Computer Science and Engineering, Department of
Date of this Version
12-1-2012
Citation
P. Z. Revesz, C. Assi, Data mining of pancreatic cancer protein databases, In: Advances in Environment, Computational Chemistry and Bioscience (includes Proc. 3rd International Conference on Bioscience and Bioinformatics), S. Oprisan et al., eds., WSEAS Press, pp. 320-325, 2012.
Abstract
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 type of rela- tional database that is also representable as an ARFF file. We developed a method to restructure protein databases so that they become amenable for various data mining and machine learning tools. Our restructuring method en- abled us to apply both decision tree and support vector machine classifiers to a pancreatic protein database. The SVM classifier that used both GO term and PFAM families to characterize proteins gave us over 73% accuracy in predicting whether a protein is involved in pancreatic cancer.
Included in
Databases and Information Systems Commons, Health Information Technology Commons, Oncology Commons, Preventive Medicine Commons
Comments
OPEN ACCESS
Christopher Assi, M.S. in Computer Science, August 2012.