Deep Mapper Graph and its Application to Visualize Plausible Pathways on High-Dimensional Distribution with Small Time-Complexity
Mapper is a topology based data analysis method that extracts topological features from high-dimensional data. The Mapper algorithm requires a filter function that maps the dataset to a Euclidian space and a clustering method, that is performed on the original dataset. This produces a graph which represents the shape of the original data. In this work, we use Mapper to uncover the conformational change of protein structures and we choose the filter function from a parameterized family, based on a deep neural network architecture. By optimizing its parameters with respect to an Energy-loss function derived from a theoretical background, we produce a Mapper graph that unveils the conformational pathways undertaken by the studied protein. Our method tackles conformational pathway detection in a unsupervised manner and therefore greatly reduces the manual and time costs necessary in this task.
PDF Abstract