Summary Deep learning is a significant step forward for developing autonomous tasks. One of its branches, computer vision, allows image recognition with high accuracy thanks to the use of convolutional neural networks (CNNs). Our goal was to train a CNN with transmitted light microscopy images to distinguish pluripotent stem cells from early differentiating cells. We induced differentiation of mouse embryonic stem cells to epiblast-like cells and took images at several time points from the initial stimulus. We found that the networks can be trained to recognize undifferentiated cells from differentiating cells with an accuracy higher than 99%. Successful prediction started just 20 min after the onset of differentiation. Furthermore, CNNs displayed great performance in several similar pluripotent stem cell (PSC) settings, including mesoderm differentiation in human induced PSCs. Accurate cellular morphology recognition in a simple microscopic set up may have a significant impact on how cell assays are performed in the near future.

Human embryonic and induced pluripotent stem cells are self-renewing pluripotent stem cells (PSC) that can differentiate into a wide range of specialized cells. Basic fibroblast growth factor is essential for PSC survival, stemness and self-renewal. PI3K/AKT pathway regulates cell viability and apoptosis in many cell types. Although it has been demonstrated that PI3K/AKT activation by bFGF is relevant for PSC stemness maintenance its role on PSC survival remains elusive. In this study we explored the molecular mechanisms involved in the regulation of PSC survival by AKT. We found that inhibition of AKT with three non-structurally related inhibitors (GSK690693, AKT inhibitor VIII and AKT inhibitor IV) decreased cell viability and induced apoptosis. We observed a rapid increase in phosphatidylserine translocation and in the extent of DNA fragmentation after inhibitors addition. Moreover, abrogation of AKT activity led to Caspase-9, Caspase-3, and PARP cleavage. Importantly, we demonstrated by pharmacological inhibition and siRNA knockdown that GSK3β signaling is responsible, at least in part, of the apoptosis triggered by AKT inhibition. Moreover, GSK3β inhibition decreases basal apoptosis rate and promotes PSC proliferation. In conclusion, we demonstrated that AKT activation prevents apoptosis, partly through inhibition of GSK3β, and thus results relevant for PSC survival.

IntroductionMesenchymal stem cells (MSCs) are a promising source of cells for regenerative therapies. Although they can be isolated easily from several tissues, cell expansion is limited since their properties are lost with successive passages. Hence, pluripotent derived MSCs (PD-MSCs) arise as a suitable alternative for MSC production. Nevertheless, at present, PD-MSC derivation protocols are either expensive or not suitable for clinical purposes.MethodsIn this work we present a therapy-grade, inexpensive and simple protocol to derive MSCs from pluripotent stem cells (PSCs) based on the use of platelet lysate (PL) as medium supplement.ResultsWe showed that the PD-MSCPL expressed multiple MSC markers, including CD90, CD73, CD105, CD166, and CD271, among others. These cells also show multilineage differentiation ability and immunomodulatory effects on pre-stimulated lymphocytes. Thorough characterization of these cells showed that a PD-MSCPL resembles an umbilical cord (UC) MSC and differs from a PSC in surface marker and extracellular matrix proteins and integrin expression. Moreover, the OCT-4 promoter is re-methylated with mesenchymal differentiation comparable with the methylation levels of UC-MSCs and fibroblasts. Lastly, the use of PL-supplemented medium generates significantly more MSCs than the use of fetal bovine serum.ConclusionsThis protocol can be used to generate a large amount of PD-MSCs with low cost and is compatible with clinical therapies.Electronic supplementary materialThe online version of this article (doi:10.1186/scrt540) contains supplementary material, which is available to authorized users.