Quantitative Design of Regulatory Elements Based on High-Precision Strength Prediction Using Artificial Neural Network

Abstract

Accurate and controllable regulatory elements such as promoters and ribosome binding sites (RBSs) are indispensable tools to quantitatively regulate gene expression for rational pathway engineering. Therefore, de novo designing regulatory elements is brought back to the forefront of synthetic biology research. Here we developed a quantitative design method for regulatory elements based on strength prediction using artificial neural network (ANN). One hundred mutated Trc promoter & RBS sequences, which were finely characterized with a strength distribution from 0 to 3.559 (relative to the strength of the original sequence which was defined as 1), were used for model training and test. A precise strength prediction model, NET90_19_576, was finally constructed with high regression correlation coefficients of 0.98 for both model training and test. Sixteen artificial elements were in silico designed using this model. All of them were proved to have good consistency between the measured strength and our desired strength. The functional reliability of the designed elements was validated in two different genetic contexts. The designed parts were successfully utilized to improve the expression of BmK1 peptide toxin and fine-tune deoxy-xylulose phosphate pathway in Escherichia coli. Our results demonstrate that the methodology based on ANN model can de novo and quantitatively design regulatory elements with desired strengths, which are of great importance for synthetic biology applications.

Characterization of regulatory sequences in alternative promoters of hypermethylated genes associated with tumor resistance to cisplatin

“…A more detailed understanding of the functionality of the alternative promoters in cisplatin resistance is likely to have other applications; for example, it may be possible to design novel anticancer drugs that interact with specific promoter sequences, e.g., G-rich sequences which may form DNA G-quadruplexes (40)(41)(42). In addition, future research may make use of novel synthetic biology methods to build molecular models of various components of alternative promoters (43)(44)(45)(46) to overcome drug resistance and enable more effective and personalized cancer therapies.…”

Advancement of Metabolic Engineering Assisted by Synthetic Biology

“…However, since position weight matrix models are highly reliant on experimental data obtained from promoter-strength studies, they are only applicable to well-studied micro-organisms, such as E. coli. Other models have also been developed to predict promoter strengths based on the partial least squares [107] and artificial neural network [108] methods among other methods. Computation models have been used for the de novo design of synthetic promoters to fine-tune the enzyme genes involved in the deoxyxylulose phosphate pathway in E. coli [108].…”

Construction of precise support vector machine based models for predicting promoter strength

“…Several kernel functions including the polynomial function, sigmoid function, and radial basis function (RBF) were tried one-by-one in preliminary experiments, and found that the RBF is most suitable for fitting the data. A mutation library containing 100 promoter sequences and their corresponding strength values [8] was randomly divided into a training set and a test set for training and test of the SVM models, respectively. Different amount of sequences (from 10 to 90) were tried one-by-one to determine the minimum size of training set for reaching the best prediction performance.…”