Machine learning tools that predict DNA formation.
Protein structure prediction is one of the most important goals currently faced in theoretical chemistry and bioinformatics. Understanding the mechanism and pattern of protein structure prediction is highly valued in medical applications. Christopher Kauffman’s research interests are in developing machine learning, statistics, and optimization methods to answer questions raised in biology with a particular emphasis on protein structure problems. More specifically, his recent research has dealt in computational prediction of protein interactions with DNA and small molecules (ligands) and in developing machine learning tools to predict protein structure. Kauffman has a strong commitment to teaching and have enjoyed several previous college teaching experiences, at the University of Minnesota and Concordia University of St. Paul.