Mapping the activation landscape of the MAPK\ERK pathway for variants of unknown significance (VUS) using convolutional neural networks (CNN).

e14615 Background: The MAPK\ERK signaling pathway is a major determinant in the control of diverse cellular processes. This pathway is often up-regulated in human tumors and as such has been an attractive target for the development of anticancer drugs. Mapping the activation landscape of MAPK\ERK is a necessary step in understanding tumor progression and determining the significance of a mutation as well as the relevance of available treatments. Here we present a CNN model, combined with an in-vitro system to investigate the activation landscape of various members of the MAPK\ERK pathway Methods: A novel multi-resolution multi-channel deep neural network was trained to classify images of cells that were transfected with known activating mutated forms of MAPK activating proteins versus WT forms of the proteins. The cells were also transfected with a fluorescently tagged ERK2 expression construct that was one of the three channels imaged by a fluorescent microscopy system. The trained network was subsequently tested on its ability to score images of cells that were transfected with VUS forms of the proteins, or images of cells that were transfected with VUS forms of MAPK proteins and were incubated with the relevant targeted therapies Results: We analyzed 6 proteins activating MAPK\ERK carrying over 100 unique VUS as well as many known oncogenic mutations and determined the pathogenicity score outputted by the network. Analysis of the performance of our model showed that our predictions exceed 95% accuracy and AUC > 0.95. Interestingly, analysis of deeper layers of the network revealed that each gene and mutation exhibit a unique ERK2 activation signal which is considerably different between active and non-active mutations as well as the ability to recognize what mutated gene was transfected, which means that each mutated gene induces different phenological attributes to the cells Conclusions: The use of deep-learning algorithms is providing increasing clinical relevance in several medical fields, most notably pathology. We show that using a cell-based assay combined with high throughput microscopy and CNN based analysis can be used to determine the activity of a wide set of mutations and potentially assist the prediction of targeted therapy outcome. Our results highlight the role of functional interpretation of molecular profiles, enabling more accurate prediction of oncogenic mutations.

Integrin αIIbβ3-Dependent ERK Signaling Is Regulated by Src and Rho Kinases in Both Leu33 and Pro33 Polymorphic Isoforms

Platelet integrin αIIbβ3 possesses a Leu/Pro polymorphism at residue 33 (Leu33/HPA-1a or Pro33/HPA-1b). The Pro33 isoform has been suggested to exhibit prothrombotic features. αIIbβ3-expressing CHO (Chinese hamster ovary) cells on immobilized fibrinogen show activation of the MAP kinase family member ERK2, with an enhanced ERK2 activity in Pro33 cells compared to Leu33 cells. In our present work, we examined how the Leu/Pro polymorphism modulates the ERK2 activation stimulated by 2 differently triggered outside-in signalings. We either treated the CHO cells with Mn2+ or allowed them to adhere to fibrinogen. Moreover, we studied which signaling cascades are involved in ERK2 activation. In contrast to immobilized fibrinogen, Mn2+ did not significantly increase ERK2 activation. However, Mn2+ had a synergistic effect on ERK2 phosphorylation when combined with immobilized fibrinogen. Pro33 cells adherent to fibrinogen exhibited a significantly greater ERK2 activity than Leu33 cells in the presence of Mn2+, which peaked after 10 min of adhesion. Our data showed that Src family and rho kinases play a crucial role in the integrin αIIbβ3-dependent outside-in signaling to ERK2.

Arrestins function in cAR1 GPCR-mediated signaling and cAR1 internalization in the development of Dictyostelium discoideum

Oscillation of chemical signals is a common biological phenomenon, but its regulation is poorly understood. At the aggregation stage of Dictyostelium discoideum development, the chemoattractant cAMP is synthesized and released at 6-min intervals, directing cell migration. Although the G protein–coupled cAMP receptor cAR1 and ERK2 are both implicated in regulating the oscillation, the signaling circuit remains unknown. Here we report that D. discoideum arrestins regulate the frequency of cAMP oscillation and may link cAR1 signaling to oscillatory ERK2 activity. Cells lacking arrestins (adcB−C−) display cAMP oscillations during the aggregation stage that are twice as frequent as for wild- type cells. The adcB−C− cells also have a shorter period of transient ERK2 activity and precociously reactivate ERK2 in response to cAMP stimulation. We show that arrestin domain–containing protein C (AdcC) associates with ERK2 and that activation of cAR1 promotes the transient membrane recruitment of AdcC and interaction with cAR1, indicating that arrestins function in cAR1-controlled periodic ERK2 activation and oscillatory cAMP signaling in the aggregation stage of D. discoideum development. In addition, ligand-induced cAR1 internalization is compromised in adcB−C− cells, suggesting that arrestins are involved in elimination of high-affinity cAR1 receptors from cell surface after the aggregation stage of multicellular development.