SMILES‐Based QSAR Models for the Calcium Channel‐Antagonistic Effect of 1,4‐Dihydropyridines

Abstract

The activity of 72 1,4-dihydropyridines as calcium channel antagonists was examined. The simplified molecular input-line entry system (SMILES) was used as representation of the molecular structure of the calcium channel antagonists. Quantitative structure-activity relationships (QSARs) were developed using CORAL software (http://www.insilico.eu/CORAL) for four random splits of the data into the training and test sets. Using the Monte Carlo method, the CORAL software generated the optimal descriptors for one-variable models. The reproducibility of each model was tested performing three runs of the Monte Carlo optimization. The obtained results reveal good predictive potential of the applied approach: The correlation coefficients (r(2) ) for the test sets of the four random splits are 0.9571, 0.9644, 0.9836, and 0.9444.

Development of the Latest Tools for Building up “Nano-QSAR”: Quantitative Features—Property/Activity Relationships (QFPRs/QFARs)

“…They are developed following a set of rules: (i) All examined eclectic systems of data are translated into quasi-SMILES with further prediction of the above mentioned endpoints by the same approach; (ii) building up these models using the quasi-SMILES can be carried out by the same algorithm (software) which is used in the case of the traditional SMILES [49][50][51][52][53][54][55][56]; (iii) eclectic systems can be similar in order for their implementation into common generalized model; (iv) the suggested model has mechanistic interpretation in terms of revealing promoters of increase and decrease for an endpoint. Thus, one concludes that the proposed approach provides models for nanomaterials, in accordance with the OECD principles [57].…”

Monte Carlo method based QSAR modeling of maleimide derivatives as glycogen synthase kinase-3β inhibitors

“…Test set Monte Carlo optimization runs is positive then that SA k is the promoter of increase; if CW(SA k ) from three independent Monte Carlo optimization runs is negative then that SA k is the promoter of decrease; if there are both positive and negative values of CW (Sk) in three runs of the Monte Carlo optimization process, then that SA k has an undefined role [26][27][28][29]32,33]. The list of all SA k , with the correlation weights for three runs of the Monte Carlo optimization process of the built QSAR model for maleimide derivatives is shown in Table S3.…”

“…For these reasons, the conformation-independent (0D, 1D and 2D-QSPR) method models based on the constitutional and topological molecular features of compounds emerged as an alternative approach [24,25]. QSAR modeling is often based on optimal descriptors calculated with the molecular graph [26][27][28]. The simplified molecular input-line entry system (SMILES) can be considered as an alternative for the representation of the molecular structure by the molecular graph [29][30][31].…”

Monte Carlo QSAR models for predicting organophosphate inhibition of acetycholinesterase

“…as a mathematical function of each character of SMILES. Not only can local SMILES attributes be used for QSAR modelling, but for global SMILES attributes as well: a characteristic of a molecule in whole, for example, the presence of nitrogen together with oxygen, the presence of double bonds and cycles, the presence of nitrogen and sulphur and absence of oxygen, and others [22][23][24][25].…”

“…The Simplified Molecular Input Line Entry System (SMILES) is an alternative to a molecular graph and can be used for the elucidation of molecular structures [19]. Recently published papers have reported the applicability of SMILES notation based optimal descriptors in QSAR modelling with calculations based on the Monte Carlo method in which the appropriate activity is treated as a random event [20][21][22][23][24][25].…”