NRProF: Neural response based protein function prediction algorithm

Hari Krishna Yalamanchili, Junwen Wang, Quan Wu Xiao

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

Abstract

A large amount of proteomic data is being generated due to the advancements in high-throughput genome sequencing. But the rate of functional annotation of these sequences falls far behind. To fill the gap between the number of sequences and their annotations, fast and accurate automated annotation methods are required. Many methods, such as GOblet, GOfigure, and Gotcha, are designed based on the BLAST search. Unfortunately, the sequence coverage of these methods is low as they cannot detect the remote homologues. The lack of annotation coverage of the existing methods advocates novel methods to improve protein function prediction. Here we present a automated protein functional assignment method based on the neural response algorithm, which simulates the neuronal behavior of the visual cortex in the human brain. The main idea of this algorithm is to define a distance metric that corresponds to the similarity of the subsequences and reflects how the human brain can distinguish different sequences. Given query protein, we predict the most similar target protein using a two layered neural response algorithm and thereby assigned the GO term of the target protein to the query. Our method predicted and ranked the actual leaf GO term among the top 5 probable GO terms with 87.66% accuracy. Results of the 5-fold cross validation and the comparison with PFP and FFPred servers indicate the prominent performance by our method. The NRProF program, the dataset, and help files are available at http://www.jjwanglab.org/NRProF/.

Original languageEnglish (US)
Title of host publication2011 IEEE International Conference on Systems Biology, ISB 2011
Pages33-40
Number of pages8
DOIs
StatePublished - 2011
Externally publishedYes
Event5th IEEE International Conference on Systems Biology, ISB 2011 - Zhuhai, China
Duration: Sep 2 2011Sep 4 2011

Other

Other5th IEEE International Conference on Systems Biology, ISB 2011
CountryChina
CityZhuhai
Period9/2/119/4/11

Fingerprint

Proteins
Brain
Servers
Genes
Throughput
Visual Cortex
Proteomics
Genome

Keywords

  • Algorithms
  • Artificial intelligence
  • Genome annotation
  • Machine learning
  • Ontology

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)

Cite this

Yalamanchili, H. K., Wang, J., & Xiao, Q. W. (2011). NRProF: Neural response based protein function prediction algorithm. In 2011 IEEE International Conference on Systems Biology, ISB 2011 (pp. 33-40) https://doi.org/10.1109/ISB.2011.6033117

NRProF : Neural response based protein function prediction algorithm. / Yalamanchili, Hari Krishna; Wang, Junwen; Xiao, Quan Wu.

2011 IEEE International Conference on Systems Biology, ISB 2011. 2011. p. 33-40.

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

Yalamanchili, HK, Wang, J & Xiao, QW 2011, NRProF: Neural response based protein function prediction algorithm. in 2011 IEEE International Conference on Systems Biology, ISB 2011. pp. 33-40, 5th IEEE International Conference on Systems Biology, ISB 2011, Zhuhai, China, 9/2/11. https://doi.org/10.1109/ISB.2011.6033117
Yalamanchili HK, Wang J, Xiao QW. NRProF: Neural response based protein function prediction algorithm. In 2011 IEEE International Conference on Systems Biology, ISB 2011. 2011. p. 33-40 https://doi.org/10.1109/ISB.2011.6033117
Yalamanchili, Hari Krishna ; Wang, Junwen ; Xiao, Quan Wu. / NRProF : Neural response based protein function prediction algorithm. 2011 IEEE International Conference on Systems Biology, ISB 2011. 2011. pp. 33-40
@inproceedings{9725d93346e54d76a979bc7da0c64fa7,
title = "NRProF: Neural response based protein function prediction algorithm",
abstract = "A large amount of proteomic data is being generated due to the advancements in high-throughput genome sequencing. But the rate of functional annotation of these sequences falls far behind. To fill the gap between the number of sequences and their annotations, fast and accurate automated annotation methods are required. Many methods, such as GOblet, GOfigure, and Gotcha, are designed based on the BLAST search. Unfortunately, the sequence coverage of these methods is low as they cannot detect the remote homologues. The lack of annotation coverage of the existing methods advocates novel methods to improve protein function prediction. Here we present a automated protein functional assignment method based on the neural response algorithm, which simulates the neuronal behavior of the visual cortex in the human brain. The main idea of this algorithm is to define a distance metric that corresponds to the similarity of the subsequences and reflects how the human brain can distinguish different sequences. Given query protein, we predict the most similar target protein using a two layered neural response algorithm and thereby assigned the GO term of the target protein to the query. Our method predicted and ranked the actual leaf GO term among the top 5 probable GO terms with 87.66{\%} accuracy. Results of the 5-fold cross validation and the comparison with PFP and FFPred servers indicate the prominent performance by our method. The NRProF program, the dataset, and help files are available at http://www.jjwanglab.org/NRProF/.",
keywords = "Algorithms, Artificial intelligence, Genome annotation, Machine learning, Ontology",
author = "Yalamanchili, {Hari Krishna} and Junwen Wang and Xiao, {Quan Wu}",
year = "2011",
doi = "10.1109/ISB.2011.6033117",
language = "English (US)",
isbn = "9781457716669",
pages = "33--40",
booktitle = "2011 IEEE International Conference on Systems Biology, ISB 2011",

}

TY - GEN

T1 - NRProF

T2 - Neural response based protein function prediction algorithm

AU - Yalamanchili, Hari Krishna

AU - Wang, Junwen

AU - Xiao, Quan Wu

PY - 2011

Y1 - 2011

N2 - A large amount of proteomic data is being generated due to the advancements in high-throughput genome sequencing. But the rate of functional annotation of these sequences falls far behind. To fill the gap between the number of sequences and their annotations, fast and accurate automated annotation methods are required. Many methods, such as GOblet, GOfigure, and Gotcha, are designed based on the BLAST search. Unfortunately, the sequence coverage of these methods is low as they cannot detect the remote homologues. The lack of annotation coverage of the existing methods advocates novel methods to improve protein function prediction. Here we present a automated protein functional assignment method based on the neural response algorithm, which simulates the neuronal behavior of the visual cortex in the human brain. The main idea of this algorithm is to define a distance metric that corresponds to the similarity of the subsequences and reflects how the human brain can distinguish different sequences. Given query protein, we predict the most similar target protein using a two layered neural response algorithm and thereby assigned the GO term of the target protein to the query. Our method predicted and ranked the actual leaf GO term among the top 5 probable GO terms with 87.66% accuracy. Results of the 5-fold cross validation and the comparison with PFP and FFPred servers indicate the prominent performance by our method. The NRProF program, the dataset, and help files are available at http://www.jjwanglab.org/NRProF/.

AB - A large amount of proteomic data is being generated due to the advancements in high-throughput genome sequencing. But the rate of functional annotation of these sequences falls far behind. To fill the gap between the number of sequences and their annotations, fast and accurate automated annotation methods are required. Many methods, such as GOblet, GOfigure, and Gotcha, are designed based on the BLAST search. Unfortunately, the sequence coverage of these methods is low as they cannot detect the remote homologues. The lack of annotation coverage of the existing methods advocates novel methods to improve protein function prediction. Here we present a automated protein functional assignment method based on the neural response algorithm, which simulates the neuronal behavior of the visual cortex in the human brain. The main idea of this algorithm is to define a distance metric that corresponds to the similarity of the subsequences and reflects how the human brain can distinguish different sequences. Given query protein, we predict the most similar target protein using a two layered neural response algorithm and thereby assigned the GO term of the target protein to the query. Our method predicted and ranked the actual leaf GO term among the top 5 probable GO terms with 87.66% accuracy. Results of the 5-fold cross validation and the comparison with PFP and FFPred servers indicate the prominent performance by our method. The NRProF program, the dataset, and help files are available at http://www.jjwanglab.org/NRProF/.

KW - Algorithms

KW - Artificial intelligence

KW - Genome annotation

KW - Machine learning

KW - Ontology

UR - http://www.scopus.com/inward/record.url?scp=80054858471&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80054858471&partnerID=8YFLogxK

U2 - 10.1109/ISB.2011.6033117

DO - 10.1109/ISB.2011.6033117

M3 - Conference contribution

AN - SCOPUS:80054858471

SN - 9781457716669

SP - 33

EP - 40

BT - 2011 IEEE International Conference on Systems Biology, ISB 2011

ER -