Backpropagation neural network is trained to identify E. coli promoter
s of all spacing classes (15 to 21). A three module approach is employ
ed wherein the first neural net module predicts the consensus boxes, t
he second module aligns the promoters to a length of 65 bases and the
third neural net module predicts the entire sequence of 65 bases takin
g care of the possible interdependencies between the bases in the prom
oters. The networks were trained with 106 promoters and random sequenc
es which were 60% AT rich and tested on 126 promoters (Bacterial, Muta
nt and Phage promoters). The network was 98% successful in promoter re
cognition and 90.2% successful in non-promoter recognition when tested
on 5000 randomly generated sequences. The network was further trained
with 11 mutated non-promoters and 8 mutated promoters of the p22ant p
romoter. The testing set with 7 mutated promoters and 13 mutated non-p
romoters of p22ant were identified. The network was upgraded using tot
al 1665 data of promoters and non-promoters to identify any promoter s
equences in the gene sequences. The network identified the locations o
f pi, P2 and P3 promoters in the pBR322 plasmid. A search for the star
t codon, Ribosomal Binding Site and the stop codon by a string search
procedure has also been added to find the possible promoters that can
yield protein products. The network was also successfully tested on a
synthetic plasmid pWM528.