Develop a VR environment for the ‘physical’ assembly of neural networks. Users of the tool will grab neural networks in the virtual and connect them to define the architecture, then run backprop and monitor training inside the VR.
Simulate the binding of drugs to targets by identifying the shape and location of regions that may be stabilized through binding of targeted molecules, and correlate with structural changes in the protein active site or lack of drug binding stabilization.
We aim to develop an assay that can differentiate between melanoma cells with high and low metastatic properties. Distinguishing metastatic potential is the ultimate goal, yet a number of secondary quantitative analyses may also be of interest.