QSPR Models on Fragment Descriptors

Соловьев, В.П.; Varnek, Alexandre

doi:10.1002/9781119161110.ch9

Cited by 8 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MLR calculations : The ISIDA QSPR, program combines forward and backward stepwise variable selection techniques. It generates large numbers of linear models starting from the training set, automatically scanning over specified ISIDA descriptor types (see section 2.2.1) and applying, for each descriptor space, algorithms of forward stepwise variable selection.…”

Section: Computational Proceduresmentioning

confidence: 99%

Predictive Models for the Free Energy of Hydrogen Bonded Complexes with Single and Cooperative Hydrogen Bonds

Madzhidov

Solov'ev

Marcou

et al. 2016

Molecular Informatics

Self Cite

View full text Add to dashboard Cite

In this work, we report QSPR modeling of the free energy ΔG of 1 : 1 hydrogen bond complexes of different H-bond acceptors and donors. The modeling was performed on a large and structurally diverse set of 3373 complexes featuring a single hydrogen bond, for which ΔG was measured at 298 K in CCl . The models were prepared using Support Vector Machine and Multiple Linear Regression, with ISIDA fragment descriptors. The marked atoms strategy was applied at fragmentation stage, in order to capture the location of H-bond donor and acceptor centers. Different strategies of model validation have been suggested, including the targeted omission of individual H-bond acceptors and donors from the training set, in order to check whether the predictive ability of the model is not limited to the interpolation of H-bond strength between two already encountered partners. Successfully cross-validating individual models were combined into a consensus model, and challenged to predict external test sets of 629 and 12 complexes, in which donor and acceptor formed single and cooperative H-bonds, respectively. In all cases, SVM models outperform MLR. The SVM consensus model performs well both in 3-fold cross-validation (RMSE=1.50 kJ/mol), and on the external test sets containing complexes with single (RMSE=3.20 kJ/mol) and cooperative H-bonds (RMSE=1.63 kJ/mol).

show abstract

Section: Computational Proceduresmentioning

confidence: 99%

Predictive Models for the Free Energy of Hydrogen Bonded Complexes with Single and Cooperative Hydrogen Bonds

Madzhidov

Solov'ev

Marcou

et al. 2016

Molecular Informatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…As shown in Table S4 (see the Supporting Information), we can assume that the structural and activity information encoded on the initial (raw) full set was kept as much as possible on the final (curated) data set. Additionally, we could confirm that the curated data set is free of duplicates using the “Find duplicate structures” option of the EdiSDF program included on the ISIDA project. , A schematic representation of the training set optimization process applied in this work is shown in Figure .…”

Section: Resultsmentioning

confidence: 99%

“…The NCI diversity set used for comparison is comprised by 1635 unique compounds included in the Diversity sets III, IV, and V provided in . Duplicate compounds in the three diversity sets were identified and removed using the EdiSDF program included on the ISIDA project. , The dissimilarity matrix for the MDS was obtained using the pdist function implemented in MatLab . The Jaccard coefficient was employed as the proximity metric.…”

Section: Resultsmentioning

confidence: 99%

Harmonization of QSAR Best Practices and Molecular Docking Provides an Efficient Virtual Screening Tool for Discovering New G-Quadruplex Ligands

Castillo-González

Mergny

Rache

et al. 2015

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Telomeres and telomerase are key players in tumorogenesis. Among the various strategies proposed for telomerase inhibition or telomere uncapping, the stabilization of telomeric G-quadruplex (G4) structures is a very promising one. Additionally, G4 stabilizing ligands also act over tumors mediated by the alternative elongation of telomeres. Accordingly, the discovery of novel compounds able to act on telomeres and/or inhibit the telomerase enzyme by stabilizing DNA telomeric G4 structures as well as the development of approaches efficiently prioritizing such compounds constitute active areas of research in computational medicinal chemistry and anticancer drug discovery. In this direction, we applied a virtual screening strategy based on the rigorous application of QSAR best practices and its harmonized integration with structure-based methods. More than 600,000 compounds from commercial databases were screened, the first 99 compounds were prioritized, and 21 commercially available and structurally diverse candidates were purchased and submitted to experimental assays. Such strategy proved to be highly efficient in the prioritization of G4 stabilizer hits, with a hit rate of 23.5%. The best G4 stabilizer hit found exhibited a shift in melting temperature from FRET assay of +7.3 °C at 5 μM, while three other candidates also exhibited a promising stabilizing profile. The two most promising candidates also exhibited a good telomerase inhibitory ability and a mild inhibition of HeLa cells growth. None of these candidates showed antiproliferative effects in normal fibroblasts. Finally, the proposed virtual screening strategy proved to be a practical and reliable tool for the discovery of novel G4 ligands which can be used as starting points of further optimization campaigns.

show abstract

“…In this step, the descriptors are selected one by one or in twos with the help of FVS‐1 and FVS‐2 (Forward stepwise Variable Selection) algorithms , respectively, each of which collected 0.4 n , 0.5 n , …, 0.9 n descriptors to increase the diversity of the resulting models, where n is the number of the compounds in the training set. Step (c) eliminates the variables with low t i =a i /Δa i values for the models, where Δ a i is a standard deviation for the coefficient a i at the i ‐th variable in the model . The algorithm selects the variable with the minimal t min < t 0 and builds a new model excluding this variable.…”

Section: Methodsmentioning

confidence: 99%

QSPR Modeling of Potentiometric Mg²⁺/Ca²⁺ Selectivity for PVC‐plasticized Sensor Membranes

et al. 2020

Self Cite

View full text Add to dashboard Cite

The development of novel ionophores for ion‐selective sensors is a time‐consuming and tedious process requiring synthesis of candidate substances, preparation of plasticized polymeric membranes, and their thorough characterization with traditional protocols to assess sensitivity, selectivity and detection limits for target ions. The vast amount of literature data accumulated on various ion‐selective sensors allows for significant facilitation of the development through in silico experiments. In this report, we performed the feasibility study on the prediction of potentiometric Mg2+/Ca2+ selectivity for various amide ligands using quantitative structure‐property relationship (QSPR) modeling. The approach proved to be promising for ionophore screening purposes with achieved precision in prediction of the selectivity coefficient logK(Mg2+/Ca2+) of 0.5 in the range from −1.7 to +2.3. The study also shows a route for prediction of new potential ionophores with high selectivity values.

show abstract

QSPR Models on Fragment Descriptors

Cited by 8 publications

References 19 publications

Predictive Models for the Free Energy of Hydrogen Bonded Complexes with Single and Cooperative Hydrogen Bonds

Predictive Models for the Free Energy of Hydrogen Bonded Complexes with Single and Cooperative Hydrogen Bonds

Harmonization of QSAR Best Practices and Molecular Docking Provides an Efficient Virtual Screening Tool for Discovering New G-Quadruplex Ligands

QSPR Modeling of Potentiometric Mg²⁺/Ca²⁺ Selectivity for PVC‐plasticized Sensor Membranes

Contact Info

Product

Resources

About

QSPR Models on Fragment Descriptors

Cited by 8 publications

References 19 publications

Predictive Models for the Free Energy of Hydrogen Bonded Complexes with Single and Cooperative Hydrogen Bonds

Predictive Models for the Free Energy of Hydrogen Bonded Complexes with Single and Cooperative Hydrogen Bonds

Harmonization of QSAR Best Practices and Molecular Docking Provides an Efficient Virtual Screening Tool for Discovering New G-Quadruplex Ligands

QSPR Modeling of Potentiometric Mg2+/Ca2+ Selectivity for PVC‐plasticized Sensor Membranes

Contact Info

Product

Resources

About

QSPR Modeling of Potentiometric Mg²⁺/Ca²⁺ Selectivity for PVC‐plasticized Sensor Membranes