Machine vision guided robot for fully automated embryonic microinjection

Microinjection is a widely used technique used in basic research and clinical settings for transgenesis, mutagenesis, cell labeling, cryopreservation, and in vitro fertilization. Microinjection is however a highly specialized and labor-intensive procedure. Here we constructed a computer vision guided robot that fully automates the process of microinjection in fruit fly (Drosophila melanogaster) and Zebrafish (Danip rerio) embyros. The robot uses machine learning models trained to detect individual embryos on agar plates and serially performs microinjection at specific locations in each detected embryo without any human intervention. We used three such robots operated by expert and naive users to automatically microinject Drosophila melanogaster (fruit fly) and Danio rerio (zebrafish) embryos. We systematically optimized robotic microinjection and validated the use of the robot for transgenesis both species. The automated microinjection robot allowed us to carry out an experiment where we injected thousands of embryos over the course of a few days, resulting in more than 350 unique transgenic lines and enabling a novel measurement of the number of independent integration events per successfully injected embryo. We showed that robotic microinjection of cryoprotective agents in zebrafish embryos significantly improves vitrification rates and survivability of cryopreserved embryos post-thaw as compared to manual microinjection, opening the tantalizing possibility of large-scale cryobanking of aquatic species at an industrial scale. We anticipate that this versatile automated microinjection system can be applied to carry out microinjections in a wide range of other organisms.