TC-ID3: A TESTCODE Based ID3 Classifier for Protein Coding Region Identification

Genes contain their information as specific sequence of nucleotides or bases that are found in DNA molecules. These specific sequences encode instructions on how to make proteins. But the regions of these genes that code for proteins may occupy only a small region of the sequence. Identifying the coding region of the sequence is of vital importance in understanding these genes. This process is automated by using classifiers. In this paper we intend to improve the efficiency of one such classifier, the ID3 decision tree Classifier by using a new attribute, the TESTCODE method.