A novel approach based on supervised machine-learning is proposed to predict the solubility of drugs and drug-like molecules in mixtures of organic solvents. Similar to quantitative structure-property relationship (QSPR) models, different solvent types are identified by molecular descriptors, which, in this study, are considered as UNIFAC subgroups. To overcome the potential lack of UNIFAC subgroups for the complex Active Pharmaceutical Ingredients (APIs) currently developed in the pharmaceutical industry, the API molecule is considered as a unique entity in the proposed modelling approach. Therefore, API solubility is predicted as a function of temperature, functional subgroups of the solvents and composition of the solvent mixture; in turn, regressors' correlation is handled through Partial Least-Squares (PLS) regression. The method is developed and tested with experimental data of a real API and 14 organic solvents that are industrially employed for crystallisation. Solubility predictions are accurate and precise for single solvents, binary mixtures and ternary mixtures of organic solvents at different compositions and temperatures, with a determination coefficient R² ≥ 0.90. To further test the applicability of the model, the proposed approach is applied to 9 literature organic solubility datasets of drugs and drug-like compounds and compared to benchmark solubility models in the literature. Results show that the proposed approach provides satisfactory predictions: the majority of validation and calibration data have R² = 0.95-0.99; the ratio between RMSE (root mean squared error) of the proposed method and the range of measured solubility values is from 1 to 3 orders of magnitude smaller than the RMSE ratio obtained by the benchmark models.

Mixed Suspension-Mixed Product Removal (MSMPR) crystallizers are widely implemented as continuous crystallizers, allowing enhanced efficiency, flexibility and product quality compared to the currently dominant batch crystallizer designs. Establishing cost effective continuous crystallization process configurations for societally- and economically-important active pharmaceutical ingredients (APIs) is essential to ensure the successful implementation of fully end-to-end continuous pharmaceutical manufacturing (CPM) campaigns. Process modelling and optimization enable rapid, systematic technoeconomic evaluation and comparison of process alternatives. This paper pursues total cost minimization of different MSMPR crystallizer configurations of three APIs (cyclosporine, paracetamol and aliskiren) whose continuous MSMPR crystallization has been experimentally demonstrated. Nonlinear optimization for total cost configuration is implemented for 1-3 crystallizers for different plant API capacities with crystallizer temperatures and residence times as decision variables. The optimization results show that the optimal number of crystallizers is dependent on plant capacity; implementing one crystallizer is preferred for all three APIs at 10² kg y^-1, however two crystallizers at 10⁴ kg y^-1 is preferable for cyclosporine and paracetamol, whilst two and three crystallizers are preferable for aliskiren at 10³ and 10⁴ kg y^-1, respectively. These trends are observed due to the increasing dominance of operating expenditures on total costs at increased capacities, making the benefits of implementing more crystallizers (enhanced yields, reduced utility loads) worth the increased capital expenditures. The process modelling and optimization methodology allows rapid technoeconomic evaluation and comparison of MSMPR crystallizer configurations for different APIs towards systematic selection of cost optimal continuous crystallizer designs for pharmaceutical manufacturing.