Novel Neural Network Prediction Systems for Human Promoters and Splice Sites

We present a detailed theoretical study of the organization and structure of landmark sequences like promoters and splice junctions in Human DNA. An improved detection of these landmark sequences in genomic DNA is important for exon detection and gene assembly. The function of eukaryotic promoters as initiators for transcription and of splice sites as signals for RNA assembly are among of the most complex processes in molecular biology. Both consist of multiple functional sites in primary DNA that are involved in the polymerase binding and splicing process, respectively. We analyzed the structure of the individual elements within promoters and splice sites using a novel technique that combines neural networks with weight pruning. For a complete promoter site prediction we combine these single predictions for each element using time-delay neural networks (TDNN). TDNNs are appropriate for recognizing promoter elements because they are able to combine multiple features, even those that appear at different relative positions in different sequences. Another advantage is the high selectivity of the TDNN, which is extremely important for promoter prediction systems, that are known to have high amount of false positive classifications. This TDNN predicts most of the annotated promoters in a set of human genes from Genbank (version 86.0). As an example, the TDNN finds the annotated promoter from a 13,865 basepair test gene, HUMTFPB, with a false positive score of 0.05% (6 false positive predictions out of 13,865). On a test set containing 40 known human gene promoters and 1000 random DNA sequences we were able to recognize 50% of the human gene promoters with a false positive classification of 0.8% (correlation coefficient of 0.61). Preliminary tests using these pruned neural networks for splice site predictions show very promising results. In the future we expect to improve performance by combining gene-finding prediction methods with our local signal predictors like the promoter and splice site networks to reduce the false positive predictions.