In order to identify signatures, we filtered for segments which had broad host range and exhibited geographic association. Starting with the set of segments conserved across multiple species, we identified those which were found exclusively in isolates from a single city (Boston, MA or Orange, CA...
According to our simulation results, using transfer learning can improve the accuracy from 33.41% up to 99.98%. In addition, two other classifiers of Support Vector Machine (SVM) and logistic regression have been used. They showed an accuracy of 83.15% and 78.56%, respectively. In another ...