Deepcell, a developer of artificial intelligence-based cell classification and isolation technologies spun out of Stanford University in 2017, said this week it has completed a $20 million Series A financing.

According to Deepcell, the financing will fund its development of its microfluidics technology, enabling the company to continue building a cell morphology “atlas” of more than 400 million cells, and drive a hypothesis-free approach to cell classification and sorting. Deepcell says its “intelligent” microfluidics platform can identify virtually any cell type, at frequencies as low as 1 in a billion.

“Cell morphology is a phenotype with a long history in clinical application that has to date been based on the eyes of a human expert. Deepcell is bringing this phenotype into modern use by adding scale, interpretability, and actionability, thanks to our innovations in AI, microfluidics, and multiomics,” Maddison Masaeli, co-founder and CEO of Deepcell, said in a statement.

Based in Mountain View, CA, Deepcell applies deep learning and big data to classify and isolate individual cells from a sample, combining advances in AI, cell capture, and single-cell analysis to sort cells based on detailed visual features. The company’s platform is designed to maintain cell viability for downstream single-cell analysis, as well as offer access to rare cells and atypical cell states, with the goal of advancing precision medicine research.

“From its early days in my lab to its launch as a startup, the Deepcell technology has offered the exciting potential of characterizing, identifying, and sorting cells without perturbation,” stated Deepcell co-founder Euan Ashley, PhD.

Unlike other approaches, Deepcell’s technology was developed to isolate and collect label-free cells of any type, keeping the cell intact for downstream biological characterization. By targeting whole cells instead of cell-free DNA, Deepcell reasons, its technology can give users access to cell-specific information—such as a view of the cell’s full DNA, RNA, epigenetics, and protein contents—as well as the ability to understand cellular heterogeneity in rich detail.

Deepcell says its AI-based technology has been shown to differentiate among cell types with greater accuracy than traditional cell isolation techniques that rely on antibody staining or similar methods. The company’s AI is designed to identify cells based on infinitesimal morphological differences that may not be visible to the human eye. Through a closed-loop process in which results from each analysis are fed back into the AI to further improve its performance.

“Identifying and isolating cells on a spectrum, all the way down to ultra-rare, harbors unprecedented potential for understanding single-cell biology and for advancing precision medicine,” added Ashley, a professor at Stanford, from which he spun out the company in 2017.

At Stanford, Ashley is Director of both the Stanford Center for Inherited Cardiovascular Disease and the Stanford Clinical Genomics Program; Co-Director of Training in Myocardial Biology and of the Stanford Data Science Initiative; and a professor of Medicine, Genetics, and Biomedical Science, as well as a professor of pathology (by courtesy)

Bow Capital led the Series A round joined by Andreessen Horowitz–which led Bow’s $5 million seed round—as well as 50Y, DCVC, Stanford University, and angel investors that included Jeffrey Dean, a Google Senior Fellow and SVP of Google Research and Google Health.

“By taking cell morphology into the digital age, Deepcell has the potential to revolutionize the field, in a similar way that high-performance computing enabled dramatic advances in genomics and transcriptomics,” added Vijay Pande, General Partner at Andreessen Horowitz.