Prediction and design of cyclodextrin inclusion complexes formation via machine learning-based strategies

Ma, Yiming; Niu, Yue; Yang, Huaiyu; Dai, Jiayu; Lin, Jiawei; Wang, Huiqi; Wu, Songgu; Yin, Qiuxiang; Zhou, Lu; Gong, Junbo

doi:10.1016/j.ces.2022.117946

Cited by 10 publications

(6 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The two endothermic peaks at 270 and 312 °C in the DSC curve correspond to the two weight loss steps observed in the TGA curve, thereby indicating the occurrence of two decomposition stages for IC (Figure D). It can be inferred that the interactions among PD, water, and β-CD work for the changes in the thermal behavior of the complex, which alters the dehydration temperature. , Evidence for these interactions can also be supported by the frequency shifts on FTIR spectra of PD/β-CD (Figure B), especially for the changes in the absorption bands of the −OH group from 3290 to 3269 cm –1 …”

Section: Resultsmentioning

confidence: 99%

Insights into Structural Features and Ternary Phase Diagrams of Prednisolone/β-Cyclodextrin Inclusion Complex

Niu

Yin

et al. 2023

Crystal Growth & Design

Self Cite

View full text Add to dashboard Cite

The poor water solubility of prednisolone (PD) can be improved by forming inclusion complexes with β-cyclodextrin (β-CD). Here, the PD/β-CD complex with a 1:2 molar ratio was successfully prepared by the saturated solution method, and its single-crystal structure was determined for the first time. The interactions between the host and guest molecules were investigated by quantum chemical methods. The thermodynamic phase diagram of PD/β-CD was established by using the static equilibrium method. The effects of the temperature and solvent composition on the preparation process of PD/β-CD were further studied. Molecular dynamics simulations were conducted to probe the formation mechanism of PD/β-CD, thereby verifying the phase region. In addition, hydrogen bonding facilitated the inclusion of the PD molecule within the CD dimer. van der Waals forces played a crucial role in the PD/β-CD formation. This study contributes to our better understanding of the structural features and formation mechanism of inclusion complexes and offers valuable insights into the industrial production of drug inclusion complexes.

show abstract

Section: Resultsmentioning

confidence: 99%

Insights into Structural Features and Ternary Phase Diagrams of Prednisolone/β-Cyclodextrin Inclusion Complex

Niu

Yin

et al. 2023

Crystal Growth & Design

Self Cite

View full text Add to dashboard Cite

show abstract

“…Due to the excessive number of features, the model will be too complex and the training time will be long. To improve the data processing speed, save time and cost, and retain the molecular structural information to the maximum extent, PCA was used to reduce the dimension of all 1545 features . The cumulative contribution of features was retained at 0.85, and the final features were compressed into 12, as shown in Figure .…”

Section: Methodsmentioning

confidence: 99%

“…However, compared with artificial neural networks (ANNs) and deep learning, they tend to show only moderate predictive accuracy. 22 This might be caused by researchers' tendency to broaden the application scope of the model and pay too much attention to the increase in the number of samples or the diversity of the structure in the database. At the same time, this is also the reason why these models have poor interpretability, and it is difficult to analyze the model through the molecular structural information.…”

Section: Introductionmentioning

confidence: 99%

“…Their main idea is to complete the model construction by combining various descriptors or molecular fingerprints through big data learning or extraction of features in cocrystal samples. − Among these models, traditional machine learning algorithms such as support vector machine (SVM), random forest (RF), and logistic regression (LR) algorithms provide useful guidelines for experimental design due to their more explicit scientific basis. However, compared with artificial neural networks (ANNs) and deep learning, they tend to show only moderate predictive accuracy . This might be caused by researchers’ tendency to broaden the application scope of the model and pay too much attention to the increase in the number of samples or the diversity of the structure in the database.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Prediction of Flavonoid Cocrystal Formation Combined with Experimental Validation

Yue,

Wang

2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

“…Our group has developed prediction models for screening the components of spherical particles 135 and inclusion com-plexes, 136 using ANN, SVM, and logistic regression (LR) algorithms in combination with molecular descriptors and solvation-free energy descriptors. Notably, models based on a combination of multiple ML algorithms (i.e., ANN, SVM, and LR) provided more accurate outcomes compared to those with a single algorithm.…”

Section: Screening and Optimization Of Crystallization Conditionsmentioning

confidence: 99%

Artificial Intelligence Assisted Pharmaceutical Crystallization

Zhu,

Zhang,

Wang

et al. 2024

Crystal Growth & Design

Self Cite

View full text Add to dashboard Cite

The ever-increasing demand for novel drug development has spurred the adaptation of conventional research methods in the era of artificial intelligence. Pharmaceutical crystallization, as an essential part of drug development, has become a thrilling research frontier that reduces screening labor via integrating automated high-throughput platforms with in situ monitoring and datadriven algorithms (e.g., machine learning) to predict physicochemical properties and various solid-state forms. In this review, we started with a primer to introduce the machine learning algorithms that are widely used in pharmaceutical crystallization. Then, we systematically summarized recent advancements on high-throughput platforms to acquire huge amounts of data sets, prediction of physicochemical properties based on abundant experimental data, optimization and monitoring of pharmaceutical crystallization process to screen crystallization conditions, and prediction of polymorphs and cocrystals. Finally, we discussed the challenges and opportunities in an endeavor to develop a fully automated pharmaceutical crystallization screening paradigm for ultimately realizing a selfdriving screening laboratory. This review highlights the frontier of artificial intelligence in pharmaceutical crystallization and offers a guideline for beginners to not only understand the basic principles of machine learning algorithms but also learn how to utilize machine learning to accelerate pharmaceutical crystallization development.

show abstract

Prediction and design of cyclodextrin inclusion complexes formation via machine learning-based strategies

Cited by 10 publications

References 48 publications

Insights into Structural Features and Ternary Phase Diagrams of Prednisolone/β-Cyclodextrin Inclusion Complex

Insights into Structural Features and Ternary Phase Diagrams of Prednisolone/β-Cyclodextrin Inclusion Complex

Machine Learning Prediction of Flavonoid Cocrystal Formation Combined with Experimental Validation

Artificial Intelligence Assisted Pharmaceutical Crystallization

Contact Info

Product

Resources

About