Abstract
AlphaFold, a deep learning-based platform widely used to predict protein and peptide structures, was employed in this study to model the self-assembling peptide RFC, which demonstrated a stable α-helical structure with high confidence. This structural prediction was supported by experimental analyses, which revealed the peptide's ability to form dense fibrillar networks and robust hydrogels, particularly at higher concentrations. These hydrogels effectively supported the 3D culture of endometrial cancer organoids, which retained key tumor characteristics, including high proliferative activity and resistance to platinum-based drugs. Among tested therapeutics, Doxorubicin showed the strongest efficacy, significantly reducing organoid viability. This study highlights the predictive power of AlphaFold in elucidating peptide structures and guiding biomaterial development. The RFC hydrogel, combined with organoid modeling, represents a promising platform for advancing cancer research and precision medicine. These findings demonstrate the synergistic value of computational tools like AlphaFold and experimental approaches in creating innovative solutions for challenging biomedical applications.