Recognition of Transcriptional and Translational Signals

The tasks of transcriptional and translational signal recognition involve the prediction of promoters and sites that function in the initiation and termination of transcription and translation. Bacterial promoter sites, specifically the Escherichia coli RNA polymerase promoter site, are now very well characterized. The main problem is that the two conserved regions of the bacterial promoter, the -10 and -35 regions, are separated from each other by 15 to 21 bases, making the detection of the entire promoter as a single pattern difficult. Eukaryotic promoters are less well characterized than their bacterial equivalents. The major elements are the CCAAT box, GC box, TATA box and cap site. 

The initiation codon, usually an AUG, signals the start of translation, and a termination codon marks the end of the translated region. In the analysis of prokaryotic DNA sequences, the signals include the transcriptional and translational initiation sites, the ribosome-binding site, and the transcriptional and translational termination sites. Due to the interrupted nature of the eukaryotic genes, the signals include the translation initiation sites, the intron/exon boundaries (splice sites), translational termination sites, and the polyadenylation sites. 

Pedersen and Engelbrecht (1995) devised a neural network to analyze E. coli promoters. They predicted the transcriptional start point, measured the information content, and identified new features signals correlated with the start site. They accomplished these tasks by using two different encoding schemes, one with windows of 1 to 51 nucleotides, the other with a 65-nucleotide window containing a 7-nucleotide hole. An interesting idea in the study was to measure the relative information content of the input data by using the ability of the neural network to learn correctly, as evaluated by the maximum test correlation coefficient. 

By selectively changing sequences in E. coli translation initiation region with randomized calliper inputs and observing the corresponding neural network performance, Nair (1997) analyzed the importance of the initiation codon and the Shine-Dalgamo sequence. 

Using 51-nucleotide sequence windows, Nair et al. (1994) devised a neural network to predict the prokaryotic transcription terminator that has no well-defined consensus patterns. In addition to the BIN4 representation (51 x 4 input units), an EIIP coding strategy was used to reflect the physical property (Le., electron-ion interaction potential values) of the nucleotide base (51 units). The latter coding strategy reduced the input layer size and training time but provided similar prediction accuracy. 

---