Recent advancements in artificial intelligence have enabled the optimization of gold nanoparticle (AuNP) biosynthesis, demonstrating significant anticancer potential both in vitro and in vivo.
The Promise of Gold Nanoparticles
Gold nanoparticles (AuNPs) exhibit unique properties such as a high surface area-to-volume ratio, tunable size, shape, and exceptional electronic characteristics. These features make them highly suitable for applications in drug delivery, diagnostics, and cancer therapies. Despite their promise, traditional chemical synthesis methods have limitations, including the use of toxic chemicals, high energy requirements, and environmental concerns. Green biosynthesis, utilizing natural microorganisms like Streptomyces flavolimosus, addresses these issues, offering a cost-effective, sustainable, and scalable alternative.
Research Aim & Objectives
The study aimed to optimize the green synthesis of AuNPs using Streptomyces flavolimosus through artificial intelligence-based methods and evaluate their anticancer efficacy. The team, comprising researchers from the City of Scientific Research and Technological Applications and Mansoura University, published their findings in Scientific Reports. This marks the first use of AI in optimizing actinomycete-mediated AuNP biosynthesis.
Research Methods
Two advanced computational approaches—central composite design (CCD) and artificial neural networks (ANN)—were employed to optimize the biosynthesis process. Key variables studied included temperature (25–45°C), incubation period (2–6 days), initial pH levels (4–8), and gold chloride (HAuCl4) concentration (200–1000 µg/mL). ANN was used to predict outcomes based on experimental data and refine the synthesis conditions. Optimal results were achieved with the cell-free supernatant of Streptomyces flavolimosus, yielding spherical nanoparticles (4–20 nm) characterized by techniques such as UV-Vis spectroscopy, TEM, and FTIR.
Results
The study yielded several key findings, which demonstrated the significant potential of AI-optimized AuNPs in cancer therapy:
Optimal Biosynthesis Conditions: The maximum AuNP yield of 866.29 µg/mL was achieved under specific conditions: 35°C, 4 days of incubation, pH 6, and 1000 µg/mL HAuCl4 concentration.
Characterization of Nanoparticles:
- Size: AuNPs were predominantly 4–20 nm in diameter.
- Surface Charge: Zeta potential was measured at -10.9 mV, indicating colloidal stability.
- Composition: FTIR analysis revealed the presence of functional groups such as hydroxyl, carbonyl, and amines on the nanoparticle surface, confirming effective biosynthesis and stabilization.
In Vitro Anticancer Activity:
- Against MCF-7 (breast cancer): IC50 = 13.4 ± 0.44 μg/mL.
- Against HeLa (cervical cancer): IC50 = 13.8 ± 0.45 μg/mL.
In Vivo Antitumor Activity:
- AuNPs significantly reduced tumor volume and weight in mice bearing Ehrlich ascites carcinoma.
- Treated groups exhibited a notable reduction in viable tumor cells compared to controls.
Model Validation: ANN outperformed CCD, with predicted AuNP biosynthesis values showing greater alignment with experimental outcomes. The R² value for ANN was 0.9885, highlighting its accuracy and reliability.
The Future of Nanomedicine
The researchers concluded that artificial intelligence, particularly the use of artificial neural networks (ANN), is a powerful tool for optimizing green biosynthesis processes. This study demonstrated the successful synthesis of gold nanoparticles (AuNPs) using the cell-free supernatant of Streptomyces flavolimosus, with ANN providing accurate predictions for optimizing bioprocess conditions. The biosynthesized AuNPs showed promising antitumor potential, validated through significant reductions in tumor growth both in vitro and in vivo.
The findings highlight the advantages of green synthesis methods, such as sustainability, low energy requirements, and environmental safety, over traditional chemical and physical synthesis approaches. The researchers emphasized that integrating biological systems like actinomycetes with advanced computational tools can offer a scalable, reproducible, and eco-friendly solution for nanoparticle production. Furthermore, the successful demonstration of ANN’s predictive capabilities positions this methodology as a robust framework for future nanotechnology applications.
Reference:
El-Naggar, Noura El-Ahmady, et al. “Artificial neural network approach for prediction of AuNPs biosynthesis by Streptomyces flavolimosus, characterization, antitumor potency in-vitro and in-vivo against Ehrlich ascites carcinoma.” Scientific Reports 13.1 (2023): 12686.