Biomineralized SERS Nanotags Encode Biomolecular Identity into Machine Learning-Resolvable Fingerprints.
The study reports that biomolecule-directed gold nanoparticle biomineralization produces SERS fingerprints that machine-learning models distinguish across amino acids and between patient-derived pediatric osteosarcoma and neuroblastoma exosomes, with 85.9% tumor-classification accuracy.
Open original publication →What the AI sees
The study reports that biomolecule-directed gold nanoparticle biomineralization produces SERS fingerprints that machine-learning models distinguish across amino acids and between patient-derived pediatric osteosarcoma and neuroblastoma exosomes, with 85.9% tumor-classification accuracy.
Research significance
Evidence is limited to preclinical classification of tumor-derived exosome fingerprints; if independently validated in clinically collected samples, the platform could potentially support pediatric cancer diagnosis, disease monitoring, or treatment selection, but no therapeutic intervention or outcome benefit is demonstrated.
Source abstract
Surface-enhanced Raman scattering (SERS) nanotags provide highly sensitive platforms for molecular analysis but often require extensive customization to generate target-specific optical signatures. Biomineralization, in which biomolecules mediate inorganic material synthesis, offers a versatile yet underexplored strategy for generating functional SERS nanotags. Here, we demonstrate that biomolecule-directed biomineralization of gold nanoparticles (AuNPs) using amino acids and exosomes generates distinct nano-bio interfacial architectures that encode biomolecular identity into machine learning-resolvable SERS fingerprints through modulation of plasmonic coupling and Raman reporter organization. As a proof-of-concept system, amino acid-biomineralized AuNPs were synthesized using biomolecules with diverse physicochemical properties, including differences in size, polarity, and charge. The resulting nanotags were characterized using UV-vis spectroscopy, SERS spectroscopy, dynamic light scattering (DLS), and transmission electron microscopy (TEM). Random forest and support vector machine (SVM) models successfully differentiated amino acid-dependent SERS signatures with near-perfect classification performance. Extending this approach to a biologically complex preclinical cancer model, exosome-biomineralized AuNP nanotags were generated using exosomes derived from clinically relevant pediatric patient-derived osteosarcoma and neuroblastoma tumors. Distinct exosome-dependent spectral fingerprints enabled 85.9% classification accuracy through a regularized logistic regression model, while Shapley Additive exPlanations (SHAP) and t-distributed stochastic neighbor embedding (t-SNE) analyses identified diagnostically relevant spectral regions and visualized clustering between tumor classes. Collectively, this work establishes biomineralization as a strategy for encoding biomolecular identity into computationally resolvable optical fingerprints through engineered nano-bio interfaces, providing a versatile framework for machine learning-enabled classification of complex biological samples.