Role of Optimization in RNA-Protein-Binding Prediction

Abstract

RNA-binding proteins (RBPs) play an important role in regulating biological processes, such as gene regulation. Understanding their behaviors, for example, their binding site, can be helpful in understanding RBP-related diseases. Studies have focused on predicting RNA binding by means of machine learning algorithms including deep convolutional neural network models. One of the integral parts of modeling deep learning is achieving optimal hyperparameter tuning and minimizing a loss function using optimization algorithms. In this paper, we investigate the role of optimization in the RBP classification problem using the CLIP-Seq 21 dataset. Three optimization methods are employed on the RNA-protein binding CNN prediction model; namely, grid search, random search, and Bayesian optimizer. The empirical results show an AUC of 94.42%, 93.78%, 93.23% and 92.68% on the ELAVL1C, ELAVL1B, ELAVL1A, and HNRNPC datasets, respectively, and a mean AUC of 85.30 on 24 datasets. This paper's findings provide evidence on the role of optimizers in improving the performance of RNA-protein binding prediction.

Keywords: Bayesian optimizer; RNA-binding proteins; artificial intelligence; bioinformatics; convolutional neural network (CNN); deep learning; grid search; machine learning; optimization; proteins; random search optimizer.

Figure 4

Random optimization vs. Bayesian optimizer.

Figure 1

RBP binding sites as a binary classification problem.

Figure 2

Model architecture.

Figure 3

One-hot encoding.

Figure 5

CNN model architecture.

Figure 6

Model performance comparison prior to and after optimization.

Figure 7

Training vs. testing loss for HNRNPC dataset.

Figure 8

Training vs. Testing loss for C22ORF28 dataset.

Figure 9

Training vs. testing loss for ELAVL1A dataset.

Figure 10

Training vs. testing AUC for AGO2 dataset.