Deep learning image recognition enables efficient genome editing in zebrafish by automated injections

Abstract

One of the most popular techniques in zebrafish research is microinjection. This is a rapid and efficient way to genetically manipulate early developing embryos, and to introduce microbes, chemical compounds, nanoparticles or tracers at larval stages. Here we demonstrate the development of a machine learning software that allows for microinjection at a trained target site in zebrafish eggs at unprecedented speed. The software is based on the open-source deep-learning library Inception v3. In a first step, the software distinguishes wells containing embryos at one-cell stage from wells to be skipped with an accuracy of 93%. A second step was developed to pinpoint the injection site. Deep learning allows to predict this location on average within 42 μm to manually annotated sites. Using a Graphics Processing Unit (GPU), both steps together take less than 100 milliseconds. We first tested our system by injecting a morpholino into the middle of the yolk and found that the automated injection efficiency is as efficient as manual injection (~ 80%). Next, we tested both CRISPR/Cas9 and DNA construct injections into the zygote and obtained a comparable efficiency to that of an experienced experimentalist. Combined with a higher throughput, this results in a higher yield. Hence, the automated injection of CRISPR/Cas9 will allow high-throughput applications to knock out and knock in relevant genes to study their mechanisms or pathways of interest in diverse areas of biomedical research.

Spatiotemporal Imaging and Pharmacokinetic of Fluorescent Compounds in Zebrafish Eleuthero-Embryos After Different Routes of Administration

“…Significantly, IY microinjections did not result in a proper intrabody distribution of the compounds. This is somewhat unexpected as the IY exposure route is often used to deliver DNA and morpholino's, and infect (eleuthero-)embryos with viruses, bacterial and cancer cells, especially since the technique is easy to perform [ 17,22,[33][34][35] ]. However, in case of small chemicals, it appears that the molecules can become entrapped in the yolk that represents a dense amphiphilic environment consisting largely of cholesterol (40% of total lipid), phosphatidylcholine (17%), and phospholipo-glycoproteins (i.e., vitellogenins) [ 36 ].…”

“…In this case, PC and IP microinjections represent excellent alternatives. We further demonstrated that the IY exposure route should be avoided and hence care needs to be taken when analyzing results from this type of exposure, even though it has been widely implemented and automated [ 17,22,34 ]. Finally, we also provide a mathematical model to predict the relative uptake of compounds as a function of time which can offer an invaluable input for future translational research and safety assessment applications.…”

A Smart Imaging Workflow for Organ-Specific Screening in a Cystic Kidney Zebrafish Disease Model

“…The limitations of the chosen approach are the requirements for manual microinjection and the positioning of embryos in agarose cavities under a stereomicroscope, which can lead to a significant workload in screening scenarios. Microinjection could be potentially automated using recently demonstrated robotic injection systems, thus further increasing throughput and reducing variability [37,38]. Manual orientation of embryos takes about 15–20 min per 96-well plate; however, it is still an order of magnitude faster than traditional mounting techniques such as embedding in low melting agarose.…”

Automated Classification of Fertilized Zebrafish Embryos

“…The image-processing algorithm is based on neural networks, which were successfully applied in zebrafish research. 6,7 It can be subdivided into two procedures: first, a preprocessing procedure identifies the position of the object (zebrafish embryo), and cropping is performed. Second, a deep learning algorithm that was trained on 1000 annotated images is used for image classification to distinguish between fertilized embryos in 2-to 16-cell stage and unfertilized zebrafish eggs or artifacts.…”