Proposing a highly accurate protein structural class predictor using segmentation-based features.
Abdollah Dehzangi,Abdollah Dehzangi,Kuldip K. Paliwal,James Lyons,Alok Sharma,Alok Sharma,Abdul Sattar,Abdul Sattar +7 more
TLDR
By proposing segmented distribution and segmented auto covariance feature extraction methods to capture local and global discriminatory information from evolutionary profiles and predicted secondary structure of the proteins, this study is able to enhance the protein structural class prediction performance significantly.Abstract:
Prediction of the structural classes of proteins can provide important information about their functionalities as well as their major tertiary structures. It is also considered as an important step towards protein structure prediction problem. Despite all the efforts have been made so far, finding a fast and accurate computational approach to solve protein structural class prediction problem still remains a challenging problem in bioinformatics and computational biology. In this study we propose segmented distribution and segmented auto covariance feature extraction methods to capture local and global discriminatory information from evolutionary profiles and predicted secondary structure of the proteins. By applying SVM to our extracted features, for the first time we enhance the protein structural class prediction accuracy to over 90% and 85% for two popular low-homology benchmarks that have been widely used in the literature. We report 92.2% and 86.3% prediction accuracies for 25PDB and 1189 benchmarks which are respectively up to 7.9% and 2.8% better than previously reported results for these two benchmarks. By proposing segmented distribution and segmented auto covariance feature extraction methods to capture local and global discriminatory information from evolutionary profiles and predicted secondary structure of the proteins, we are able to enhance the protein structural class prediction performance significantly.read more
Citations
More filters
Journal ArticleDOI
Gram-positive and Gram-negative protein subcellular localization by incorporating evolutionary-based descriptors into Chou׳s general PseAAC
Abdollah Dehzangi,Abdollah Dehzangi,Rhys Heffernan,Alok Sharma,Alok Sharma,James Lyons,Kuldip K. Paliwal,Abdul Sattar,Abdul Sattar +8 more
TL;DR: This study proposes two segmentation based feature extraction methods and shows that by applying a Support Vector Machine (SVM) classifier to the extracted features, they are able to enhance Gram-positive and Gram-negative subcellular localization prediction accuracies by up to 6.4% better than previous studies including the studies that used GO for feature extraction.
Journal ArticleDOI
Predicting protein structural classes for low-similarity sequences by evaluating different features
TL;DR: A powerful method to predict protein structural classes for low-similarity sequences is developed on the basis of a very objective and strict benchmark dataset and will provide an important guide to extract valuable information from protein sequences.
Journal ArticleDOI
Systematic tissue-specific functional annotation of the human genome highlights immune-related DNA elements for late-onset Alzheimer's disease.
Qiongshi Lu,Ryan L Powles,Sarah B. Abdallah,Derek Ou,Qian Wang,Yiming Hu,Yisi Lu,Wei Liu,Boyang Li,Shubhabrata Mukherjee,Paul K. Crane,Hongyu Zhao +11 more
TL;DR: The GenoSkyline-Plus annotations demonstrate that integrated genome annotations at the single tissue level provide a valuable tool for understanding the etiology of complex human diseases.
Journal ArticleDOI
Membrane proteins structures : A review on computational modeling tools
Jose G. Almeida,António J Preto,Panagiotis I. Koukos,Alexandre M. J. J. Bonvin,Irina S. Moreira,Irina S. Moreira +5 more
TL;DR: This review highlights the importance of membrane proteins and how computational methods are capable of overcoming challenges associated with their experimental characterization and focuses on computational techniques to determine the 3D structure of MP and characterize their binding interfaces.
Journal ArticleDOI
PSSM-Suc: Accurately predicting succinylation using position specific scoring matrix into bigram for feature extraction
Abdollah Dehzangi,Yosvany López,Sunil Pranit Lal,Ghazaleh Taherzadeh,Jacob J. Michaelson,Abdul Sattar,Tatsuhiko Tsunoda,Alok Sharma +7 more
TL;DR: A new predictor called PSSM-Suc is proposed which employs evolutionary information of amino acids for predicting succinylated lysine residues using profile bigrams extracted from position specific scoring matrices and showed a significant improvement in performance over state-of-the-art predictors.
References
More filters
Journal ArticleDOI
Prediction of protein structure class by coupling improved genetic algorithm and support vector machine
TL;DR: A novel method for the prediction of protein structure class is presented by coupling the improved genetic algorithm (GA) with the support vector machine (SVM) by applied to the selection of an optimized feature subset and the optimization of SVM parameters.
Journal ArticleDOI
Using support vector machines for prediction of protein structural classes based on discrete wavelet transform
TL;DR: A new method, in which the support vector machine combines with discrete wavelet transform, is developed to predict the protein structural classes, showing that the proposed approach can remarkably improve the success rates, and might become a useful tool for predicting the other attributes of proteins as well.
Journal ArticleDOI
A strategy to select suitable physicochemical attributes of amino acids for protein fold recognition.
Alok Sharma,Alok Sharma,Kuldip K. Paliwal,Abdollah Dehzangi,James Lyons,Seiya Imoto,Satoru Miyano +6 more
TL;DR: The multi-dimensional successive feature selection (MD-SFS) approach to systematically select attributes of the amino acids has been applied successfully and the selected attributes show improved protein fold recognition performance.
Journal ArticleDOI
Prediction of the protein structural class by specific peptide frequencies
TL;DR: A new structural class prediction algorithm is worked out using the most frequent i-peptides (with i=2, 3, 4), which characterize the four structural classes, which achieves the best prediction accuracy.
Journal ArticleDOI
Exploring an alignment free approach for protein classification and structural class prediction.
TL;DR: This work investigates the effectiveness of a strategy based on the CGR approach using a fixed reverse encoding of amino acids into nucleic sequences and its relevance to protein classification into functional families and the prediction of protein structural classes and suggests that the reverse encoding approach could be relevant in both cases.