Applying neural networks to classify influenza virus antigenic types and hosts

Pavan K. Attaluri, Zhengxin Chen, Guoqing Lu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

Influenza viruses continue to evolve rapidly and are responsible for seasonal epidemics and occasional, but catastrophic, pandemics. We recently demonstrated the use of decision tree and support vector machine methods in classifying pandemic swine flu viral strains with high accuracy. Here, we applied the technique of artificial neural networks for the prediction of important influenza virus antigenic types (H1, H3, and H5) and hosts (Human, Avian, and Swine), which fulfills a critical need for a computational system for influenza surveillance. A comprehensive experiment on different k-mers and different binary encoding types showed classification based upon frequencies of k-mer nucleotide strings performed better than transformed binary data of nucleotides. It has been found for the first time that the accuracy of virus classification varies from host to host and from gene segment to gene segment. In particular, compared to avian and swine viruses, human influenza viruses can be classified with high accuracy, which indicates influenza virus strains might have become well adapted to their human host and hence less variation occurs in human viruses. In addition, the accuracy of host classification varies from genome segment to segment, achieving the highest values when using the HA and NA segments for human host classification. This research, along with our previous studies, shows machine learning techniques play an indispensable role in virus classification.

Original languageEnglish (US)
Title of host publication2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010
Pages279-284
Number of pages6
DOIs
StatePublished - Aug 20 2010
Event2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010 - Montreal, QC, Canada
Duration: May 2 2010May 5 2010

Publication series

Name2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010

Conference

Conference2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010
CountryCanada
CityMontreal, QC
Period5/2/105/5/10

Fingerprint

Viruses
Neural networks
Genes
Nucleotides
Decision trees
Support vector machines
Learning systems

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Biomedical Engineering

Cite this

Attaluri, P. K., Chen, Z., & Lu, G. (2010). Applying neural networks to classify influenza virus antigenic types and hosts. In 2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010 (pp. 279-284). [5510726] (2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010). https://doi.org/10.1109/CIBCB.2010.5510726

Applying neural networks to classify influenza virus antigenic types and hosts. / Attaluri, Pavan K.; Chen, Zhengxin; Lu, Guoqing.

2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010. 2010. p. 279-284 5510726 (2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Attaluri, PK, Chen, Z & Lu, G 2010, Applying neural networks to classify influenza virus antigenic types and hosts. in 2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010., 5510726, 2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010, pp. 279-284, 2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010, Montreal, QC, Canada, 5/2/10. https://doi.org/10.1109/CIBCB.2010.5510726
Attaluri PK, Chen Z, Lu G. Applying neural networks to classify influenza virus antigenic types and hosts. In 2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010. 2010. p. 279-284. 5510726. (2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010). https://doi.org/10.1109/CIBCB.2010.5510726
Attaluri, Pavan K. ; Chen, Zhengxin ; Lu, Guoqing. / Applying neural networks to classify influenza virus antigenic types and hosts. 2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010. 2010. pp. 279-284 (2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010).
@inproceedings{efcabe4a34154cb491cf61b44aff10fe,
title = "Applying neural networks to classify influenza virus antigenic types and hosts",
abstract = "Influenza viruses continue to evolve rapidly and are responsible for seasonal epidemics and occasional, but catastrophic, pandemics. We recently demonstrated the use of decision tree and support vector machine methods in classifying pandemic swine flu viral strains with high accuracy. Here, we applied the technique of artificial neural networks for the prediction of important influenza virus antigenic types (H1, H3, and H5) and hosts (Human, Avian, and Swine), which fulfills a critical need for a computational system for influenza surveillance. A comprehensive experiment on different k-mers and different binary encoding types showed classification based upon frequencies of k-mer nucleotide strings performed better than transformed binary data of nucleotides. It has been found for the first time that the accuracy of virus classification varies from host to host and from gene segment to gene segment. In particular, compared to avian and swine viruses, human influenza viruses can be classified with high accuracy, which indicates influenza virus strains might have become well adapted to their human host and hence less variation occurs in human viruses. In addition, the accuracy of host classification varies from genome segment to segment, achieving the highest values when using the HA and NA segments for human host classification. This research, along with our previous studies, shows machine learning techniques play an indispensable role in virus classification.",
author = "Attaluri, {Pavan K.} and Zhengxin Chen and Guoqing Lu",
year = "2010",
month = "8",
day = "20",
doi = "10.1109/CIBCB.2010.5510726",
language = "English (US)",
isbn = "9781424467662",
series = "2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010",
pages = "279--284",
booktitle = "2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010",

}

TY - GEN

T1 - Applying neural networks to classify influenza virus antigenic types and hosts

AU - Attaluri, Pavan K.

AU - Chen, Zhengxin

AU - Lu, Guoqing

PY - 2010/8/20

Y1 - 2010/8/20

N2 - Influenza viruses continue to evolve rapidly and are responsible for seasonal epidemics and occasional, but catastrophic, pandemics. We recently demonstrated the use of decision tree and support vector machine methods in classifying pandemic swine flu viral strains with high accuracy. Here, we applied the technique of artificial neural networks for the prediction of important influenza virus antigenic types (H1, H3, and H5) and hosts (Human, Avian, and Swine), which fulfills a critical need for a computational system for influenza surveillance. A comprehensive experiment on different k-mers and different binary encoding types showed classification based upon frequencies of k-mer nucleotide strings performed better than transformed binary data of nucleotides. It has been found for the first time that the accuracy of virus classification varies from host to host and from gene segment to gene segment. In particular, compared to avian and swine viruses, human influenza viruses can be classified with high accuracy, which indicates influenza virus strains might have become well adapted to their human host and hence less variation occurs in human viruses. In addition, the accuracy of host classification varies from genome segment to segment, achieving the highest values when using the HA and NA segments for human host classification. This research, along with our previous studies, shows machine learning techniques play an indispensable role in virus classification.

AB - Influenza viruses continue to evolve rapidly and are responsible for seasonal epidemics and occasional, but catastrophic, pandemics. We recently demonstrated the use of decision tree and support vector machine methods in classifying pandemic swine flu viral strains with high accuracy. Here, we applied the technique of artificial neural networks for the prediction of important influenza virus antigenic types (H1, H3, and H5) and hosts (Human, Avian, and Swine), which fulfills a critical need for a computational system for influenza surveillance. A comprehensive experiment on different k-mers and different binary encoding types showed classification based upon frequencies of k-mer nucleotide strings performed better than transformed binary data of nucleotides. It has been found for the first time that the accuracy of virus classification varies from host to host and from gene segment to gene segment. In particular, compared to avian and swine viruses, human influenza viruses can be classified with high accuracy, which indicates influenza virus strains might have become well adapted to their human host and hence less variation occurs in human viruses. In addition, the accuracy of host classification varies from genome segment to segment, achieving the highest values when using the HA and NA segments for human host classification. This research, along with our previous studies, shows machine learning techniques play an indispensable role in virus classification.

UR - http://www.scopus.com/inward/record.url?scp=77955633246&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955633246&partnerID=8YFLogxK

U2 - 10.1109/CIBCB.2010.5510726

DO - 10.1109/CIBCB.2010.5510726

M3 - Conference contribution

AN - SCOPUS:77955633246

SN - 9781424467662

T3 - 2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010

SP - 279

EP - 284

BT - 2010 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2010

ER -