skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Non-linear quantitative structure-activity relationship for adenine derivatives as competitive inhibitors of adenosine deaminase

Abstract

Logistic regression and artificial neural networks have been developed as two non-linear models to establish quantitative structure-activity relationships between structural descriptors and biochemical activity of adenosine based competitive inhibitors, toward adenosine deaminase. The training set included 24 compounds with known k {sub i} values. The models were trained to solve two-class problems. Unlike the previous work in which multiple linear regression was used, the highest of positive charge on the molecules was recognized to be in close relation with their inhibition activity, while the electric charge on atom N1 of adenosine was found to be a poor descriptor. Consequently, the previously developed equation was improved and the newly formed one could predict the class of 91.66% of compounds correctly. Also optimized 2-3-1 and 3-4-1 neural networks could increase this rate to 95.83%.

Authors:
 [1];  [2];  [3];  [4]
  1. Department of Biophysics, Faculty of Science, Tarbiat Modares University, P.O. Box: 14115/175, Tehran (Iran, Islamic Republic of)
  2. Department of Biophysics, Faculty of Science, Tarbiat Modares University, P.O. Box: 14115/175, Tehran (Iran, Islamic Republic of) . E-mail: parviz@modares.ac.ir
  3. Department of Biology, Faculty of Science, Tehran University, P.O. Box: 13155-6455, Tehran (Iran, Islamic Republic of)
  4. Department of Biochemistry, Faculty of Science, Tarbiat Modares University, P.O. Box: 14115/175, Tehran (Iran, Islamic Republic of)
Publication Date:
OSTI Identifier:
20793227
Resource Type:
Journal Article
Resource Relation:
Journal Name: Biochemical and Biophysical Research Communications; Journal Volume: 338; Journal Issue: 2; Other Information: DOI: 10.1016/j.bbrc.2005.10.049; PII: S0006-291X(05)02311-9; Copyright (c) 2005 Elsevier Science B.V., Amsterdam, The Netherlands, All rights reserved; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES; ADENINES; ADENOSINE; BIOCHEMISTRY; NEURAL NETWORKS; STRUCTURE-ACTIVITY RELATIONSHIPS; TRAINING

Citation Formats

Sadat Hayatshahi, Sayyed Hamed, Abdolmaleki, Parviz, Safarian, Shahrokh, and Khajeh, Khosro. Non-linear quantitative structure-activity relationship for adenine derivatives as competitive inhibitors of adenosine deaminase. United States: N. p., 2005. Web. doi:10.1016/J.BBRC.2005.1.
Sadat Hayatshahi, Sayyed Hamed, Abdolmaleki, Parviz, Safarian, Shahrokh, & Khajeh, Khosro. Non-linear quantitative structure-activity relationship for adenine derivatives as competitive inhibitors of adenosine deaminase. United States. doi:10.1016/J.BBRC.2005.1.
Sadat Hayatshahi, Sayyed Hamed, Abdolmaleki, Parviz, Safarian, Shahrokh, and Khajeh, Khosro. Fri . "Non-linear quantitative structure-activity relationship for adenine derivatives as competitive inhibitors of adenosine deaminase". United States. doi:10.1016/J.BBRC.2005.1.
@article{osti_20793227,
title = {Non-linear quantitative structure-activity relationship for adenine derivatives as competitive inhibitors of adenosine deaminase},
author = {Sadat Hayatshahi, Sayyed Hamed and Abdolmaleki, Parviz and Safarian, Shahrokh and Khajeh, Khosro},
abstractNote = {Logistic regression and artificial neural networks have been developed as two non-linear models to establish quantitative structure-activity relationships between structural descriptors and biochemical activity of adenosine based competitive inhibitors, toward adenosine deaminase. The training set included 24 compounds with known k {sub i} values. The models were trained to solve two-class problems. Unlike the previous work in which multiple linear regression was used, the highest of positive charge on the molecules was recognized to be in close relation with their inhibition activity, while the electric charge on atom N1 of adenosine was found to be a poor descriptor. Consequently, the previously developed equation was improved and the newly formed one could predict the class of 91.66% of compounds correctly. Also optimized 2-3-1 and 3-4-1 neural networks could increase this rate to 95.83%.},
doi = {10.1016/J.BBRC.2005.1},
journal = {Biochemical and Biophysical Research Communications},
number = 2,
volume = 338,
place = {United States},
year = {Fri Dec 16 00:00:00 EST 2005},
month = {Fri Dec 16 00:00:00 EST 2005}
}