Faculty Sponsor
Badri Adhikari
Final Abstract for URS Program
The full extent of the impact of deep learning models on structural biology will depend on their ability to provide novel biological insights. The field of structure prediction, where deep learning has produced miraculously accurate results, is at a critical stage of benefiting from the methods in interpretable deep learning. The exact mechanisms by which advanced computational models learn to interpret protein shapes and functions during their training remain largely unclear. These questions underscore the need for further research, as understanding these mechanisms is crucial for researchers to trust the predictions of these models. However, interpretable machine learning is ripening with several highly promising approaches applied to various problems. This work reviews all the efforts to interpret deep learning methods in protein structure prediction. We also review the standard methods and most recent breakthroughs in interpretable machine learning. Most importantly, we investigate which interpretability methods have already been used and tested and which are promising to explore.
Presentation Type
Visual Presentation
Document Type
Poster
Publication Date
2022
Included in
Artificial Intelligence and Robotics Commons, Nervous System Diseases Commons, Neurology Commons