Sculpting with stem cells: how models of embryo development take shape

ABSTRACT During embryogenesis, organisms acquire their shape given boundary conditions that impose geometrical, mechanical and biochemical constraints. A detailed integrative understanding how these morphogenetic information modules pattern and shape the mammalian embryo is still lacking, mostly owing to the inaccessibility of the embryo in vivo for direct observation and manipulation. These impediments are circumvented by the developmental engineering of embryo-like structures (stembryos) from pluripotent stem cells that are easy to access, track, manipulate and scale. Here, we explain how unlocking distinct levels of embryo-like architecture through controlled modulations of the cellular environment enables the identification of minimal sets of mechanical and biochemical inputs necessary to pattern and shape the mammalian embryo. We detail how this can be complemented with precise measurements and manipulations of tissue biochemistry, mechanics and geometry across spatial and temporal scales to provide insights into the mechanochemical feedback loops governing embryo morphogenesis. Finally, we discuss how, even in the absence of active manipulations, stembryos display intrinsic phenotypic variability that can be leveraged to define the constraints that ensure reproducible morphogenesis in vivo.

Deep learning-based algorithm for predicting the live birth potential of mouse embryos

In assisted reproductive technology (ART), embryos produced by in vitro fertilization (IVF) are graded according to their live birth potential, and high-grade embryos are preferentially transplanted. However, the rate of live birth following clinical ART remains low worldwide, suggesting that grading is inaccurate. One explanation is that grading is classically based on the characteristic shape of embryos at a limited number of developmental stages and does not consider the shape of embryos and intracellular structures, e.g., nuclei, at various stages important for normal embryogenesis. Therefore, here we developed a Normalized Multi-View Attention Network (NVAN) that directly predicts live birth potential from nuclear structural features in live-cell fluorescence images taken of mouse embryos across a wide range of stages. The classification accuracy of our method was 83.87%, which greatly exceeded that of existing machine-learning methods and that of visual inspection by embryo culture specialists. By visualizing the features that contributed most to the prediction of live birth potential, we found that the size and shape of the cell nucleus at the morula stage and at the time of cell division were important for live birth prediction. We anticipate that our method will help ART and developmental engineering as a new basic technology for IVF embryo selection.