Pierce Zhang

Project Portfolio

Bacteria Species Identification using DNA Sequences

Abstract or project description

From a data set containing partial genetic sequences of bacteria, identify the bacterial species. First, we could do exploratory analysis, calculating basic statistical properties such as A/T, C/G content. Second, we could use a basic model such as logistic regression as our initial classifier. Third, we could use either a random forest algorithm or a neural network as a more advanced classifier.