Crystal Sanchez
Pronouns: she/her
Research Mentor(s): Jaie Woodard, Postdoctoral Fellow
Research Mentor School/College/Department: Computational Medicine and Bioinformatics, Michigan Medicine
Presentation Date: Thursday, April 22, 2021
Session: Session 5 (3pm-3:50pm)
Breakout Room: Room 10
Presenter: 2
Abstract
Proteins are responsible for much of the functions and regulation of living organisms and their body systems. Understanding protein function has much to do with protein structure, thus, knowing what form proteins take is very useful. There are millions of different types of proteins, many of which are essential for human survival. Current ways to determine protein structure require knowledge of the genetic DNA sequence, which can later be translated into an amino acid sequence, thus revealing the shape through chemical properties. However, this study aims to create a program that can accurately predict protein structure without knowledge of the amino acid sequence. Instead, cryo-EM density maps are utilized to map the protein structure. The density maps are created utilizing convolutional neural networks (CNN), which are used to predict key atoms. These deep learning techniques are applied to create the program that can accurately predict a protein structure. This research is valuable because other scientists who require knowledge of protein structure could use it, especially if they do not have access to a specific genetic sequence they need. Next steps include perfecting the program such that the predictions reach the threshold for accuracy.
Authors: Crystal Sanchez
Research Method: Computer Programming
