Using Machine Learning to Automatically Identify Elemental Ions in X-ray Crystal Structures
Construction of protein structures from X-ray crystallography data is a difficult, time consuming, and error-prone process. With of 90,000 protein structures currently deposited in online data banks, tools to automatically construct, analyze, and fix models is essential for correct scientific analysis. My research is to apply techniques from the machine learning field to identify elementary ions, such as zinc and calcium, in available data. These atoms are often essential to enzyme function, but their identification requires knowledge of esoteric rules, making it great ground for computational automation.
Message to Sponsor
- Major: Molecular and Cell Biology, Computer Science (minor)
- Sponsor: Pergo Fund
- Mentor: Susan Marqusee, Molecular and Cell Biology