engleski

Evaluation of RNA Atom Distance Prediction Models

RNA molecules can fold and form connections with themselves. Since such transformations lead to various possible three-dimensional structures and a diversity of corresponding functions, the knowledge of such structures is of great importance. The RNAFold model predicts a three- dimensional RNA structure using deep learning methods and practices that have shown remarkable progress in related problems. This thesis aims to analyse different model configurations to get an overview and a direction in the first stages of RNAFold’s implementation. By observing multiple performance metrics, the objective is to find a correlation between model architecture and performance, and determine which factors may improve current model implementation.

RNA ; folding ; model ; deep-learning ; analysis

nije evidentirano