QSAR study of α1β4 integrin inhibitors by GA-MLR and GA-SVM methods

In this work, the linear (multiple linear regressions) and nonlinear (support vector machine) methods are used to develop quantitative structure–activity relationship models in order to predict the activities of some α1β4 integrin inhibitors. A dataset that consisted of 51 molecules was divided into the training and test subsets. Stepwise and genetic algorithm methods have been employed for selection of relevant descriptors. Comparison of the obtained results indicated the superiority of the genetic algorithm over the stepwise method for feature selection. The models were validated using the cross-validation, external test set, and Y- randomization test. Comparison of the results showed that SVM was very accurate approach in predicting the activities of α1β4 integrin inhibitors. The predicted results of this study can provide better insights to design new α1β4 integrin inhibitors.

[1]  M. Ganjali,et al.  QSAR study of C allosteric binding site of HCV NS5B polymerase inhibitors by support vector machine , 2011, Molecular Diversity.

[2]  Paola Gramatica,et al.  Modeling and prediction by using WHIM descriptors in QSAR studies: submitochondrial particles (SMP) as toxicity blosensors of chlorophenols , 1996 .

[3]  Eslam Pourbasheer,et al.  Application of principal component-genetic algorithm-artificial neural network for prediction acidity constant of various nitrogen-containing compounds in water , 2009 .

[4]  Y. S. Prabhakar,et al.  Topological descriptors in modeling the agonistic activity of human A3 adenosine receptor ligands: the derivatives of 2-chloro-N(6)-substituted-4'-thioadenosine-5'-uronamide. , 2009, European journal of medicinal chemistry.

[5]  Paola Gramatica,et al.  Structure/Response Correlations and Similarity/Diversity Analysis by GETAWAY Descriptors, 2. Application of the Novel 3D Molecular Descriptors to QSAR/QSPR Studies , 2002, J. Chem. Inf. Comput. Sci..

[6]  Erik Johansson,et al.  On the selection of the training set in environmental QSAR analysis when compounds are clustered , 2000 .

[7]  R. Hynes,et al.  Integrin receptors are required for cell survival and proliferation during development of the peripheral glial lineage. , 2001, Developmental biology.

[8]  B. Holzmann,et al.  Molecular analysis of the physiological and pathophysiological role of α4-integrins , 1995, Journal of Molecular Medicine.

[9]  P. Kubes.  Introduction: The complexities of leukocyte recruitment , 2002 .

[10]  M. Hemler.  VLA proteins in the integrin family: structures, functions, and their role on leukocytes. , 1990, Annual review of immunology.

[11]  Lemont B. Kier,et al.  Electrotopological State Indices for Atom Types: A Novel Combination of Electronic, Topological, and Valence State Information , 1995, J. Chem. Inf. Comput. Sci..

[12]  T. Paavonen,et al.  In vivo evidence of the role of α4β1‐VCAM‐1 interaction in sarcoma, but not in carcinoma extravasation , 1994 .

[13]  D. Clegg,et al.  Integrin α4β1 function is required for cell survival in developing retina , 2004 .

[14]  R. A. Ellis,et al.  Molecular modeling system. , 1972, Journal of molecular biology.

[15]  R. R. Hocking.  The analysis and selection of variables in linear regression , 1976 .

[16]  Eslam Pourbasheer,et al.  QSAR study on melanocortin-4 receptors by support vector machine. , 2010, European journal of medicinal chemistry.

[17]  M. Hemler,et al.  The pathophysiologic role of alpha 4 integrins in vivo. , 1994, The Journal of clinical investigation.

[18]  David A. Belsley,et al.  Regression Analysis and its Application: A Data-Oriented Approach.@@@Applied Linear Regression.@@@Regression Diagnostics: Identifying Influential Data and Sources of Collinearity , 1981 .

[19]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[20]  Vipin Kumar,et al.  QSAR studies on estimation of monoamine oxidase-A inhibitory activity using topological descriptors , 2011, Medicinal Chemistry Research.

[21]  N. Draper,et al.  Applied Regression Analysis , 1966 .

[22]  M. Sadeghi,et al.  Spectrophotometric simultaneous determination of ceratine, creatinine, and uric acid in real samples by orthogonal signal correction–partial least squares regression , 2009 .

[23]  Lu Xu,et al.  A QSAR study of the antiallergic activities of substituted benzamides and their structures , 1999 .

[24]  Eslam Pourbasheer,et al.  QSRR Study of GC Retention Indices of Essential-Oil Compounds by Multiple Linear Regression with a Genetic Algorithm , 2008 .

[25]  P. Khadikar,et al.  QSAR prediction of toxicity of nitrobenzenes. , 2001, Bioorganic & medicinal chemistry.

[26]  K. Lam,et al.  Structure–activity relationship studies of a series of peptidomimetic ligands for α4 β1 integrin on Jurkat T‐leukemia cells , 2006 .

[27]  M. Ganjali,et al.  QSAR study on hERG inhibitory effect of kappa opioid receptor antagonists by linear and non-linear methods , 2013, Medicinal Chemistry Research.

[28]  藤田 稔夫.  QSAR and drug design : new developments and applications , 1995 .

[29]  R. Alon,et al.  Immune cell migration in inflammation: present and future therapeutic targets , 2005, Nature Immunology.

[30]  C. Hansch,et al.  p-σ-π Analysis. A Method for the Correlation of Biological Activity and Chemical Structure , 1964 .

[31]  Eslam Pourbasheer,et al.  Application of genetic algorithm-support vector machine (GA-SVM) for prediction of BK-channels activity. , 2009, European journal of medicinal chemistry.

[32]  D. Clegg,et al.  The alpha4 subunit of integrin is important for neural crest cell migration. , 1998, Developmental biology.

[33]  Bernard F. Buxton,et al.  Drug Design by Machine Learning: Support Vector Machines for Pharmaceutical Data Analysis , 2001, Comput. Chem..

[34]  D. Griffith,et al.  Multivariate statistical analysis for geographers , 1997 .

[35]  K. No,et al.  PXR ligand classification model with SFED-weighted WHIM and CoMMA descriptors , 2012, SAR and QSAR in environmental research.

[36]  Timothy A. Springer,et al.  Adhesion receptors of the immune system , 1990, Nature.

[37]  Jian-hui Jiang,et al.  Quantitative structure-activity relationships (QSAR): studies of inhibitors of tyrosine kinase. , 2003, European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences.

[38]  J. Gasteiger,et al.  Chemical Information in 3D Space , 1997 .

[39]  K. Lam,et al.  An alpha4beta1 integrin antagonist decreases airway inflammation in ovalbumin-exposed mice. , 2009, European journal of pharmacology.

[40]  Richard O Hynes,et al.  Integrins Bidirectional, Allosteric Signaling Machines , 2002, Cell.

[41]  William D. Berry,et al.  Multiple regression in practice , 1985 .

[42]  Tingjun Hou,et al.  Applications of Genetic Algorithms on the Structure-Activity Relationship Analysis of Some Cinnamamides , 1999, J. Chem. Inf. Comput. Sci..

[43]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[44]  Hugo Kubinyi,et al.  3D QSAR in drug design : theory, methods and applications , 2000 .