Non-active Mutations Research Articles

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.

Contribution of the extracellular domain to agonist-induced and constitutive LH receptor activation

Glycoprotein hormone receptors like the LH and FSH receptor are G-protein-coupled receptors characterized by a large N-terminally extracellular domain. While it is well established that the ectodomain is responsible for specific hormone binding, the activation mechanism is still not understood. To investigate the functional role of the ectodomain, we N-terminally deleted various portions of the LH receptor ectodomain. Upon addition of amino acids 1–39 of the V2 vasopressin receptor to the N-termini of the truncated LHRs, these mutants transiently expressed in COS-7 cells revealed cell surface targeting comparable to the wildtype receptor. However, mutant LHRs did not display constitutive cAMP formation, nor revealed activation by hCG. To exclude that this lack to hCG response was due to negligible agonist affinity, single-chain hCG was fused to the wildtype or truncated receptors. While the wildtype LHR fused to hCG exhibited constitutive cAMP formation after transient expression, and could further be stimulated by exogenous hormone, none of the truncated receptors displayed elevated basal activity indicating that hCG does not functionally interact with the heptahelical LHR portion and that the entire intact ectodomain is required for hormone-induced receptor activation. To examine if truncated LHRs are fundamentally misfolded and principally unable to interact with Gs, several naturally occurring activating mutations were introduced into the transmembrane helices of a truncated LHR. While all mutations induced constitutive activity in the wildtype LHR, only one mutation evoked agonist-independent cAMP formation via the truncation mutant. The activity of most non-active mutations could be recovered by N-terminal linking of the TSHR or FSHR ectodomain to the transmembrane helices of the LHR, whereas linking of the hLGR7 ectodomain was ineffective. These data highlight an as yet unappreciated structural role of the LHR ectodomain for the stabilization of a distinct conformation of the heptahelical portion poised for activation by agonist or activating mutations.