Date of this Version
Christopher Assi, Data Mining of Protein Databases, M.S. Thesis, University of Nebraska-Lincoln, August 2012.
Data mining of protein databases poses special challenges because many protein databases are non-relational whereas most data mining and machine learning algorithms assume the input data to be a relational database. Protein databases are non-relational mainly because they often contain set data types. We developed new data mining algorithms that can restructure non-relational protein databases so that they become relational and amenable for various data mining and machine learning tools. We applied the new restructuring algorithms to a pancreatic protein database. After the restructuring, we also applied two classification methods, such as decision tree and SVM classifiers and compared their accuracy in predicting whether particular pancreatic proteins are involved in pancreatic cancer. From our prediction the SVM gave us not only the highest accuracy, about 73%, but it also gave the most consistency among the GO terms and PFAM family proteins.
Adviser: Peter Revesz