Apigenin Cocrystals: From Computational Prescreening to Physicochemical Property Characterization

Makadia, Jay; Seaton, Colin C.; Li, Mingzhong

doi:10.1021/acs.cgd.3c00030

Cited by 3 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, in order to evaluate the predictive performance of our models on new cocrystals, we conducted a literature search and identified five Apigenin cocrystals that were discovered after our initial data compilation and, therefore, not part of our original data set. These cocrystals were thoroughly confirmed in the original manuscript Figure S3 demonstrates that the Ensemble model is able to predict four out of five cocrystals before batchwise training and all five cocrystals after batchwise training.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning-Guided Prediction of Cocrystals Using Point Cloud-Based Molecular Representation

Ahmadi,

Ghanavati,

Rohani

2024

Chem. Mater.

View full text Add to dashboard Cite

The design and synthesis of cocrystals have emerged as promising crystal engineering strategies for enhancing the physicochemical properties of a diverse range of target molecules. A prediction strategy to identify whether a pair of target and auxiliary molecules would form a cocrystal can greatly accelerate the process of cocrystal discovery. In this study, we compiled and performed DFT calculations for 12,776 molecules (6,388 cocrystals). All entries in the database were obtained from experimental attempts reported in the literature. Electrostatic potential (ESP) surfaces were then extracted from the DFT results and used for the development of four machine learning models (PointNet, ANN, RF, Ensemble). The Ensemble model, leveraging the complementary strengths of the PointNet, ANN, and RF models, demonstrated superior discriminatory performance with a BACC (0.942) and an AUC (0.986) on the unseen test data subset. To assess the performance of the models on individual molecules, we separated the cocrystals of caffeine, fumaric acid, and salicylic acid from the overall database. The Ensemble model exhibited remarkable robustness, classifying the 312 cocrystals in this subset into their respective classes, with an average BACC of 98%. Furthermore, through conducting data analysis, 132 batches of cocrystal instances were gathered. After three batches were excluded, our proposed models were tested with these previously unseen molecules both before and after implementation of a batchwise retraining method.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Machine Learning-Guided Prediction of Cocrystals Using Point Cloud-Based Molecular Representation

Ahmadi,

Ghanavati,

Rohani

2024

Chem. Mater.

View full text Add to dashboard Cite

show abstract

A pharmaceutical cocrystal of apigenin with piperazine: Preparation, structural characterization, and dissolution performance

Zhang,

Shen,

Zhang

et al. 2024

Journal of Molecular Structure

View full text Add to dashboard Cite

Rational Design of the Carbamazepine Ternary Cocrystals

Boycov,

Drozd,

Manin

et al. 2024

Crystal Growth & Design

View full text Add to dashboard Cite

The first ternary cocrystals of carbamazepine (CBZ) were successfully identified through a large-scale screening. A design strategy involved the use of an aliphatic dicarboxylic acid to link CBZ and a third component into a hydrogen-bonded trimeric unit. Out of the 10 dicarboxylic acids tested, only malonic acid produced a positive response in the attempt to obtain the CBZ ternary cocrystals with benzamide and picolinamide. The crystal structures of the novel ternary cocrystals obtained by vapor diffusion crystallization were determined by single-crystal X-ray diffraction. Structural analysis revealed that the ternary cocrystals are isostructural and exhibit the packing of trimers into ladder-like chains. The relationship between the CBZ binary and ternary cocrystals was confirmed by comparing the crystal structures. The cocrystal solubility method was applied to estimate the thermodynamic parameters of the ternary cocrystal formation. The negative values of the Gibbs free energy, enthalpy, and entropy indicate that the reaction of ternary cocrystal formation is a thermodynamically favored process and driven by enthalpy. Despite the isostructural nature, the physicochemical properties of the ternary cocrystals, including melting point and thermodynamic solubility, are strongly influenced by the variable coformer.

show abstract

Apigenin Cocrystals: From Computational Prescreening to Physicochemical Property Characterization

Cited by 3 publications

References 35 publications

Machine Learning-Guided Prediction of Cocrystals Using Point Cloud-Based Molecular Representation

Machine Learning-Guided Prediction of Cocrystals Using Point Cloud-Based Molecular Representation

A pharmaceutical cocrystal of apigenin with piperazine: Preparation, structural characterization, and dissolution performance

Rational Design of the Carbamazepine Ternary Cocrystals

Contact Info

Product

Resources

About