MIA-QSAR: a simple 2D image-based approach for quantitative structure–activity relationship analysis

Abstract An accessible and quite simple QSAR method, based on 2D image analysis, is reported. A case study is carried out in order to compare this model with a previously reported sophisticated methodology. A well known set of ( S )- N -[(1-ethyl-2-pyrrolidinyl)methyl]-6-methoxybenzamides, compounds with affinity to the dopamine D 2 receptor subtype, was divided in 40 calibration compounds and 18 test compounds and the descriptors were generated from pixels of 2D structures of each compound, which can be drawn with aid of any appropriate program. Bilinear (conventional) PLS was utilized as the regression method and leave-one-out cross-validation was performed using the NIPALS algorithm. The good predicted Q 2 value obtained for the series of test compounds (0.58), together with the similar prediction quality obtained to other data sets (nAChR ligands, HIV protease inhibitors, COX-2 inhibitors and anxiolytic agents), suggests that the model is robust and seems to be as applicable as more complex methods.

[1]  T. Liljefors,et al.  Novel potent ligands for the central nicotinic acetylcholine receptor: synthesis, receptor binding, and 3D-QSAR analysis. , 2000, Journal of medicinal chemistry.

[2]  K. Esbensen,et al.  Regression on multivariate images: Principal component regression for modeling, prediction and visual diagnostic tools , 1991 .

[3]  S. Bromidge,et al.  Novel and selective 5-HT2C/2B receptor antagonists as potential anxiolytic agents: synthesis, quantitative structure-activity relationships, and molecular modeling of substituted 1-(3-pyridylcarbamoyl)indolines. , 1998, Journal of medicinal chemistry.

[4]  Herman van Vlijmen,et al.  3D QSAR (COMFA) of a series of potent and highly selective VLA-4 antagonists , 2002, J. Comput. Aided Mol. Des..

[5]  Paul Geladi,et al.  Image analysis and chemical information in images , 1986 .

[6]  Age K. Smilde,et al.  A multiway 3D QSAR analysis of a series of (S)-N-[(1-ethyl-2-pyrrolidinyl)methyl]-6-methoxybenzamides , 1998, J. Comput. Aided Mol. Des..

[7]  Nouri Neamati,et al.  Application of CoMFA and CoMSIA 3D-QSAR and docking studies in optimization of mercaptobenzenesulfonamides as HIV-1 integrase inhibitors. , 2004, Journal of medicinal chemistry.

[8]  P. Geladi,et al.  Multivariate image analysis , 1996 .

[9]  R. Zauhar,et al.  Computational studies on HIV-1 protease inhibitors: influence of calculated inhibitor-enzyme binding affinities on the statistical quality of 3D-QSAR CoMFA models. , 2000, Journal of medicinal chemistry.

[10]  A. Hopfinger,et al.  Construction of 3D-QSAR Models Using the 4D-QSAR Analysis Formalism , 1997 .

[11]  Kim H. Esbensen,et al.  The AMT approach in chemometrics — first forays , 1996 .

[12]  R. Cramer,et al.  Comparative molecular field analysis (CoMFA). 1. Effect of shape on binding of steroids to carrier proteins. , 1988, Journal of the American Chemical Society.

[13]  Computer-aided design of selective COX-2 inhibitors: comparative molecular field analysis, comparative molecular similarity indices analysis, and docking studies of some 1,2-diarylimidazole derivatives. , 2002, Journal of medicinal chemistry.

[14]  F. Sanz,et al.  Ligands of neuronal nicotinic acetylcholine receptor (nAChR): inferences from the Hansch and 3-D quantitative structure-activity relationship (QSAR) Models. , 2002, Current medicinal chemistry.

[15]  A. Molla,et al.  Discovery of ritonavir, a potent inhibitor of HIV protease with high oral bioavailability and clinical efficacy. , 1998, Journal of medicinal chemistry.