AI and biotech startup Deepcell said it is collaborating with Gilead Sciences to codevelop a custom AI foundation model for Chinese hamster ovary (CHO) cell morphology.
Under the collaboration, Deepcell will image Gilead’s CHO cell lines on its REM-I imaging platform and train the model to learn morphological structure without manual labeling. The companies plan to publish an open-weight version of the model for the broader research and bioprocessing community.
The model could provide an earlier read on cell line quality by learning directly from single-cell morphology. Financial and other details were not disclosed.
“Beyond scoring cell line quality, the REM-I platform gives teams a window into transfection efficiency, timing, and culture and media conditions, and those same insights may extend to monitoring cells in a bioreactor,” Deepcell CTO Mahyar Salek said in a statement. “We built REM-I to read biology that humans can’t, and a CHO foundation model puts that capability directly into the hands of process development scientists.”
The deal is the second AI and imaging partnership in as many weeks for Gilead, which announced a deal Aug. 14 with Israel’s Nucleai to support antibody-drug conjugate development in cancer therapy.
Nucleai, Gilead Collaborate on Tissue Analysis in Cancer Therapy Development
Nucleai said it is running an ongoing translational research collaboration with Gilead Sciences to support Gilead’s global antibody-drug conjugate (ADC) clinical development programs.