Recognizing pathogenic antibodies in SLE using general regression neural networks

Mohamad Hasan Bahari; Asad Azemi; Mir Mojtaba Mirsalehi; Mahmoud Mahmoudi; Morteza Khadime

Recognizing pathogenic antibodies in SLE using general regression neural networks

Mohamad Hasan Bahari, Asad Azemi, Mir Mojtaba Mirsalehi, Mahmoud Mahmoudi, Morteza Khadime

Penn State Brandywine

Research output: Contribution to journal › Article › peer-review

Abstract

In this paper, a new method, based on artificial neural networks (ANN), has been introduced for recognizing pathogenic antibodies in Systemic Lupus Erythmatosus (SLE). dsDNA binding antibodies have been implicated in the pathogenesis of this autoimmune disease. In order to identify these dsDNA binding antibodies, the protein sequences of 42 dsDNA binding and 608 non-dsDNA binding antibodies were extracted from Kabat database and coded using five different physicochemical properties of their amino acids. Coded antibodies were used as the training patterns for five parallel general regression neural networks (GRNNs). Comparing the results obtained by the proposed method with other published results shows the efficacy of proposed approach.

Original language	English (US)
Pages (from-to)	2855-2864
Number of pages	10
Journal	International Journal of Innovative Computing, Information and Control
Volume	8
Issue number	4
State	Published - Apr 2012

All Science Journal Classification (ASJC) codes

Software
Theoretical Computer Science
Information Systems
Computational Theory and Mathematics

Cite this

@article{f6a73077de7b419493a03d41d75280ed,

title = "Recognizing pathogenic antibodies in SLE using general regression neural networks",

abstract = "In this paper, a new method, based on artificial neural networks (ANN), has been introduced for recognizing pathogenic antibodies in Systemic Lupus Erythmatosus (SLE). dsDNA binding antibodies have been implicated in the pathogenesis of this autoimmune disease. In order to identify these dsDNA binding antibodies, the protein sequences of 42 dsDNA binding and 608 non-dsDNA binding antibodies were extracted from Kabat database and coded using five different physicochemical properties of their amino acids. Coded antibodies were used as the training patterns for five parallel general regression neural networks (GRNNs). Comparing the results obtained by the proposed method with other published results shows the efficacy of proposed approach.",

author = "Bahari, {Mohamad Hasan} and Asad Azemi and Mirsalehi, {Mir Mojtaba} and Mahmoud Mahmoudi and Morteza Khadime",

year = "2012",

month = apr,

language = "English (US)",

volume = "8",

pages = "2855--2864",

journal = "International Journal of Innovative Computing, Information and Control",

issn = "1349-4198",

publisher = "IJICIC Editorial Office",

number = "4",

}

TY - JOUR

T1 - Recognizing pathogenic antibodies in SLE using general regression neural networks

AU - Bahari, Mohamad Hasan

AU - Azemi, Asad

AU - Mirsalehi, Mir Mojtaba

AU - Mahmoudi, Mahmoud

AU - Khadime, Morteza

PY - 2012/4

Y1 - 2012/4

N2 - In this paper, a new method, based on artificial neural networks (ANN), has been introduced for recognizing pathogenic antibodies in Systemic Lupus Erythmatosus (SLE). dsDNA binding antibodies have been implicated in the pathogenesis of this autoimmune disease. In order to identify these dsDNA binding antibodies, the protein sequences of 42 dsDNA binding and 608 non-dsDNA binding antibodies were extracted from Kabat database and coded using five different physicochemical properties of their amino acids. Coded antibodies were used as the training patterns for five parallel general regression neural networks (GRNNs). Comparing the results obtained by the proposed method with other published results shows the efficacy of proposed approach.

AB - In this paper, a new method, based on artificial neural networks (ANN), has been introduced for recognizing pathogenic antibodies in Systemic Lupus Erythmatosus (SLE). dsDNA binding antibodies have been implicated in the pathogenesis of this autoimmune disease. In order to identify these dsDNA binding antibodies, the protein sequences of 42 dsDNA binding and 608 non-dsDNA binding antibodies were extracted from Kabat database and coded using five different physicochemical properties of their amino acids. Coded antibodies were used as the training patterns for five parallel general regression neural networks (GRNNs). Comparing the results obtained by the proposed method with other published results shows the efficacy of proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=84859179567&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859179567&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84859179567

SN - 1349-4198

VL - 8

SP - 2855

EP - 2864

JO - International Journal of Innovative Computing, Information and Control

JF - International Journal of Innovative Computing, Information and Control

IS - 4

ER -

Recognizing pathogenic antibodies in SLE using general regression neural networks

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this