Innovative functional materials integrating host–guest complexes in cryogels offer promising applications in topical drug delivery, enhancing drug solubility and stability. In this study, we designed and developed a cryogel-based patch for acne treatment by polymerizing an acrylate-functionalized γ-cyclodextrin (γ-CD) and trimethoprim (TMP) inclusion complex with [2-(acryloyloxy)ethyl]trimethylammonium chloride (AETMA) at low temperatures. A multistep workflow was applied to synthesize the inclusion complex via mortar-assisted kneading, followed by cryogel formulation through radical cryopolymerization. The resulting hybrid system leverages the cationic nature of AETMA to promote adhesion and electrostatic interactions with the skin surface. At the same time, γ-CD serves as a drug reservoir, facilitating sustained release of the drug. The system was characterized by FT-IR, TGA, and SEM analyses. In vitro release studies demonstrated a sustained TMP release profile, best described by the Korsmeyer–Peppas diffusion model. Antibacterial assays confirmed the system’s effectiveness against Staphylococcus aureus, supporting its potential for localized and prolonged acne treatment. Moreover, cytocompatibility tests demonstrated that the formulation is biocompatible, further validating its suitability for topical application.

Virtual screening (VS) workflows often combine structure- and ligand-based methods; however, their value depends on the number of compounds that can be tested. We benchmarked 20 fixed-budget strategies derived from molecular docking (GNINA CNN score), maximum common substructure (MCS) similarity, and a calibrated machine-learning (ML)-QSAR classifier across five pharmacologically diverse targets. Individual methods, best-rank and worst-rank fusion, mean-rank consensus, and sequential funnels were evaluated at 1%, 5%, and 10% library fractions, with every strategy selecting the same number of compounds. ML-QSAR was the strongest standalone method, recovering 47.6%, 81.6%, and 84.4% of actives at the three cutoffs. At the 1% budget, ML-QSAR achieved the highest mean hit recovery (47.6% recall; 99.2% precision). At 5% and 10%, best-rank fusion of QSAR and MCS produced the highest mean recall (83.2% and 86.4%). Among the sequential workflows, QSAR → MCS achieved the highest 1% hit recovery (45.2 ± 3.3% recall), whereas docking-first funnels consistently underperformed under the default, non-optimized conditions evaluated in this study. Target-level results showed substantial variability in MCS-containing workflows and limited benefits from adding docking without target-specific optimization. Under matched assay budgets, a validated ligand-based predictor or a simple two-method rank-fusion scheme provided the highest observed mean hit recovery without requiring elaborate integration.