A Human Promoter Prediction using MACA-CLONAL Classifier

Abstract

DNA is a very important component in a cell, which is located in nucleus. DNA contains lot of information. For DNA sequence to transcript and form RNA which copies required information, we need a promoter. So promoter plays a vital role in DNA transcription. It is defined as the sequence in region of upstream of transcriptional start site (TSS). If we identify promoter region we can extract information regarding gene expression patterns, cell specificity and development. So we propose a novel fast multiple attractor cellular automata (MACA) with modified Clonal classifier for promoter prediction in eukaryotes. We have used three important features like TATA box, GC box and CAAT box for developing this classifier. We have also used context future 6-mer for predicting same. The proposed classifier is trained and tested with datasets from DBTSS, EID, UTRdb datasets . In training phase of classifier 100% specificity was obtained. In testing phase 84.5% sensitivity and 92.7% specificity was achieved in an average. The time taken to predict promoter region of length 252 in an average is 4 micro seconds.