Bio-Functional Investigation and AI-Driven Target Interaction Prediction of Chrono Control Penta as a Plant Multifunctional Dermo Cosmetic Peptide

Skin aging is influenced by both internal and external factors, resulting in wrinkles, decreased elasticity and irregular pigmentation. Hyaluronic acid (HA), a key component of the extracellular matrix, is essential for skin hydration and structural support. Peptides, short amino acid chains, have gained attention in cosmetics due to their multifunctional biological activities. This study explored the moisturizing and metal-chelating properties of Chrono Control Penta (S-Cannabis Sativa-pentapeptide-1), a novel plant-derived peptide whose sequence is WVSPL. In vitro, it chelated iron ions up to 17.86 ± 2.50% and copper ions up to 47.08 ± 1.49% at 10 mM and 3 mM, respectively. Western blot and Enzyme-Linked Immunosorbent Assay (ELISA) analysis showed that, under H2O2-induced stress, Chrono Control Penta increased hyaluronan synthase 2 (HAS2) production by 81.72% in BJ-5ta fibroblasts and enhanced HA secretion by 20.11% compared to simulated aging conditions alone, respectively. Furthermore, experiments carried out with the Franz diffusion cell and human full thickness skin demonstrated the peptide’s ability to penetrate the skin layers and even diffuse laterally with a quantified peptide skin biodistribution accounting for 0.095/0.06 nM/mg in 6 h. Advanced AI-based modeling (AlphaFold2, RosettaFold) and docking analysis revealed stable peptide-peptide transporter 2 (PEPT2) interactions, supporting carrier-mediated skin permeation and linking computational predictions with experimental diffusion data. Hence, this study extends previous evidence on the cosmetic efficacy of Chrono Control Penta by (i) adding mechanistic insights into metal chelation and HAS2/HA modulation, (ii) rigorously quantifying local skin penetration and lateral diffusion with HPLC-MS/MS, and (iii) providing a plausible mechanistic link between skin biodistribution and PEPT2-mediated transport based on deep learning structural models.