Different approaches to encode and model 3D information in a MIA-QSAR perspective

Daré, Joyce K.; Freitas, Matheus P.

doi:10.1016/j.chemolab.2021.104286

Cited by 4 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Facing these results, the robustness of the models seems to be more related to the alignment aspect of the structures than to how well their tridimensional features are described. This finding is in agreement with our most recent study, 10 where the inclusion of 3D information into MIA-QSAR descriptors implicated in worse models than those obtained with the conventional MIA-QSAR analysis, which is based on the alignment of congruent pharmacophoric substructures and disregards the spatial aspects of the molecules as in traditional 2D QSAR techniques.…”

Section: Resultssupporting

confidence: 92%

“…Accordingly, efforts to evolve the MIA-QSAR technique by adding another dimension have been performed, but the images analyzed from the slicing of a 3D-array with the molecule inside, as well as from images obtained in three perspectives of the molecule placed in a box, did not improve the prediction capability of the models. 10 Therefore, we inquire whether conformational information is indeed an essential condition to obtain predictive and interpretable QSAR models. Accordingly, the goal of this study is to perform a thorough investigation of the effects of conformational information on a 3D-QSAR modeling technique, a commonly conformation-dependent approach, by comparing models built with descriptors that encode fully described tridimensional aspects, with descriptors in which this information is suppressed or not fully described.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Is conformation relevant for QSAR purposes? 2D Chemical representation in a 3D‐QSAR perspective

Daré

Freitas

2022

J Comput Chem

Self Cite

View full text Add to dashboard Cite

Conformation has a key role in the mechanism of interaction between small molecules and biological receptors. However, encoding this type of information in molecular descriptors for the construction of robust quantitative structure–activity relationships (QSAR) models is not an easy task and, so far, the dependence of these models on such feature has not been thoroughly investigated. In the present study, the authors explore the effects of conformational information on a 3D‐QSAR technique by comparing models built with descriptors that encode fully described tridimensional aspects (structures docked inside a biological target), with descriptors in which this information is suppressed (flat structures) or not fully described (structures with quantum‐chemically optimized geometries). As a result, the validation parameters indicate that the robustness of the models seems to be more related to the alignment aspect of the structures than to how well their tridimensional features are described.

show abstract

Section: Resultssupporting

confidence: 92%

Section: Introductionmentioning

confidence: 99%

Is conformation relevant for QSAR purposes? 2D Chemical representation in a 3D‐QSAR perspective

Daré

Freitas

2022

J Comput Chem

Self Cite

View full text Add to dashboard Cite

show abstract

“…The MIA-QSAR technique aims to correlate numerous columns of individual variables to a single column dependent variable, y. Various coordinates of pixels in the molecular drawing depict structural changes in the MIA-QSAR technique, and these changes were utilized to show variation in bioactivity for a congeneric group of drug-like compounds [16,17]. In the modeling process, the substitution pattern, as well as the congeneric series of compounds, may be used to predict the bioactivities of comparable compounds.…”

Section: Introductionmentioning

confidence: 99%

Application of MIA-QSAR in Designing New Protein P38 MAP Kinase Compounds Using a Genetic Algorithm

Mirshafiei

Niazi‎²,

Yazdanipour³

2023

Period. Polytech. Chem. Eng.

View full text Add to dashboard Cite

Multivariate image analysis quantitative structure-activity relationship (MIA-QSAR) study aims to obtain information from a descriptor set, which are image pixels of two-dimensional molecule structures. In the QSAR study of protein P38 mitogen-activated protein (MAP) kinase compounds, the genetic algorithm application for pixel selection and image processing is investigated. There is a quantitative relationship between the structure and the pIC50 based on the information obtained. (The pIC50 is the negative logarithm of the half-maximal inhibitory concentration ( IC50 ), so pIC50 = −log IC50 .) Protein P38 MAP kinase inhibitors are used in the treatment of malignant tumors. The development of a model to predict the pIC50 of these compounds was performed in this study. To accomplish this, the molecules were first plotted and fixed in the same coordinates in ChemSketch. Then, the images were processed in the MATLAB program. Partial least squares (PLS) model, orthogonal signal correction partial least squares (OSC-PLS) model, and genetic algorithm partial least squares (GA-PLS) model methods are used to generate quantitative models, and pIC50 prediction is performed. The GA-PLS model has the highest predictive power for a series of statistical parameters such as root mean square error of prediction (RMSEP) and relative standard errors of prediction (RSEP). Finally, the molecular junction (docking) was done for predicted molecules in quantitative structure activity relationship (QSAR) with an appropriate receptor and acceptable results were obtained. These results are good and proper for the prediction of compounds with better properties.

show abstract

QSAR Modeling Based on Conformation Ensembles Using a Multi-Instance Learning Approach

Zankov

Matveieva

Nikonenko

et al. 2021

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Modern QSAR approaches have wide practical applications in drug discovery for designing potentially bioactive molecules. If such models are based on the use of 2D descriptors, important information contained in the spatial structures of molecules is lost. The major problem in constructing models using 3D descriptors is the choice of a putative bioactive conformation, which affects the predictive performance. The multi-instance (MI) learning approach considering multiple conformations in model training could be a reasonable solution to the above problem. In this study, we implemented several multi-instance algorithms, both conventional and based on deep learning, and investigated their performance. We compared the performance of MI-QSAR models with those based on the classical single-instance QSAR (SI-QSAR) approach in which each molecule is encoded by either 2D descriptors computed for the corresponding molecular graph or 3D descriptors issued for a single lowest energy conformation. The calculations were carried out on 175 data sets extracted from the ChEMBL23 database. It is demonstrated that (i) MI-QSAR outperforms SI-QSAR in numerous cases and (ii) MI algorithms can automatically identify plausible bioactive conformations.

show abstract

Different approaches to encode and model 3D information in a MIA-QSAR perspective

Cited by 4 publications

References 28 publications

Is conformation relevant for QSAR purposes? 2D Chemical representation in a 3D‐QSAR perspective

Is conformation relevant for QSAR purposes? 2D Chemical representation in a 3D‐QSAR perspective

Application of MIA-QSAR in Designing New Protein P38 MAP Kinase Compounds Using a Genetic Algorithm

QSAR Modeling Based on Conformation Ensembles Using a Multi-Instance Learning Approach

Contact Info

Product

Resources

About