Predicting Secondary Structure of Protein Using Hybrid of Convolutional Neural Network and Support Vector Machine

Abstract

Protein secondary structure prediction is one of the problems in the Bioinformatics field, which conducted to find the function of proteins. Protein secondary structure prediction is done by classifying each sequence of protein primary structure into the sequence of protein secondary structure, which fall in sequence labelling problems and can be solved with the machine learning. Convolutional Neural Network (CNN) and Support Vector Machine (SVM) are 2 methods that often used to solve classification problems. In this research, we proposed a hybrid of 1-Dimensional CNN and SVM to predict the secondary structure of the protein. In this research, we used a novel hybrid 1-Dimensional CNN and SVM for sequence labelling, specifically to predict the secondary structure of the protein. Our hybrid model managed to outperform previous studies in term of Q3 and Q8 accuracy on CB513 dataset.

Deep learning for protein secondary structure prediction: Pre and post-AlphaFold

“…However, several PSSP studies have attempted to use different algorithms to make secondary structure predictions. Dionysiou et al [122] , Sutanto et al [123] , and Görmez and Aydın [124] used SVM instead of a fully connected layer. Random forest was utilized in several PSSP studies [125] , [126] , [127] , while a Bayesian classifier was used in other studies [119] , [103] , [121] .…”

Protein Secondary Structure Prediction based on CNN and Machine Learning Algorithms

“…Proteins are the building blocks of amino acid sequences [1] [2]. Generally, there are four types of protein structure's which are primary, secondary, tertiary, and quadratic structure.…”

“…Generally, there are four types of protein structure's which are primary, secondary, tertiary, and quadratic structure. Secondary structure are the building blocks of the macromolecule structure [1]. Secondary structures can be divided into two categories-the regular and the irregular secondary structures.…”

“…Convolutional neural network is a form of artificial neural network that is generally used in deep learning for image processing [1] [2]. The hidden units of the CNN are frequently the same dimensions or size as the processed data [1]. The data is convolved by the hidden units, which then stored the information from the data.…”

“…After that, the pooling stage is performed on the existing feature maps, collecting dense information from them [1][9]. Support vector machine is a machine learning algorithm based on a supervised technique that has been used for different types of classification problems [1]. If a model of SVM is given that the sets of labeled schooling data for each section, it will be enabled to classify the new data.…”