QSPR for the prediction of critical micelle concentration of different classes of surfactants using machine learning algorithms.

The determination of the critical micelle concentration (CMC) is a crucial factor when evaluating surfactants, making it an essential tool in studying the properties of surfactants in various industrial fields. In this present research, we assembled a comprehensive set of 593 different classes of surfactants including, anionic, cationic, nonionic, zwitterionic, and Gemini surfactants to establish a link between their molecular structure and the negative logarithmic value of critical micelle concentration (pCMC) utilizing quantitative structure-property relationship (QSPR) methodologies. Statistical analysis revealed that a set of 14 significant Mordred descriptors (SlogP, GATS6d, nAcid, GATS8dv, GATS4dv, PEOE_VSA11, GATS8d, ATS0p, GATS1d, MATS5p, GATS3d, NdssC, GATS6dv and EState_VSA4), along with temperature, served as appropriate inputs. Different machine learning methods, such as multiple linear regression (MLR), random forest regression (RFR), artificial neural network (ANN), and support vector regression (SVM), were employed in this study to build QSPR models. According to the statistical coefficients of QSPR models, SVR with Dragonfly hyperparameter optimization (SVR-DA) was the most accurate in predicting pCMC values, achieving (R2 = 0.9740, Q2 = 0.9739, r‾m2 = 0.9627, and Δrm2 = 0.0244) for the entire dataset.

Balancing competing objectives in bigel formulations using many-objective optimization algorithms and different decision-making methods.

Many-objective optimization, which deals with balancing multiple competing objectives to find compromised solutions, is essential for solving complex problems. This study explores evolutionary algorithms for optimizing the microstructural, rheological, stability, and drug release properties of bigel systems formulated using structured almond oil, mixed organogelators, and carbopol. The oleogel was identified as the dispersed phase, with droplet sizes ranging from 1.43 µm to 7.37 µm, indicating improved characteristics compared to other bigels. Each formulation exhibited non-Newtonian shear-thinning and thixotropic behaviors, which were positively influenced by the proportions of the excipients. After undergoing multiple stress cycles, highly concentrated bigels exhibited phase separation. Unexpectedly, bigels with lower viscosity exhibited reduced rates of drug release. FT-IR and HPLC analyses confirmed the compatibility and stability of drug-excipient interactions, with impurities remaining below 4%. This study emphasizes the complex interactions within mixed lipid-based bigels, requiring many-objective optimization techniques to address conflicting objectives. The objectives of optimization involve simultaneously minimizing microstructural properties while maximizing structural recovery and drug release properties. This led to conflicting objectives, where achieving higher structural recovery did not align with the desired drug release rate. Additionally, more stable formulations did not meet the optimal microstructural objectives. To resolve these conflicts, an RSM-MaOEAs approach was applied, employing various decision-making methods. Among EAs, RSM-RVEA notably achieved exceptional convergence. Furthermore, three MaOEAs-integrated decision-making methods-WSM, WPM, NED-and the RSM-desirability, offered potential solutions. Overall, this research proposes a robust framework for compromising the bigels' performance and stability, with broader applications in drug delivery and related fields.