3D molecular fragment descriptors for structure–property modeling: predicting the free energies for the complexation between antipodal guests and β-cyclodextrins

Соловьев, А. Е.; Соловьев, В.П.

doi:10.1007/s10847-017-0739-z

Cited by 5 publications

(2 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each type of SMF and a combination of variable selection techniques, two types of equations were prepared, including the term

a_{0}

or without it. The selection of descriptors for the model was carried out in several stages:, a ) filtering of descriptors, b ) forward stepwise variable selection – an iterative process of accumulating descriptors that significantly correlate with the property, c ) backward stepwise variable selection – the iterative process of excluding some selected descriptors, which introduce large errors into the model. In stage ( a ), descriptors were excluded: rare, occurring in less than three molecules of the training set; having constant occurrence count in all compounds of the training set; having a squared correlation coefficient with the property below the given threshold

R_{y j l i m}^{2}

=0.001; one of each pair if a squared correlation coefficient between them is higher than the specified threshold

R_{i j l i m}^{2}

=0.99.…”

Section: Methodsmentioning

confidence: 99%

Predictive Models for HOMO and LUMO Energies of N‐Donor Heterocycles as Ligands for Lanthanides Separation

Solov'ev

Ustynyuk

Zhokhova

et al. 2018

Molecular Informatics

View full text Add to dashboard Cite

Quantum chemical calculations combined with QSPR methodology reveal challenging perspectives for the solution of a number of fundamental and applied problems. In this work, we performed the PM7 and DFT calculations and QSPR modeling of HOMO and LUMO energies for polydentate N-heterocyclic ligands promising for the extraction separation of lanthanides because these values are related to the ligands selectivity in the respect to the target cations. Data for QSPR modeling comprised the PM7 calculated HOMO and LUMO energies of N-donor heterocycles, including several types of both known and virtual undescribed polydentate ligands. Ensemble modeling included various molecular fragments as descriptors and different variable selection techniques to build consensus models (CMs) on a training set of 388 ligands using external cross-validation. CMs were then verified to make predictions for two external test sets: 45 ligands (T1) that were similar to the ligands of the training set, and 1546 structures (T2), which were substantially different from the ligands of the training set. The consensus models predict well in 5-fold cross-validation (RMSE =0.097 eV, RMSE =0.064 eV), and on the external test sets (T1: RMSE =0.26 eV, RMSE =0.24 eV; T2: RMSE =0.26 eV, RMSE =0.17 eV). An analysis of the results reveals that substituents in heteroaromatic rings of the ligands and at the amide nitrogens can deeply influence their metal binding properties.

show abstract

“…For each type of SMF and a combination of variable selection techniques, two types of equations were prepared, including the term

a_{0}

R_{y j l i m}^{2}

=0.001; one of each pair if a squared correlation coefficient between them is higher than the specified threshold

R_{i j l i m}^{2}

=0.99.…”

Section: Methodsmentioning

confidence: 99%

Predictive Models for HOMO and LUMO Energies of N‐Donor Heterocycles as Ligands for Lanthanides Separation

Solov'ev

Ustynyuk

Zhokhova

et al. 2018

Molecular Informatics

View full text Add to dashboard Cite

show abstract

“…In fact, machine learning tends to encounter predictive limitation when substantially different guest molecules are used in the testing set. Even though some predictive models for complexation free energy between CDs and guest molecules had been built in previously published papers, these models were limited to the dataset with no more than 300 data point20, 34. In current research, the full dataset with 3000 data points had about 1320 different chemical structures, which highly contributed to the high-accuracy predictive ability.…”

Section: Resultsmentioning

confidence: 97%

Predicting complexation performance between cyclodextrins and guest molecules by integrated machine learning and molecular modeling techniques

Zhao¹,

Ye²,

Su³

et al. 2019

Acta Pharmaceutica Sinica B

View full text Add to dashboard Cite

Most pharmaceutical formulation developments are complex and ideal formulations are generally obtained after extensive experimentation. Machine learning is increasingly advancing many aspects in modern society and has achieved significant success in multiple subjects. Current research demonstrated that machine learning can be adopted to build up high-accurate predictive models in drugs/cyclodextrins (CDs) systems. Molecular descriptors of compounds and experimental conditions were employed as inputs, while complexation free energy as outputs. Results showed that the light gradient boosting machine provided significantly improved predictive performance over random forest and deep learning. The mean absolute error was 1.38 kJ/mol and squared correlation coefficient was 0.86. The evaluation of relative importance of molecular descriptors further demonstrated the key factors affecting molecular interactions in drugs/CD systems. In the specific ketoprofen–CD systems, machine learning model showed better predictive performance than molecular modeling calculation, while molecular simulation could provide structural, dynamic and energetic information. The integration of machine learning and molecular simulation could produce synergistic effect for interpreting and predicting pharmaceutical formulations. In conclusion, the developed predictive models were able to quickly and accurately predict the solubilizing capacity of CD systems. Current research has taken an important step toward the application of machine learning in pharmaceutical formulation design.

show abstract

3D-QSAR for binding constants of β-cyclodextrin host-guest complexes by utilising spectrophores as molecular descriptors

Jeschke

Cole

2019

Chemosphere

View full text Add to dashboard Cite

3D molecular fragment descriptors for structure–property modeling: predicting the free energies for the complexation between antipodal guests and β-cyclodextrins

Cited by 5 publications

References 51 publications

Predictive Models for HOMO and LUMO Energies of N‐Donor Heterocycles as Ligands for Lanthanides Separation

Predictive Models for HOMO and LUMO Energies of N‐Donor Heterocycles as Ligands for Lanthanides Separation

Predicting complexation performance between cyclodextrins and guest molecules by integrated machine learning and molecular modeling techniques

3D-QSAR for binding constants of β-cyclodextrin host-guest complexes by utilising spectrophores as molecular descriptors

Contact Info

Product

Resources

About