Prediction and Analysis of Pseudomonas Aeruginosa Promoters Based on Sequence Features

Although a great deal of research has been undertaken for promoter prediction, many algorithms tend to exhibit unsatisfied specificity. Most of the existing prokaryotic promoter researches are designed for Escherichia coli. Here, we built a predictor based on sequence-based features for identifying promoters in Pseudomonas aeruginosa. The results indicate that our model can recognize the promoter from non-promoters with high precision. The DNA sequence is also the carrier of information transmission, which inspired us to analyze promoter sequence longitudinally by adopting the signal processing method. We combined with an artificial neural network to build a promoter prediction model. The performance of the model was tested by 5-fold cross-validation. The results showed that the method proposed here achieved an area under curve of 90%, suggesting that the powerful ability of this model for promoter recognition in P. aeruginosa.