![]() ![]() Automated and unbiased phenotyping based on a multitude of morphological features would overcome this challenge. Thus, the phenotypes caused by changes in the activity of different signaling pathways can be easily confused by even the most experienced developmental biologists. Furthermore, while misregulation of the BMP, Wnt, RA, FGF and PCP signaling pathways leads to specific defects, for example, an enlarged head in the case of Wnt mutants 11, 12, all of these mutants also have malformed shortened tails 13, 14, 15, 16, 17 (Fig. 1b and Supplementary Videos 6 and 7), but the defect in Nodal mutants is caused by an early lack of mesoderm 9, whereas cyclopia in Shh mutants is caused by a late defect in midline patterning 10. For example, both Nodal and Shh mutants have cyclopic eyes (Fig. Loss of activity in any of these pathways causes characteristic patterning defects, which, however, can be difficult to distinguish (Fig. The ligands activating these signaling pathways are dynamically expressed from specific source tissues in the embryo (Fig. Bone morphogenetic protein (BMP), retinoic acid (RA), Wnt, fibroblast growth factor (FGF) and Nodal pattern the germ layers and regulate the formation of the orthogonal anterior–posterior and dorsal–ventral axes Sonic hedgehog (Shh) and planar cell polarity (PCP) signaling, in turn, control the elongation and morphogenesis of the body axis and later shape the formation of tissues 2, 3, 6, 7, 8. Given their important roles in controlling cell identity and behavior, misregulation of signaling pathways in adult tissues can induce the formation of tumors with embryo-like properties, defective cell proliferation and migration 4, 5.ĭuring zebrafish development, seven major signaling pathways orchestrate the formation of the body plan. As part of this work, we freely provide more than 2 million images that were used to train and test EmbryoNet.Įarly development is governed by a handful of signaling pathways that balance tissue growth, differentiation and morphogenesis 1, 2, 3. Furthermore, using automated phenotyping in high-throughput drug screens, we show that EmbryoNet can resolve the mechanism of action of pharmaceutical substances. Our classification algorithms have wide applications in developmental biology and robustly identify signaling defects in evolutionarily distant species. Combined with a model of time-dependent developmental trajectories, this approach identifies and classifies with high precision phenotypic defects caused by loss of function of the seven major signaling pathways relevant for vertebrate development. Here we use a machine learning approach for automated phenotyping to train a deep convolutional neural network, EmbryoNet, to accurately identify zebrafish signaling mutants in an unbiased manner. Classification of phenotypic defects can identify the underlying signaling mechanisms, but this requires expert knowledge and the classification schemes have not been standardized. Evolutionarily conserved signaling pathways are essential for early embryogenesis, and reducing or abolishing their activity leads to characteristic developmental defects. ![]()
0 Comments
Leave a Reply. |