A newly developed artificial intelligence-guided workflow has identified hydrogels as a promising option for delivering localized treatment for gum disease and preventing its progression, according to a news release.
Furthermore, the workflow identified guanosine monophosphate (GMP) and deoxyguanosine monophosphate (dGMP) as the most promising hydrogel candidates based on their antibacterial activity, biocompatibility, and effectiveness in treating periodontitis, according to the release dated July 1 from the West China School of Stomatology, Sichuan University.
“Both candidates successfully formed stable supramolecular hydrogels with favorable mechanical properties such as self-healing and shear-thinning behavior,” Hang Zhao, a professor at Sichuan University and lead researcher of the study, said in the release.
For the study, researchers combined AI with laboratory testing to identify new biomaterials for treating periodontitis. They compiled nine large public bioactivity datasets and trained machine-learning models to predict properties such as antibacterial activity, toxicity, antiviral potential, and anti-inflammatory effects using thousands of molecular descriptors.
After screening thousands of compounds, the highest-ranked candidates were synthesized and tested for hydrogel formation, mechanical strength, antibacterial activity against Porphyromonas gingivalis, biocompatibility, and effectiveness in mouse models of periodontitis. The AI-guided workflow identified GMP and dGMP as the two most promising hydrogel candidates, according to the release.
In mouse models with periodontitis, both hydrogels reduced bacterial levels and inflammation, preserved alveolar bone, and promoted tissue repair. Their therapeutic effects were comparable to those of minocycline. When administered early, the hydrogels helped prevent disease progression.
The findings demonstrate how AI may accelerate biomaterial discovery by quickly identifying the most promising candidates instead of relying solely on trial-and-error testing. The researchers believe this strategy could reduce development time and costs while improving the design of safe and effective biomaterials for clinical use, according to the release.
In the future, an AI-driven approach may accelerate the development of personalized hydrogels for drug delivery, wound healing, tissue engineering, regenerative medicine, and other oral health applications.
“In laboratory experiments, the hydrogels effectively inhibited Porphyromonas gingivalis while exhibiting excellent biocompatibility and minimal toxicity,” Zhao added.
