Regression based predictor for p53 transactivation

In the current study we introduce a novel in-silico predictor for p53-RE transactivation capability based on a combination of multidimensional scaling and multinomial logistic regression. Experimentally validated known p53-REs along with their transactivation capabilities are used for training. Through cross-validation studies we show that our method outperforms other existing methods. To demonstrate the utility of this method we (a) rank putative p53-REs of target genes and target microRNAs based on the predicted transactivation capability and (b) study the implication of polymorphisms overlapping p53-RE on its transactivation capability.Taking into account both nucleotide interactions and the spacer length of p53-RE, we have created a novel in-silico regression-based transactivation capability predictor for p53-REs and used it to analyze validated and novel p53-REs and to predict the impact of SNPs overlapping these elements.More than half of human cancers have a mutation in the tumor suppressor protein p53 or one of its target genes [1]. The p53 gene has been implicated as a master regulator of genomic stability, cell cycle, apoptosis, and DNA repair [2-5]. p53 regulates its target genes through binding specifically to a palindromic consensus sequence, RRRCWWGYYY-(spacer of 0–13 bp)-RRRCWWGYYY [6]. Since the consensus-binding site for p53 has been established [6], many p53 target genes have been identified experimentally [7-10]. Computational algorithms were also developed to explore the potential p53-response elements (p53-REs) on a genomic scale [10,11]. Currently, there are > 150 experimentally verified p53-RE sequences, with > 1500 high-probability p53 loci [11,12]. One feature of p53, however, confounds the discovery of novel transregulated genes; while some binding sites match the expected consensus sequence quite well, others can be consensus-poor and yet are both necessary, and sufficient, to transactivate a gene [13]. Not surprisingly, nearly all known R