Recognizing pathogenic antibodies in SLE using general regression neural networks

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

Research output: Contribution to journalArticlepeer-review


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 languageEnglish (US)
Pages (from-to)2855-2864
Number of pages10
JournalInternational Journal of Innovative Computing, Information and Control
Issue number4
StatePublished - Apr 2012

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Information Systems
  • Computational Theory and Mathematics


Dive into the research topics of 'Recognizing pathogenic antibodies in SLE using general regression neural networks'. Together they form a unique fingerprint.

Cite this