Invention:
This innovation is a nanotechnology- and artificial intelligence-powered platform that combines plasmonic gold nanomaterials (AuNMs) with machine learning (ML) to achieve high-throughput, selective, and broad-spectrum identification of potential inhibitors of amyloid beta aggregation. Proof of concept testing found that the platform can identify spectral features corresponding to early and late aggregation phases to accurately predict the specific stages of amyloid beta aggregation, which has not been demonstrated with similar screening methods. This innovation has the potential to extend to the discovery of potential aggregation inhibitors of three proteins associated with neurogenerative diseases, such as Alzheimer’s disease, and other biological applications.
Background:
Protein aggregation often begins with small, transient oligomers that are the most toxic and clinically relevant, but these species are difficult to identify due to their low concentrations, heterogeneity, and ability to quickly develop into larger fibrils. Conventional approaches frequently overlook these early intermediates or call for specialized equipment. Gold nanoparticle colorimetric biosensors, such as this innovation, exploit plasmonic optical properties, where protein aggregation induces measurable color or light-scattering changes, enabling highly sensitive detection. In addition, the integration of machine learning in these biosensors can further improve signal interpretation, sensitivity, and reliability.
Applications:
- Protein aggregation biosensor
- Gold nanoparticle-based biosensor
- Gold Nanomaterials (AuNMs) utilization
- AI and Machine Learning in medical diagnostics
- Real-time monitoring and predictive analytics (e.g. Alzheimer’s disease)
Advantages:
- High-throughput enabling faster diagnosis and treatment decisions
- Catalyzes and detects protein aggregation
- Analyze and predict protein aggregation characteristics
- Automatic identification of early and late aggregation phases
- Cost-effective
- Improved signal interpretation, sensitivity, and reliability
