Exploration of the Solubility Hyperspace of Selected Active Pharmaceutical Ingredients in Choline- and Betaine-Based Deep Eutectic Solvents: Machine Learning Modeling and Experimental Validation – PubMed Black Hawk Supplements

BLACK HAWK: High quality lions mane supplement for adrenal fatigue

Published article

Deep eutectic solvents (DESs) are popular green media used for various industrial, pharmaceutical, and biomedical applications. However, the possible compositions of eutectic systems are so numerous that it is impossible to study all of them experimentally. To remedy this limitation, the solubility landscape of selected active pharmaceutical ingredients (APIs) in choline chloride- and betaine-based deep eutectic solvents was explored using theoretical models based on machine learning. The…
Black Hawk Supplements, best supplements in the UK

Exploration of the Solubility Hyperspace of Selected Active Pharmaceutical Ingredients in Choline- and Betaine-Based Deep Eutectic Solvents: Machine Learning Modeling and Experimental Validation - PubMed

Exploration of the Solubility Hyperspace of Selected Active Pharmaceutical Ingredients in Choline- and Betaine-Based Deep Eutectic Solvents: Machine Learning Modeling and Experimental Validation

Piotr Cysewski et al. Molecules. .

Abstract

Deep eutectic solvents (DESs) are popular green media used for various industrial, pharmaceutical, and biomedical applications. However, the possible compositions of eutectic systems are so numerous that it is impossible to study all of them experimentally. To remedy this limitation, the solubility landscape of selected active pharmaceutical ingredients (APIs) in choline chloride- and betaine-based deep eutectic solvents was explored using theoretical models based on machine learning. The available solubility data for the selected APIs, comprising a total of 8014 data points, were collected for the available neat solvents, binary solvent mixtures, and DESs. This set was augmented with new measurements for the popular sulfa drugs in dry DESs. The descriptors used in the machine learning protocol were obtained from the σ-profiles of the considered molecules computed within the COSMO-RS framework. A combination of six sets of descriptors and 36 regressors were tested. Taking into account both accuracy and generalization, it was concluded that the best regressor is nuSVR regressor-based predictive models trained using the relative intermolecular interactions and a twelve-step averaged simplification of the relative σ-profiles.

Keywords: COSMO-RS; DES; green solvents; machine learning; solubility; sulfonamides; σ-profiles.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1

Mole fraction solubilities of four different sulfonamides in DESs composed of choline chloride (ChCl) or betaine (BI) with 1,2-propanediol (P2D), ethylene glycol (ETG), diethylene glycol (DEG), or triethylene glycol (TEG) in a 1:2 molar ratio at various temperatures.

Figure 2
Figure 2

Collection of the API solubility values, expressed as the decadal logarithm of the mole fraction, in choline chloride and betaine deep eutectic solvents in ambient conditions. Newly measured values are marked with black borders. Only the 1:2 proportion of HBA and HBD was included. Colors map the span of solubility values. APIs include the following: caffeine (CAF), theobromine (THB), theophylline (THP), ferulic acid (FA), edaravone (EDA), ibuprofen (IB), ketoprofen (KP), curcumin (CUR), dapsone (DAP), probenecid (PC), sulfacetamide (SCM), sulfamethazine (SMZ), sulfamethoxazole (SMA), sulfanilamide (SNM), and sulfasalazine (SSZ). HBDs: 1,2-propanediol (P2D), ethylene glycol (ETG), diethylene glycol (DEG), triethylene glycol (TEG), 1,3-butanediol (B3D), glycerol (GLY), fructose (FRU), glucose (GLU), sorbitol (SOR), xylitol (XYL), sucrose (SUC), and maltose (MAL).

Figure 3
Figure 3

Relationship of experimental solubility and values computed using COSMO-RS for all the included APIs in neat solvents, binary solvent mixtures, and all studied DES systems. The temperature relationships and concentration dependencies of saturated solutions were taken into account.

Figure 4
Figure 4

Relationship of experimental solubility and values computed using COSMO-RS for the subset of data presented in Figure 1, characterizing only APIs in DES systems. Open circles mark newly measured sulfonamides, and open triangles point out selected HBD counterparts of the studied DESs. For acronyms and their meanings, refer to Figure 1.

Figure 5
Figure 5

Comparison of nuSVR model’s performance, the parameters of which were tuned on all six descriptors sets. Lines represent the percentage of outliers and bars stand for MAPE of train and test subsets.

Figure 6
Figure 6

Correlation between experimental solubility values (N = 8014) and those computed using the NuSVR regressor trained on the B2 set of descriptors. Dotted and dashed lines represent values corresponding to three times the standard deviation computed for the whole dataset or test subset, respectively.

Figure 7
Figure 7

The presentation of the individual σ–potentials enabling the computation of the actual values of Δσpot for SMZ + ChCl + TEG + water at T = 25 °C. Three types of resolutions are plotted, illustrating the three sets of molecular descriptors used in the machine learning protocol, namely open circles, which denote a full distribution of 61 points (descriptors set C) and two ways of averaging. The grey solid step line represents every six points (descriptor set B), and the dotted black step line characterizes the average over twelve points (descriptor set A).

Similar articles

References

    1. Kumar V., Bansal V., Madhavan A., Kumar M., Sindhu R., Awasthi M.K., Binod P., Saran S. Active pharmaceutical ingredient (API) chemicals: A critical review of current biotechnological approaches. Bioengineered. 2022;13:4309–4327. doi: 10.1080/21655979.2022.2031412. – DOI – PMC – PubMed
    1. Kątny M., Frankowski M. Impurities in Drug Products and Active Pharmaceutical Ingredients. Crit. Rev. Anal. Chem. 2017;47:187–193. doi: 10.1080/10408347.2016.1242401. – DOI – PubMed
    1. Martínez F., Jouyban A., Acree W.E. Pharmaceuticals solubility is still nowadays widely studied everywhere. Pharm. Sci. 2017;23:1–2. doi: 10.15171/PS.2017.01. – DOI
    1. Savjani K.T., Gajjar A.K., Savjani J.K. Drug Solubility: Importance and Enhancement Techniques. ISRN Pharm. 2012;2012:1–10. doi: 10.5402/2012/195727. – DOI – PMC – PubMed
    1. Coltescu A.R., Butnariu M., Sarac I. The importance of solubility for new drug molecules. Biomed. Pharmacol. J. 2020;13:577–583. doi: 10.13005/bpj/1920. – DOI

MeSH terms

Substances

Grants and funding

This research received no external funding.

LinkOut – more resources

BLACK HAWK: Best shilajit supplement for dads

Read the original publication:

Exploration of the Solubility Hyperspace of Selected Active Pharmaceutical Ingredients in Choline- and Betaine-Based Deep Eutectic Solvents: Machine Learning Modeling and Experimental Validation – PubMed