QSPR study on solubility of some fullerenes derivatives using the genetic algorithms — Multiple linear regression

Pourbasheer, Eslam; Aalizadeh, Reza; Ardabili, Jamal Saffar; Ganjali, Mohammad Reza

doi:10.1016/j.molliq.2015.01.028

Cited by 33 publications

(14 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such cases include constant or near constant descriptors with low variance, descriptors with missing or zero values, and collinear highly correlated pairs of variables. In the case of correlated variables, the one with higher correlation with the endpoint is chosen in developing the model [23]. In addition to descriptors' reduction, a feature selection process is followed in order to optimize the performance of the model.…”

Section: Feature Reductionmentioning

confidence: 99%

“…Robustness metrics such as squared cross validated correlation coefficient (Q 2 ), leave-one-out cross-validation coefficient (Q 2 LOO ), and leave-many-out cross-validation coefficients (Q 2 LMO−10% and Q 2 LMO−25% ) are popular robustness indicators [46,47]. To avoid the possibility of overestimation by using only leave-one-out cross validation, a bootstrap procedure (Q 2 Boot ) is suggested [23] and is mainly suitable for a limited number of training cases [50]. These approaches systematically take out data points from the training set, reconstructing the model, and then predict the left-out data points.…”

Section: Robustnessmentioning

confidence: 99%

See 1 more Smart Citation

Practices and Trends of Machine Learning Application in Nanotoxicology

et al. 2020

View full text Add to dashboard Cite

Machine Learning (ML) techniques have been applied in the field of nanotoxicology with very encouraging results. Adverse effects of nanoforms are affected by multiple features described by theoretical descriptors, nano-specific measured properties, and experimental conditions. ML has been proven very helpful in this field in order to gain an insight into features effecting toxicity, predicting possible adverse effects as part of proactive risk analysis, and informing safe design. At this juncture, it is important to document and categorize the work that has been carried out. This study investigates and bookmarks ML methodologies used to predict nano (eco)-toxicological outcomes in nanotoxicology during the last decade. It provides a review of the sequenced steps involved in implementing an ML model, from data pre-processing, to model implementation, model validation, and applicability domain. The review gathers and presents the step-wise information on techniques and procedures of existing models that can be used readily to assemble new nanotoxicological in silico studies and accelerates the regulation of in silico tools in nanotoxicology. ML applications in nanotoxicology comprise an active and diverse collection of ongoing efforts, although it is still in their early steps toward a scientific accord, subsequent guidelines, and regulation adoption. This study is an important bookend to a decade of ML applications to nanotoxicology and serves as a useful guide to further in silico applications.

show abstract

Section: Feature Reductionmentioning

confidence: 99%

Section: Robustnessmentioning

confidence: 99%

Practices and Trends of Machine Learning Application in Nanotoxicology

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In addition to QSAR studies, a molecular docking method representing the true conformation of the compound in protein bonding sites was performed [60]. To perform a docking analysis, AutoDock 4.2 [61] was used to understand the interactions between the most potent B-raf 600E inhibitor in the data set and this kinase.…”

Section: Molecular Dockingmentioning

confidence: 99%

Analysis of B-Raf $$^{\mathrm{V600E}}$$ V 600 E inhibitors using 2D and 3D-QSAR, molecular docking and pharmacophore studies

Aalizadeh

Pourbasheer

2015

Mol Divers

Self Cite

View full text Add to dashboard Cite

In the present work, a molecular modeling study was carried out using 2D and 3D quantitative structure-activity relationships for the various series of compounds known as B-Raf[Formula: see text] inhibitors. For 2D-QSAR analysis, a linear model was developed by MLR based on GA-OLS with appropriate results [Formula: see text], which was validated by several external validation techniques. To perform a 3D-QSAR analysis, CoMFA and CoMSIA methods were used. The selected CoMFA model could provide reliable statistical values [Formula: see text] based on the training set in the biases of the selected alignment. Using the same selected alignment, a statistically reliable CoMSIA model, out of thirty-one different combinations, was also obtained [Formula: see text]. The predictive accuracy of the derived models was rigorously evaluated with the external test set of nineteen compounds based on several validation techniques. Molecular docking simulations and pharmacophore analyses were also performed to derive the true conformations of the most potent inhibitors with B-Raf[Formula: see text] kinase.

show abstract

“…The majority of these works are based on the applications of classic Molecular Dynamics methods (MD). 4,5,6,7,8,9,10,11 Nevertheless, Density Functional Theory (DFT) simulations 12 or quantitative structure properties relationship (QSPR) 13 studies have been also published. Among the new alternatives studied for C 60 dispersion in solvents, the recent works by Chaban et al 5 …”

Section: Introductionmentioning

confidence: 99%

Theoretical Study on the Solvation of C₆₀Fullerene by Ionic Liquids II: DFT Analysis of the Interaction Mechanism

García

Aparício

2015

J. Phys. Chem. B

View full text Add to dashboard Cite

As a continuation of our previous work (J. Phys. Chem. B, 2014, 118, 11330) on the solvation of C60 by ionic liquids (ILs) using Molecular Dynamic simulations, this paper reports a systematic density functional theory (DFT) analysis on the interaction mechanism between C60 and 24 different ionic liquids (belonging to the imidazolium, piperazinium, and cholinium groups). Properties such as binding energies, charge distributions, intermolecular interactions, or electronic structure were analyzed as a function of the selected ILs. The stronger IL-C60 interactions would be related with π-π stacking between the C60 surface and anions such as salycilate ([SA]). Likewise, the electronic structure analysis pointed to a well-defined relationship between the energetics of IL-C60 systems and IL features. Therefore, ILs with deep HOMO energies as well as weak interaction between both ions would be a priori good candidates for C60 solvation. Although only short-range interactions are studied in the framework of DFT, this work provides useful information for the rational design of ILs that could exhibit suitable features as C60 solvents.

show abstract

QSPR study on solubility of some fullerenes derivatives using the genetic algorithms — Multiple linear regression

Cited by 33 publications

References 46 publications

Practices and Trends of Machine Learning Application in Nanotoxicology

Practices and Trends of Machine Learning Application in Nanotoxicology

Analysis of B-Raf $$^{\mathrm{V600E}}$$ V 600 E inhibitors using 2D and 3D-QSAR, molecular docking and pharmacophore studies

Theoretical Study on the Solvation of C₆₀Fullerene by Ionic Liquids II: DFT Analysis of the Interaction Mechanism

Contact Info

Product

Resources

About

QSPR study on solubility of some fullerenes derivatives using the genetic algorithms — Multiple linear regression

Cited by 33 publications

References 46 publications

Practices and Trends of Machine Learning Application in Nanotoxicology

Practices and Trends of Machine Learning Application in Nanotoxicology

Analysis of B-Raf $$^{\mathrm{V600E}}$$ V 600 E inhibitors using 2D and 3D-QSAR, molecular docking and pharmacophore studies

Theoretical Study on the Solvation of C60Fullerene by Ionic Liquids II: DFT Analysis of the Interaction Mechanism

Contact Info

Product

Resources

About

Theoretical Study on the Solvation of C₆₀Fullerene by Ionic Liquids II: DFT Analysis of the Interaction Mechanism