A Novel Technique of Feature Extraction with Dual Similarity Measures for Protein Sequence Classification

Abstract

In this article, a novel approach for extracting features from protein sequences is proposed. This approach extracts only six features corresponding to each protein sequence. These features are computed by globally considering the probabilities of occurrences of the amino acids in different positions within the superfamily which locally belongs to the six exchange groups. Then, these features are used as an input to the Neural Network formed by Boolean-Like Training Algorithm (BLTA). The BLTA is used to classify the protein sequences obtained from the Protein Information Resource (PIR). To investigate the efficacy of proposed feature extraction approach, the experimentation is performed on two superfamilies, namely Ras and Globin using tenfold cross validation. The highest Classification Accuracy achieved is 100.00±00.00 with Computational Time 170.49±70.87 (s) are remarkably better in comparison to the Classification Accuracies and Computational Time achieved by Mansouri, Bandyopadhyay and Wang. The experimental results demonstrate that the proposed approach extracts the most significant and lesser number of features for each protein sequence due to which it results in considerably potential improvement in Classification Accuracy and takes less Computational Time in comparison with other well-known feature extraction approaches.

AnOxPePred: using deep learning for the prediction of antioxidative properties of peptides

“…This is usually circumvented by aligning the sequences 26 or, in cases where aligning is impossible, with feature extraction, i.e. representing the sequences as a feature vector reflecting their properties [22][23][24][25][27][28][29] . Unfortunately, the resulting feature vectors are inherently biased by the method of feature extraction used 30 .…”

A Generalized Enhanced Quantum Fuzzy Approach for Efficient Data Clustering

“…This implies that how these protein sequences can be represented in terms of feature vectors so that these feature vectors can be applied as an input to the clustering algorithm. For this purpose, we have used the encoding technique presented in [53] that entails the extraction of six features corresponding to each protein sequence.…”

A Novel Scalable Apache Spark Based Feature Extraction Approaches for Huge Protein Sequence and their Clustering Performance Analysis

“…Gupta et al [28] used the general version of Chou [29] pseudo amino acid composition, which is a sixtydimensional numerical feature vector of protein sequences, to develop an alignment-free approach for finding similarity across protein sequences. Bharill et al [30] developed an approach to extract six-dimensional numerical feature vectors from a protein sequence. Likewise, many feature extraction techniques [23,20,24,31,25,30,28] have been introduced in the past, but, none of them is scalable.…”

“…Bharill et al [30] developed an approach to extract six-dimensional numerical feature vectors from a protein sequence. Likewise, many feature extraction techniques [23,20,24,31,25,30,28] have been introduced in the past, but, none of them is scalable. A scalable approach for selecting statistically relevant characteristics from a large sequence is required.…”