Comments on "What if Cocrystallization Fails for Neutral Molecules? Screening Offered Eutectics as Alternate Pharmaceutical Materials: Leflunomide-A Case Study"

Acree, Jr. William E.; Jouyban, Abolghasem

doi:10.15171/ps.2019.51

Cited by 1 publication

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Drugs with outliers tend to have higher molecular weight and more acidic functional groups, which are not clearly expressed in the training set. In addition, it may also be influenced by the quality of the collected data, such as the validity of applied melting point and melting enthalpy data . Accordingly, these results also indicate the requirement of further expanding the dataset to adequately obtain the features of multiple drugs so that the solubility of the drug in various solvents can be more accurately predicted.…”

Section: Resultsmentioning

confidence: 99%

“…Acree Jr et al compared the reported melting point and melting enthalpy data of multiple drugs and found that data may be influenced by a number of factors, such as the experimental device, the method of experiment, and the purity of the experimental sample. 33 Therefore, in this work, according to the current problems of available models, we focused on developing an explainable strategy that combines molecular thermodynamics and machine learning to predict the solubility of drugs in various solvents. PC-SAFT was utilized to model drugs and solvents as a representative theory of molecular thermodynamics.…”

Section: Introductionmentioning

confidence: 99%

“…Meanwhile, some models met the problem of the validity of applied descriptors and poor solubility data. Acree Jr et al compared the reported melting point and melting enthalpy data of multiple drugs and found that data may be influenced by a number of factors, such as the experimental device, the method of experiment, and the purity of the experimental sample …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Novel Computational Approach by Combining Machine Learning with Molecular Thermodynamics for Predicting Drug Solubility in Solvents

2021

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

In this work, a novel strategy that combined molecular thermodynamic and machine learning was proposed to accurately predict the solubility of drugs in various solvents. The strategy was based on 16 molecular descriptors representing drug–drug interactions and drug–solvent interactions including physical parameters, pure perturbed-chain statistical associating fluid theory (PC-SAFT) parameters of drugs and solvents, and mixing rules. These molecular descriptors were inputted into five machine learning algorithms [multiple linear regression (MLR), artificial neural network (ANN), random forest (RF), extremely randomized trees (ET), and support vector machine (SVM)] to train the predictive model. A single-hidden-layer neural network was finally determined as the predictive model for predicting the solubility of drugs in various solvents. The drug solubility in the generalization evaluation set has also been successfully predicted, which indicates the good prediction performance of the model. Three directions for improving the model were summarized as adding molecular descriptors of drug–solvent interactions in the water system and drug–drug interactions in the organic solvent system and expanding the dataset to adequately obtain the features of multiple drugs. These findings show that the proposed model has the capability of solubility prediction, which is expected to provide important information for drug development and drug solvent screening.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation