ANALYSIS OF TRANSCRIPTION CONTROL SIGNALS USING ARTIFICIAL NEURAL NETWORKS

The role of the upstream region in controlling the transcription effic iency of a gene is well established. However, the question of predicti ng the extent of gene expressed given the upstream region has so far r emained unresolved. Using an artificial neural network (ANN) to captur e rite internal representation associated with the transcription contr ol signal, the present work predicts the rate of mRNA synthesis based on the pattern contained in the upstream region. Further, the model ha s been used to predict the transcription efficiency, for all possible single base mutations associated with the beta-globin promoter. The si mulation results reveal that apart from the experimental observation t hat a -79G-A and -78G-A mutation increases the efficiency of transcrip tion, mutation in these regions by C or T also causes an increase in t ranscription. Furthermore the simulation results verify that mutations in the conserved region, in general, decrease the transcriptional eff iciency. However, the results also show that certain sequence elements , when mutated, either cause a marginal increase in the level of trans cription or have no effect on transcription levels. The simulation res ults can be used as a guide in designing mutation experiments since an a priori estimate of the possible outcome of a mutation can be obtain ed.