The material library is an emerging, new data-driven approach for developing pharmaceutical process models. How many materials or samples should be involved in a particular application scenario is unclear, and the impact of sample size on process modeling is worth discussing. In this work, the direct compression process was taken as the research object, and the effects of different sample sizes of material libraries on partial least squares (PLS) modeling in the prediction of tablet tensile strength were investigated. A primary material library comprising 45 materials was built. Then, material subsets containing 5 × i (i = 1, 2, 3, …, 8) materials were sampled from the primary material library. Each subset underwent sampling 1000 times to analyze variations in model fitting performance. Both hierarchical sampling and random sampling were employed and compared, with hierarchical sampling implemented with the help of the tabletability classification index d. For each subset, modeling data were organized, incorporating 18 physical properties and tableting pressure as the independent variables and tablet tensile strength as the dependent variable. A series of chemometric indicators was used to assess model performance and find important materials for model training. It was found that the minimum R² and RMSE values reached their maximum, and the corresponding values were kept almost unchanged when the sample sizes varied from 20 to 45. When the sample size was smaller than 15, the hierarchical sampling method was more reliable in avoiding low-quality few-shot PLS models than the random sampling method. Two important materials were identified as useful for building an initial material library. Overall, this work demonstrated that as the number of materials increased, the model’s reliability improved. It also highlighted the potential for effective few-shot modeling on a small material library by controlling its information richness.

Background/Objectives: Tablet is the most popular oral solid dosage form, and high-shear wet granulation and tableting (HSWGT) is a versatile technique for manufacturing tablets. The conventional pharmaceutical development for HSWGT is carried out in a step-by-step mode, which is inefficient and may result in local optimal solutions. Inspired by the co-design philosophy, a formulation–process–product integrated design (FPPID) framework is innovatively brought forward to enable the target-oriented and simultaneous exploration of the formulation design space and the process design space. Methods: A combination of strategies, such as a material library, model-driven design (MDD), and simulation-supported solution generation, are used to manage the complexity of the multi-step development processes of HSWGT. The process model was developed at the intermediate level by incorporating dimensionless parameters from the wet granulation regime map approach into the process of the partial least square (PLS) model. The tablets tensile strength (TS) and solid fraction (SF) could be predicted from the starting materials’ properties and process parameters. The material library was used to diversify the model input and improve the model’s generalization ability. Furtherly, the mixture properties calculation model and the process model were interconnected. Results: A four-step FPPID methodology including the target definition, the formulation simulation, the process simulation, and the solution generation was implemented. The performance of FPPID was demonstrated through the efficient development of high-drug-loading tablets. Conclusions: As a holistic design method, the proposed FPPID offers great opportunity for designers to handle the complex interplay in the sequential development stages, facilitate instant decisions, and accelerate product development.

Background: Twin-screw wet granulation (TSWG) is a promising continuous manufacturing technology, featuring high operational flexibility, short residence time and consistent quality. The process development of TSWG relies on the synergy of material characterization, screw configuration, and process parameter optimization. Objective: In order to fully combine various design variables, and to accelerate the process development of TSWG, a material–process–equipment integrated design (MPEID) methodology is first applied to the TSWG process of Guizhi Fuling capsule, a botanical drug product. Methods: First, an equivalent formulation was designed to save trial costs. Second, 3D printing technology was used to customize both conveying and kneading elements with the lead, with the kneading discs stagger angle (SA) and the thickness (thick) as screw element variables. The position of fabricated kneading elements was varied to generate different screw configurations. Then, the critical screw parameters (CSPs) and critical process parameters (CPPs) were identified by a two-step design of experiment (DOE) toward optimizing granule quality. Results: As a result, the SA and thick were identified as CSPs, and the liquid-to-solid ratio was the CPP. Under the optimal TSWG process conditions, the twin-screw granulator could be operated under low torque (i.e., average torque = 1.48 ± 0.06 Nm). The dried granules exhibited superior flowability, as well as highly consistent particle size distribution with industrial batches. After capsule filling, the dissolution test results showed the prepared Guizhi Fuling capsules reached 93.7% cumulative dissolution at 15 min, which approached that of commercial capsules (i.e., 93.0%). Conclusions: This study demonstrated the feasibility of proposed MPEID methodology, supporting the efficient and cost-effective process development of TSWG.