Search

Showing total 2 results
2 results

1. A computational method for prediction of matrix proteins in endogenous retroviruses.

Author

Ma, Yucheng, Liu, Ruiling, Lv, Hongqiang, Han, Jiuqiang, Zhong, Dexing, and Zhang, Xinman

Subjects
HUMAN endogenous retroviruses, ENDOGENOUS retroviruses, CANCER invasiveness, EXTRACELLULAR matrix proteins, RETROVIRUSES, GLYCOPROTEINS
Abstract

Human endogenous retroviruses (HERVs) encode active retroviral proteins, which may be involved in the progression of cancer and other diseases. Matrix protein (MA), in group-specific antigen genes (gag) of retroviruses, is associated with the virus envelope glycoproteins in most mammalian retroviruses and may be involved in virus particle assembly, transport and budding. However, the amount of annotated MAs in ERVs is still at a low level so far. No computational method to predict the exact start and end coordinates of MAs in gags has been proposed yet. In this paper, a computational method to identify MAs in ERVs is proposed. A divide and conquer technique was designed and applied to the conventional prediction model to acquire better results when dealing with gene sequences with various lengths. Initiation sites and termination sites were predicted separately and then combined according to their intervals. Three different algorithms were applied and compared: weighted support vector machine (WSVM), weighted extreme learning machine (WELM) and random forest (RF). G − mean (geometric mean of sensitivity and specificity) values of initiation sites and termination sites under 5-fold cross validation generated by random forest models are 0.9869 and 0.9755 respectively, highest among the algorithms applied. Our prediction models combine RF & WSVM algorithms to achieve the best prediction results. 98.4% of all the collected ERV sequences with complete MAs (125 in total) could be predicted exactly correct by the models. 94,671 HERV sequences from 118 families were scanned by the model, 104 new putative MAs were predicted in human chromosomes. Distributions of the putative MAs and optimizations of model parameters were also analyzed. The usage of our predicting method was also expanded to other retroviruses and satisfying results were acquired. [ABSTRACT FROM AUTHOR]

Published
2017
Full Text
View/download PDF

2. A computational method for prediction of matrix proteins in endogenous retroviruses

Author

Jiuqiang Han, Xinman Zhang, Hongqiang Lv, Ruiling Liu, Dexing Zhong, and Yucheng Ma

Subjects
0301 basic medicine, RNA viruses, Computer science, Endogenous retrovirus, lcsh:Medicine, Pathology and Laboratory Medicine, Machine Learning, Database and Informatics Methods, Mathematical and Statistical Techniques, Medicine and Health Sciences, lcsh:Science, Extreme learning machine, chemistry.chemical_classification, Budding, Multidisciplinary, Applied Mathematics, Simulation and Modeling, Genomics, Medical Microbiology, Viral Pathogens, Physical Sciences, Viruses, Pathogens, Sequence Analysis, Statistics (Mathematics), Algorithms, Research Article, Optimization, Computer and Information Sciences, Bioinformatics, Gene prediction, Computational biology, ENCODE, Research and Analysis Methods, Microbiology, Viral Matrix Proteins, 03 medical and health sciences, Viral envelope, Sequence Motif Analysis, Artificial Intelligence, Support Vector Machines, Retroviruses, Genetics, Animals, Humans, Statistical Methods, Gene Prediction, Gene, Microbial Pathogens, Viral matrix protein, Biology and life sciences, Human endogenous retrovirus, lcsh:R, Endogenous Retroviruses, Organisms, Chromosome, Computational Biology, Genome Analysis, Support vector machine, 030104 developmental biology, chemistry, lcsh:Q, Glycoprotein, Mathematics, Forecasting
Abstract

Human endogenous retroviruses (HERVs) encode active retroviral proteins, which may be involved in the progression of cancer and other diseases. Matrix protein (MA), in group-specific antigen genes (gag) of retroviruses, is associated with the virus envelope glycoproteins in most mammalian retroviruses and may be involved in virus particle assembly, transport and budding. However, the amount of annotated MAs in ERVs is still at a low level so far. No computational method to predict the exact start and end coordinates of MAs in gags has been proposed yet. In this paper, a computational method to identify MAs in ERVs is proposed. A divide and conquer technique was designed and applied to the conventional prediction model to acquire better results when dealing with gene sequences with various lengths. Initiation sites and termination sites were predicted separately and then combined according to their intervals. Three different algorithms were applied and compared: weighted support vector machine (WSVM), weighted extreme learning machine (WELM) and random forest (RF). G - mean (geometric mean of sensitivity and specificity) values of initiation sites and termination sites under 5-fold cross validation generated by random forest models are 0.9869 and 0.9755 respectively, highest among the algorithms applied. Our prediction models combine RF & WSVM algorithms to achieve the best prediction results. 98.4% of all the collected ERV sequences with complete MAs (125 in total) could be predicted exactly correct by the models. 94,671 HERV sequences from 118 families were scanned by the model, 104 new putative MAs were predicted in human chromosomes. Distributions of the putative MAs and optimizations of model parameters were also analyzed. The usage of our predicting method was also expanded to other retroviruses and satisfying results were acquired.

Published
2017