future use. This has potential for many areas of medical research including the development of cell and gene therapies.

For example, last month the company announced it will partner with the Translational Genomics Research Institute (TGen), an affiliate of City of Hope, to classify and isolate cells linked with specific diseases such as melanoma, an aggressive form of skin cancer. Although Deepcell’s technology can be used to study any disease, it is focusing on melanoma as a pilot cell-characterisation study and is also studying melanoma in partnership with the University of Zurich in Switzerland.

“Deepcell is advancing the use of computational methods with our deep learning capabilities to help fulfill the promise of precision medicine,” said Mahyar Salek, President, CTO and Co-founder of Deepcell.

“AI can learn to identify cells based on visual differences that are hardly accessible to the human eye and can continually improve, thanks to our capability to sort cells and thereby elicit ground truth at scale. With training on billions of cell images and sorting cells, our AI technology connects morphology to multi-omics, delivering unprecedented access to the exciting world of biology.”