The Role of Artificial Intelligence in Designing Next-Generation Nanoformulations: A Comprehensive Review

Abstract

The integration of artificial intelligence (AI) into pharmaceutical nanoformulation designs represents a paradigmatic shift from traditional empirical approaches to data-driven, predictive methodologies. This comprehensive review examines the current state and future prospects of AI applications in nanoformulation development, encompassing machine learning algorithms, deep learning architectures, and optimization techniques. We analyze how AI addresses critical challenges in nanoparticle design, including property prediction, material selection, process optimization, and personalized medicine applications. The review covers key AI methodologies such as supervised and unsupervised learning, neural networks, genetic algorithms, and ensemble methods, while discussing their specific applications in lipid nanoparticles, polymeric systems, inorganic nanocarriers, and hybrid formulations. Current limitations, including data scarcity, model interpretability, and regulatory considerations, are critically evaluated alongside emerging solutions. We conclude by identifying future research directions that could revolutionize nanoformulation development through enhanced AI integration, ultimately accelerating the translation of nanomedicines from laboratory to clinic.

Keywords

Artificial intelligence, machine learning, nanoformulations, drug delivery, predictive modelling, pharmaceutical design

Introduction

The pharmaceutical industry faces unprecedented challenges in developing effective drug delivery systems that can overcome biological barriers, enhance therapeutic efficacy, and minimize adverse effects.¹ Nanoformulations have emerged as a promising solution, offering unique advantages including improved bioavailability, targeted delivery, controlled release, and reduced toxicity. ² However, the rational design of nanoformulations remains a complex endeavor due to the multitude of variables influencing their properties and performance.³ Traditional nanoformulation development relies heavily on empirical approaches, involving extensive trial-and-error experimentation that is both time-consuming and resource-intensive.⁴ The vast parameter space encompassing material selection, formulation composition, processing conditions, and quality attributes creates an exponentially large design space that is practically impossible to explore comprehensively through conventional methods.⁵ Artificial intelligence has emerged as a transformative technology capable of addressing these limitations by leveraging computational power to analyze complex datasets, identify patterns, and make predictions that guide rational formulation design^.6 The integration of AI methodologies into nanoformulation development promises to accelerate discovery timelines, reduce development costs, and improve success rates in bringing nanomedicines to market.⁷ This review provides a comprehensive analysis of current AI applications in nanoformulation design, examining methodological approaches, case studies, challenges, and future prospects. We aim to provide researchers and practitioners with insights into how AI can be effectively leveraged to advance the field of nanomedicine.⁸

2. Fundamentals of AI in Pharmaceutical Sciences

2.1 Machine Learning Paradigms

Machine learning, a subset of artificial intelligence, enables computers to learn and make decisions from data without explicit programming for specific tasks. In nanoformulation design, three primary learning paradigms are employed: ⁹

Supervised learning utilizes labeled datasets where input-output relationships are known, enabling the development of predictive models. Common algorithms include linear regression, support vector machines, random forests, and neural networks. ¹⁰ These methods excel at predicting nanoparticle properties such as size, zeta potential, encapsulation efficiency, and release kinetics based on formulation parameters.¹¹

Unsupervised learning identifies hidden patterns in unlabeled data, facilitating material discovery and formulation clustering.¹² Techniques such as principal component analysis, k-means clustering, and hierarchical clustering help identify relationships between formulation components and group similar nanoformulations based on their properties.¹³

Reinforcement learning employs reward-based learning, where agents learn optimal strategies through interaction with their environment.¹⁴ This approach shows promise for process optimization and adaptive formulation design, where algorithms learn to adjust parameters based on experimental feedback.¹⁵

2.2 Deep Learning Architectures

Deep learning represents a specialized subset of machine learning utilizing neural networks with multiple hidden layers to model complex, non-linear relationships.¹⁶ Several architectures have found particular relevance in nanoformulation designs:

Feedforward neural networks serve as universal function approximators capable of modeling complex relationships between formulation inputs and outputs. These networks have been successfully applied to predict particle size distributions, drug loading capacities, and stability profiles.¹⁷

Convolutional Neural Networks (CNNs) excel at processing structured data such as molecular representations and microscopy images.¹⁸ In nanoformulation contexts, CNNs analyze particle morphology from electron microscopy images and extract structural features from molecular descriptors.¹⁹

Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks handle sequential data, making them suitable for modeling time-dependent processes such as drug release kinetics and stability studies.²⁰

Generative Adversarial Networks (GANs) consist of competing generator and discriminator networks that can create novel molecular structures and formulation designs with desired properties.²¹

2.3 Optimization Algorithms

AI-driven optimization techniques address multi-objective formulation design challenges:

Genetic algorithms mimic evolutionary processes to explore formulation space and identify optimal solutions.²² These algorithms excel at handling discrete variables and complex constraint spaces common in nanoformulation designs.²³

Particle Swarm Optimization simulates social behavior to determine optimal solutions through collective intelligence.²⁴ This approach proves particularly effective for continuous optimization problems in process parameter tuning.²⁵

Bayesian optimization utilizes probabilistic models to efficiently explore expensive-to-evaluate functions, making it ideal for experimental design where each evaluation requires costly synthesis and characterization.²⁶

3. AI Applications in Nanoformulation Design

3.1 Property Prediction and QSPR Modeling

Quantitative Structure-Property Relationship (QSPR) modeling represents one of the most mature applications of AI in nanoformulation design.²⁷ These models establish mathematical relationships between molecular/formulation descriptors and physicochemical properties.²⁸

Particle Size Prediction: Machine learning models have been developed to predict nanoparticle size based on formulation parameters.²⁹ Support vector regression and random forest algorithms have demonstrated high accuracy in predicting mean particle sizes for various nanocarrier systems. Neural networks capture non-linear relationships between polymer molecular weight, drug-to-polymer ratios, and solvent systems to predict size distributions.³⁰

Encapsulation Efficiency Modeling: AI models predict drug loading and encapsulation efficiency by analyzing drug-polymer interactions, solubility parameters, and processing conditions.³¹ These models help optimize formulations to achieve maximum drug loading while maintaining stability.³²

Stability Prediction: Long-term stability assessment traditionally requires months of storage studies.³³ AI models trained on short-term stability data can predict long-term behavior, significantly accelerating formulation development. Machine learning algorithms analyze relationships between formulation composition, storage conditions, and stability indicators to forecast shelf life.³⁴

Release Kinetics Modeling: AI approaches model complex drug release mechanisms from nanocarriers.³⁵ Neural networks capture the interplay between diffusion, erosion, and swelling processes to predict release profiles under various conditions. These models enable rational design of controlled-release formulations with predetermined release characteristics.³⁶

3.2 Material Discovery and Selection

AI accelerates the identification of novel materials and optimal material combinations for nanoformulation development:

Virtual Screening of Excipients: Machine learning algorithms screen large databases of pharmaceutical excipients to identify candidates with desired properties.³⁷ These approaches consider molecular descriptors, physicochemical properties, and compatibility profiles to rank potential excipients.³⁸

Polymer Design: AI-driven approaches design novel polymers with tailored properties for specific drug delivery applications. Generative models create new polymer structures, while predictive models assess their suitability for nanoformulation applications.³⁹

Lipid Selection for LNPs: The design of lipid nanoparticles (LNPs) benefits significantly from AI-guided lipid selection. Machine learning models predict the performance of lipid combinations based on their molecular structures and physicochemical properties, enabling rapid identification of optimal lipid compositions.⁴⁰

3.3 Process Optimization

AI optimizes manufacturing processes for nanoformulation production:

Nanoprecipitation Optimization: Machine learning models optimize nanoprecipitation parameters, including solvent ratios, flow rates, temperature, and mixing conditions. These models predict how process variables affect particle properties, enabling quality-by-design approaches.⁴¹

Microfluidic Process Control: AI algorithms control microfluidic devices for precise nanoparticle synthesis. Real-time optimization adjusts flow rates and mixing patterns based on in-line monitoring data to maintain consistent product quality.⁴²

Spray Drying Optimization: Complex spray drying processes benefit from the AI optimization of multiple process parameters. Machine learning models predict how inlet temperature, flow rates, and atomization pressure affect particle properties and yield.⁴³

Scale-up Prediction: AI models facilitate process scale-up by predicting how formulation and process changes affect product quality during manufacturing scale increases. These models help maintain product consistency across different production scales.⁴⁴

3.4 Quality Control and Characterization

AI enhances quality control procedures and characterization techniques:

Image Analysis: Computer vision algorithms analyze microscopy images to characterize particle morphology, size distributions, and aggregation states. Convolutional neural networks automatically identify particle boundaries and extract morphological features.⁴⁵

Spectroscopic Data Analysis: AI algorithms analyze spectroscopic data (FTIR, NMR, Raman) to characterize drug-polymer interactions, crystallinity, and chemical stability. These approaches identify subtle spectral changes indicating formulation instability.⁴⁶

Real-time Process Monitoring: Machine learning algorithms monitor manufacturing processes in real-time, detecting deviations and predicting quality issues before they occur. This enables proactive quality control and reduces batch failures.⁴⁷

4. Specific Nanocarrier Systems

4.1 Lipid Nanoparticles (LNPs)

Lipid nanoparticles have received considerable publicity, particularly following their successful application in COVID-19 mRNA vaccines. AI approaches have been instrumental in optimizing LNP formulations:

Composition Optimization: Machine learning models predict optimal lipid ratios by analyzing the relationships between lipid molecular structures and LNP properties. These models consider factors such as phase behavior, membrane fluidity, and protein interactions.⁴⁸

mRNA Delivery Optimization: AI algorithms optimize LNP formulations specifically for nucleic acid delivery, considering factors such as endosomal escape, cellular uptake, and transfection efficiency. These models integrate multiple performance metrics to identify optimal formulations.⁴⁹

Targeting Enhancement: AI approaches design targeted LNPs by predicting how surface modifications affect biodistribution and cellular uptake. Machine learning models analyze ligand-receptor interactions to optimize targeting efficiency.⁵⁰

4.2 Polymeric Nanoparticles

Polymeric nanocarriers offer versatile platforms for drug delivery, with AI contributing to their optimization:

Polymer Selection: AI models screen polymer libraries to identify candidates with optimal properties for specific applications. These models consider biodegradability, biocompatibility, and drug-polymer compatibility.⁵¹

Block Copolymer Design: Machine learning approaches design block copolymers with precise control over micelle formation, drug loading, and release characteristics. These models predict how molecular architecture affects self-assembly behavior.

Surface Functionalization: AI algorithms optimize surface modification strategies to achieve desired pharmacokinetic profiles and targeting capabilities. These approaches consider the effects of surface chemistry on protein adsorption and cellular interactions.⁵²

4.3 Inorganic Nanocarriers

Inorganic nanoparticles offer unique advantages, including magnetic properties, fluorescence, and high drug loading capacity:

Metal Nanoparticle Design: AI approaches optimize the synthesis of metallic nanoparticles with controlled size, shape, and surface properties. Machine learning models predict how synthesis parameters affect particle characteristics.

Mesoporous Silica Optimization: AI algorithms optimize mesoporous silica nanoparticles for drug delivery applications, considering pore size, surface area, and drug loading capacity. These models guide the design of tailored porous structures.⁵³

Magnetic Nanoparticle Engineering: Machine learning approaches optimize magnetic nanoparticles for targeted delivery and hyperthermia applications. These models consider magnetic properties, biocompatibility, and targeting efficiency.

4.4 Hybrid and Multi-component Systems

Complex nanoformulations combining multiple materials benefit from AI optimization:

Core-Shell Nanoparticles: AI models optimize core-shell architectures by predicting how different material combinations affect drug loading, release, and stability. These approaches consider interfacial interactions and structural stability.⁵⁴

Nanocomposite Design: Machine learning algorithms design nanocomposites with synergistic properties by optimizing component ratios and spatial arrangements. These models predict how material combinations affect overall performance.

Stimuli-Responsive Systems: AI approaches design smart nanocarriers that respond to specific biological stimuli. These models optimize trigger mechanisms and response kinetics for controlled drug release.⁵⁵

5. Data Sources and Databases

5.1 Experimental Databases

The success of AI in nanoformulation design heavily depends on access to high-quality, comprehensive datasets:

Literature Mining: Automated text mining approaches extract formulation data from scientific publications, creating large datasets for model training. Natural language processing techniques identify relevant information from research articles.⁵⁶

Collaborative Databases: Community-driven databases aggregate experimental data from multiple research groups, providing standardized datasets for AI model development. These databases require careful curation to ensure data quality and consistency.

Commercial Databases: Pharmaceutical companies maintain proprietary databases containing formulation data, process parameters, and performance metrics. These databases provide valuable training data but are often not publicly accessible.⁵⁷

5.2 Computational Data

Molecular Descriptors: Computational chemistry approaches generate molecular descriptors for drugs and excipients, providing input features for AI models. These descriptors include electronic, topological, and physicochemical properties.

Simulation Data: Molecular dynamics simulations offer comprehensive details about drug-polymer interactions, membrane permeation, and release mechanisms. This data supplements experimental observations for AI model training.⁵⁸

Quantum Chemical Calculations: Electronic structure calculations provide fundamental properties such as binding energies, molecular orbitals, and reactivity indices that inform AI models.⁵⁹

5.3. Data Standardization and Quality

Data Harmonization: Standardizing data formats and measurement protocols across different sources improves AI model performance. This includes consistent units, measurement conditions, and characterization methods.

Quality Control: Implementing quality control measures ensures data reliability, including outlier detection, uncertainty quantification, and validation procedures.

FAIR Principles: Following Findable, Accessible, Interoperable, and Reusable (FAIR) data principles enhances the value and usability of nanoformulation datasets.⁶⁰

6. Challenges and Limitations

6.1 Data-Related Challenges

Data Scarcity: Many nanoformulation systems suffer from limited experimental data, making it challenging to train robust AI models. The expensive and time-consuming nature of nanoformulation characterization limits dataset sizes.

Data Quality Issues: Inconsistent experimental protocols, measurement errors, and reporting standards affect data quality. Variability between laboratories and measurement techniques introduces noise that can degrade model performance.

Bias in Datasets: Publication bias toward successful formulations and limited exploration of failure modes can create biased training datasets that may not represent the full formulation space.⁶¹

Missing Data: Incomplete characterization of formulations creates gaps in datasets that can limit model applicability and accuracy.

6.2 Model-Related Limitations

Interpretability: Many AI models, particularly deep learning approaches, operate as "black boxes" with limited interpretability. Understanding why models make specific predictions is crucial for scientific acceptance and regulatory approval.⁶²

Generalizability: Models trained on specific datasets may not generalize well to new formulation systems or operating conditions. This limits their applicability across different nanocarrier types or pharmaceutical applications.

Extrapolation Limitations: AI models may perform poorly when predicting properties outside their training domain, limiting their utility for exploring novel formulation spaces.

Model Validation: Rigorous validation of AI models requires extensive experimental verification, which can be resource-intensive and time-consuming.⁶³

6.3 Technical Challenges

Feature Selection: Identifying relevant input features for AI models requires domain expertise and careful analysis. Irrelevant or redundant features can degrade model performance.

Hyperparameter Optimization: AI models contain numerous hyperparameters that require optimization. This process can be computationally expensive and may require expertise in machine learning.

Computational Requirements: Complex AI models may require significant computational resources, limiting their accessibility to researchers with limited computing infrastructure.⁶⁴

6.4 Regulatory and Practical Considerations

Regulatory Acceptance: Regulatory agencies are still developing frameworks for evaluating AI-designed formulations. Clear guidelines and validation requirements are needed for regulatory acceptance.

Intellectual Property: AI-generated formulations raise questions about patentability and intellectual property rights, particularly when algorithms contribute to inventive processes.⁶⁵

Integration with Existing Workflows: Incorporating AI tools into established research and development workflows requires training, infrastructure changes, and cultural adaptation.⁶⁶

7. Emerging Trends and Future Directions

7.1 Advanced AI Architectures

Graph Neural Networks: This architecture represents molecules and formulations as graphs, enabling a more natural representation of chemical structures and interactions. Graph neural networks show promise for predicting molecular properties and drug-excipient interactions.

Transformer Models: Originally developed for natural language processing, transformer architectures are being adapted for chemical and pharmaceutical applications. These models can capture long-range dependencies in molecular sequences and formulation recipes.⁶⁷

Physics-Informed Neural Networks: These approaches incorporate physical laws and constraints into neural network architectures, improving model accuracy and interpretability for pharmaceutical applications.

Multi-modal Learning: Integrating diverse data types (molecular structures, images, spectra, and text) into unified AI models promises more comprehensive formulation design capabilities.⁶⁸

7.2 Automated Experimentation

Robotic Synthesis: Automated synthesis platforms integrated with AI algorithms enable high-throughput formulation screening and optimization. These systems can synthesize and characterize hundreds of formulations automatically.

Active Learning: AI algorithms guide experimental design by selecting the most informative experiments to perform, maximizing learning while minimizing experimental costs.

Closed-Loop Optimization: Integrated systems combining AI prediction, automated synthesis, and characterization enable autonomous formulation optimization with minimal human intervention.⁶⁹

7.3 Personalized Nanomedicine

Patient-Specific Formulations: AI models incorporating patient genetic, physiological, and pathological data can design personalized nanoformulations optimized for individual patients.

Precision Dosing: Machine learning algorithms can predict optimal dosing regimens based on patient characteristics and formulation properties, improving therapeutic outcomes while minimizing adverse effects.

Biomarker Integration: AI approaches can integrate multiple biomarkers to predict formulation performance and optimize treatment strategies for individual patients.⁷⁰

7.4 Sustainability and Green Chemistry

Environmentally Friendly Design: AI algorithms can optimize formulations for environmental sustainability, considering factors such as biodegradability, toxicity, and manufacturing energy consumption.

Green Synthesis Routes: Machine learning approaches can identify environmentally friendly synthesis methods and optimize process conditions to minimize waste and energy consumption.

Life Cycle Assessment: AI models can evaluate the complete life cycle environmental impact of nanoformulations, guiding sustainable design decisions.⁷¹

7.5 Regulatory Science Integration

Predictive Toxicology: AI models for predicting nanoformulation toxicity can support safety assessment and regulatory decision-making. These models integrate multiple toxicity endpoints and exposure scenarios.

Quality by Design (QbD): AI approaches support QbD implementation by predicting critical quality attributes and optimizing control strategies throughout the product lifecycle.

Digital Twins: Virtual representations of manufacturing processes enable real-time monitoring, optimization, and regulatory compliance assessment.⁷²

8. Case Studies and Success Stories

8.1 mRNA: Vaccine Development

The rapid development of COVID-19 mRNA vaccines demonstrated the power of AI in nanoformulation design. Machine learning algorithms optimized lipid nanoparticle formulations for mRNA delivery, contributing to the unprecedented speed of vaccine development. AI models predicted optimal lipid ratios, identified stable formulations, and guided manufacturing process optimization.

8.2 Cancer Nanomedicine

AI approaches have been successfully applied to design targeted nanocarriers for cancer therapy. Machine learning models optimized polymer-drug conjugates for enhanced tumor accumulation and reduced systemic toxicity. These approaches integrated tumor biology, pharmacokinetics, and formulation science to design more effective cancer nanomedicines.⁷³

8.3 Ophthalmic Drug Delivery

AI algorithms optimized nanoformulations for ocular drug delivery, addressing challenges such as tear clearance, conjunctival absorption, and biocompatibility. Machine learning models predicted formulation performance in different ocular tissues and optimized drug release kinetics for sustained therapy.

8.4 Protein and Peptide Delivery

AI approaches addressed the challenges of protein and peptide drug delivery by optimizing protective nanocarriers. These models considered protein stability, formulation interactions, and release mechanisms to design effective protein delivery systems.⁷⁴

9. Best Practices and Recommendations

9.1 Data Management

Standardize Protocols: Implement standardized experimental protocols and data collection procedures to ensure consistency and quality across datasets.

Comprehensive Characterization: Perform thorough characterization of nanoformulations, including physicochemical properties, stability, and performance metrics.

Data Sharing: Promote data sharing and collaboration to build larger, more diverse datasets that improve AI model performance.

Version Control: Implement proper version control for datasets and models to ensure reproducibility and track improvements over time.⁷⁵

9.2 Model Development

Cross-Validation: Use rigorous cross-validation procedures to assess model performance and avoid overfitting to training data.

External Validation: Validate models on independent datasets to assess generalizability and real-world performance.

Uncertainty Quantification: Implement uncertainty quantification methods to assess prediction reliability and guide experimental validation.

Interpretability Tools: Use interpretability methods such as SHAP values and feature importance analysis to understand model predictions.⁷⁶

9.3 Experimental Integration

Design of Experiments: Use statistical design of experiments principles to collect high-quality training data efficiently.

Active Learning: Implement active learning strategies to guide experimental design and maximize information gain.

Validation Studies: Perform systematic validation studies to verify AI predictions experimentally.⁷⁷

9.4 Regulatory Considerations

Documentation: Maintain comprehensive documentation of AI models, training data, and validation procedures for regulatory submissions.

Risk Assessment: Perform thorough risk assessments of AI-designed formulations, considering potential failure modes and safety implications.

Quality Systems: Implement quality systems that ensure AI model reliability and traceability throughout the product lifecycle.⁷⁸

10. CONCLUSIONS

The integration of artificial intelligence into nanoformulation designs represents a transformative advancement that promises to revolutionize pharmaceutical development. AI approaches have demonstrated remarkable success in addressing traditional challenges in formulation design, from property prediction and material selection to process optimization and quality control. Current applications of machine learning and deep learning in nanoformulation design have shown significant promise, with successful implementations across various nanocarrier systems, including lipid nanoparticles, polymeric systems, and inorganic carriers. The rapid development of COVID-19 mRNA vaccines exemplifies the potential impact of AI-driven approaches in addressing urgent medical needs. However, significant challenges remain that must be addressed to fully realize the potential of AI in nanoformulation design. Data scarcity, quality issues, and standardization challenges continue to limit model development and validation. The interpretability of AI models remains a critical concern for scientific acceptance and regulatory approval. Technical limitations, including generalizability and extrapolation capabilities, require continued research and development. Despite these challenges, the future outlook for AI in nanoformulation designs is highly promising. Emerging trends, including advanced neural network architectures, automated experimentation, and personalized medicine approaches, are opening new possibilities for more sophisticated and effective formulation design. The integration of AI with robotic synthesis platforms and high-throughput characterization methods promises to accelerate the pace of discovery and development significantly. The path forward requires continued collaboration between pharmaceutical scientists, computer scientists, and regulatory experts to address current limitations and develop robust, validated AI approaches. Investment in data infrastructure, model interpretability, and regulatory science is essential for the successful translation of AI innovations into clinical practice. As the field continues to mature, we anticipate that AI will be a vital component of nanoformulation design, enabling the development of more effective, safer, and personalized nanomedicines. The convergence of artificial intelligence and nanotechnology holds the promise of transforming pharmaceutical development and ultimately improving patient outcomes through more rational and efficient design of drug delivery systems. The success of AI in nanoformulation design will ultimately depend on the pharmaceutical community's commitment to data sharing, methodological rigor, and collaborative research. By addressing current challenges and embracing emerging opportunities, the field can harness the full potential of artificial intelligence to accelerate the development of next-generation nanomedicines that address unmet medical needs and improve human health.

REFERENCES

1. Hassan SA, Almaliki MN, Hussein ZA, Albehadili HM, Rabeea Banoon S, Abboodi A, Al-Saady M. Development of nanotechnology by artificial intelligence: a comprehensive review. Journal of Nanostructures. 2023 Oct 1;13(4):915-32.
2. Akhtar M, Nehal N, Gull A, Parveen R, Khan S, Khan S, Ali J. Explicating the transformative role of artificial intelligence in designing targeted nanomedicine. Expert Opinion on Drug Delivery. 2025 May 23:1-21.
3. Zafar S, Rana N. The convergence of nanotechnology and artificial intelligence: unlocking future innovations. Recent Innovations in Chemical Engineering. 2025 Feb 4.
4. Fu G, Sun P, Zhu W, Yang J, Cao Y, Yang MY, Cao Y. A deep- learning-based approach for fast and robust steel surface defects classification. OptLE. 2019;121:397-405.
5. Adir O, Poley M, Chen G, Froim S, Krinsky N, Shklover J, et al. Cancer Treatment: Integrating Artificial Intelligence and Nanotechnology for Precision Cancer Medicine (Adv. Mater. 13/2020). Adv Mater. 2020;32(13).
6. Lai C-S, Chakraborty I, Tai H-H, Verma D, Chang K-P, Wang J-C. Advanced Impacts of Nanotechnology and Intelligence. IEEE Nanotechnology Magazine. 2023;17(1):13-21.
7. Mansoori GA. Principles of Nanotechnology. WORLD SCIENTIFIC; 2005.
8. Biswas A, Bayer IS, Biris AS, Wang T, Dervishi E, Faupel
9. Advances in top–down and bottom–up surface nanofabrication: Techniques, applications and future prospects. Advances in Colloid and Interface Science. 2012;170(1-2):2-27.
10. Gentili PL. Untangling Complex Systems. CRC Press; 2018.Bayda S, Adeel M, Tuccinardi T, Cordani M, Rizzolio The History of Nanoscience and Nanotechnology: From Chemical–Physical Applications to Nanomedicine. Molecules. 2019;25(1):112.
11. P.S A, Aithal S. Nanotechnology based Innovations and Human Life Comfortability –Are we Marching towards Immortality? International Journal of Applied Engineering and Management Letters. 2018:71-86.
12. Mohajerani A, Burnett L, Smith JV, Kurmus H, Milas J, Arulrajah A, et al. Nanoparticles in Construction Materials and Other Applications, and Implications of Nanoparticle Use. Materials. 2019;12(19):3052.
13. Ferreira MAM, Filipe JA. Nanotechnology Applications – The Future Arrived Suddenly. Computational Approaches in Biomedical Nano-Engineering: Wiley; 2018. p. 23-41.
14. Nasrollahzadeh M, Sajadi SM, Sajjadi M, Issaabadi Z. An Introduction to Nanotechnology. Interface Science and Technology: Elsevier; 2019. p. 1-27.
15. Chen W, Liu X, Zhang S, Chen S. Artificial intelligence for drug discovery: Resources, methods, and applications. Molecular Therapy - Nucleic Acids. 2023;31:691-702.
16. Kumar A, Gadag S, Nayak UY. The Beginning of a New Era: Artificial Intelligence in Healthcare. Advanced Pharmaceutical Bulletin. 2020;11(3):414-425.
17. Kaur C, Garg U. Artificial intelligence techniques for cancer detection in medical image processing: A review. Materials Today: Proceedings. 2023;81:806-809.
18. Zheng H, Lu X, He K. In situ transmission electron microscopy and artificial intelligence enabled data analytics for energy materials. Journal of Energy Chemistry. 2022;68:454-493.
19. Wang C, Lv Z, Yang W, Feng X, Wang B. A rational design of functional porous frameworks for electrocatalytic CO2 reduction reaction. Chemical Society Reviews. 2023;52(4):1382-1427.
20. Das KP, J C. Nanoparticles and convergence of artificial intelligence for targeted drug delivery for cancer therapy: Current progress and challenges. Frontiers in Medical Technology. 2023;4.
21. He C, Liu D, Lin W. Self-Assembled Core–Shell Nanoparticles for Combined Chemotherapy and Photodynamic Therapy of Resistant Head and Neck Cancers. ACS Nano. 2015;9(1):991- 1003.
22. Chen X, Zou D, Cheng G, Xie H, Su F. Effects of flipped language classrooms on learning outcomes in higher education: A Bayesian meta-analysis. Australasian Journal of Educational Technology. 2023;39(2):65-97.
23. Škorc G, ?as J, Brezovnik S, Šafari? R. Position Control with Parameter Adaptation for a Nano-Robotic Cell. Strojniški vestnik – Journal of Mechanical Engineering. 2011;57(04):313-322.
24. Safaric R, Cas J, Skorc G, Protsenko SI. Micro and nano robotics. 2009 XXII International Symposium on Information, Communication and Automation Technologies; 2009/10: IEEE; 2009.
25. Oubellil R, Voda A, Boudaoud M, Regnier S. A 2-DOF H control strategy for a 3 axes robotic system operating at the nanometer scale. 2016 20th International Conference on System Theory, Control and Computing (ICSTCC); 2016/10: IEEE; 2016.
26. Narayan J, Mishra S, Jaiswal G, Dwivedy SK. Novel design and kinematic analysis of a 5-DOFs robotic arm with three- fingered gripper for physical therapy. Materials Today: Proceedings. 2020;28:2121-2132.
27. Mazaafrianto DN, Maeki M, Ishida A, Tani H, Tokeshi M. Recent Microdevice-Based Aptamer Sensors. Micromachines. 2018;9(5):202.
28. Cheraghi AR, Shahzad S, Graffi K. Past, Present, and Future of Swarm Robotics. Lecture Notes in Networks and Systems: Springer International Publishing; 2021. p. 190-233.
29. Sun T, Chen J, Zhang J, Zhao Z, Zhao Y, Sun J, Chang H. Application of micro/nanorobot in medicine. Frontiers in Bioengineering and Biotechnology. 2024;12.
30. Chen Y, Chen D, Liang S, Dai Y, Bai X, Song B, et al. Recent Advances in Field-Controlled Micro–Nano Manipulations and Micro–Nano Robots. Advanced Intelligent Systems. 2021;4(3).
31. Kong X, Gao P, Wang J, Fang Y, Hwang KC. Advances of medical nanorobots for future cancer treatments. Journal of Hematology and Oncology. 2023;16(1).
32. Mavroidis C, Ferreira A. Nanorobotics: Past, Present, and Future. Nanorobotics: Springer New York; 2012. p. 3-27.
33. Giri G, Maddahi Y, Zareinia K. A Brief Review on Challenges in Design and Development of Nanorobots for Medical Applications. Applied Sciences. 2021;11(21):10385.
34. Chugh V, Basu A, Kaushik NK, Kaushik A, Mishra YK, Basu AK. Smart nanomaterials to support quantum-sensing electronics. Materials Today Electronics. 2023;6:100067.
35. Khazaei M, Hosseini MS, Haghighi AM, Misaghi M. Nanosensors and their applications in early diagnosis of cancer. Sensing and Bio-Sensing Research. 2023;41:100569.
36. Verma SK, Anjali, Dubey D, Verma RK. Recent advancements in Skin tissue engineering in the application of Nanotechnology. Research Journal of Biotechnology. 2023;18(2):127-136.
37. Virk V, Deepak H, Taneja K, Srivastava R, Giri S. Amelioration in nanobiosensors for the control of plant diseases: current status and future challenges. Frontiers in Nanotechnology. 2024;6.
38. Ramathulasi T, Babu R, Yousuff M, Ramathulasi T. Patient Monitoring Through Artificial Intelligence. Artificial Intelligence for Health 40: Challenges and Applications: River Publishers; 2023. p. 91-128.
39. Srivastava AK, Dev A, Karmakar S. Nanosensors and nanobiosensors in food and agriculture. Environ Chem Lett. 2017;16(1):161-182.
40. Oukhatar A, Bakhouya M, Ouadghiri DE. Electromagnetic- Based Wireless Nano-Sensors Network: Architectures and Applications. JCom. 2021:8-19.
41. Tovar-Lopez FJ. Recent Progress in Micro- and Nanotechnology-Enabled Sensors for Biomedical and Environmental Challenges. Sensors. 2023;23(12):5406.
42. Dhahi TS, Yousif Dafhalla AK, Tayfour OE, Mubarakali A, Alqahtani AS, Tayfour Ahmed AE, et al. Advances in nano sensors for monitoring and optimal performance enhancement in photovoltaic cells. iScience. 2024;27(4):109347.
43. Sun T, Feng B, Huo J, Xiao Y, Wang W, Peng J, et al. Artificial Intelligence Meets Flexible Sensors: Emerging Smart Flexible Sensing Systems Driven by Machine Learning and Artificial Synapses. Nano-Micro Letters. 2023;16(1).
44. Nandipati M, Fatoki O, Desai S. Bridging Nanomanufacturing and Artificial Intelligence—A Comprehensive Review. Materials. 2024;17(7):1621.
45. Ammendolia MG, De Berardis B. Nanoparticle Impact on the Bacterial Adaptation: Focus on Nano-Titania. Nanomaterials. 2022;12(20):3616.
46. Chakraborty A, Diwan A, Tatake J. Prospect of nanomaterials as antimicrobial and antiviral regimen. AIMS Microbiology. 2023;9(3):444-466.
47. Alayande AB, Kang Y, Jang J, Jee H, Lee Y-G, Kim IS, Yang E. Antiviral Nanomaterials for Designing Mixed Matrix Membranes. Membranes. 2021;11(7):458.
48. Omran B, Baek K-H. Nanoantioxidants: Pioneer Types, Advantages, Limitations, and Future Insights. Molecules. 2021;26(22):7031.
49. Jabber Al-Saady MAA, Aldujaili NH, Rabeea Banoon S, Al- Abboodi A. Antimicrobial properties of nanoparticles in biofilms. Bionatura. 2022;7(4):1-9.
50. Al-Abboodi A, Mhouse Alsaady HA, Banoon SR, Al-Saady M. Conjugation strategies on functionalized iron oxide nanoparticles as a malaria vaccine delivery system. Bionatura. 2021;3(3):2009-2016.
51. Ghani Al-Muhanna S, Ameer Al-Kraety IA, Rabeea Banoon S. Statistical Analysis of COVID-19 infections according to the gender and age in Najaf Province, Iraq. Bionatura. 2022;7(2):1-3.
52. Zhou C, Liu Y, Li Y, Shi L. Recent advances and prospects in nanomaterials for bacterial sepsis management. Journal of Materials Chemistry B. 2023;11(45):10778-10792.
53. Han F, Meng Q, Xie E, Li K, Hu J, Chen Q, et al. Engineered biomimetic micro/nano-materials for tissue regeneration. Frontiers in Bioengineering and Biotechnology. 2023;11.
54. Holzinger A, Keiblinger K, Holub P, Zatloukal K, Müller H. AI for life: Trends in artificial intelligence for biotechnology. N Biotechnol. 2023;74:16-24.
55. Vora LK, Gholap AD, Jetha K, Thakur RRS, Solanki HK, Chavda VP. Artificial Intelligence in Pharmaceutical Technology and Drug Delivery Design. Pharmaceutics. 2023;15(7):1916.
56. Goswami L, Deka MK, Roy M. Artificial Intelligence in Material Engineering: A Review on Applications of Artificial Intelligence in Material Engineering. Adv Eng Mater. 2023;25(13).
57. Mobarak MH, Mimona MA, Islam MA, Hossain N, Zohura FT, Imtiaz I, Rimon MIH. Scope of machine learning in materials research—A review. Applied Surface Science Advances. 2023;18:100523.
58. Vicci DH. Emotional Intelligence in Artificial Intelligence: A Review and Evaluation Study. SSRN Electronic Journal. 2024.
59. Elliott D, Soifer E. AI Technologies, Privacy, and Security. Frontiers in Artificial Intelligence. 2022;5.
60. Agrawal R, Tilak P, Devand A, Bhatnagar A, Gupta P. Artificial Intelligence in Nanotechnology. Data-Intensive Research: Springer Nature Singapore; 2024. p. 239-248.
61. Bankins S, Formosa P. The Ethical Implications of Artificial Intelligence (AI) For Meaningful Work. J Bus Ethics. 2023;185(4):725-740.
62. Sacha GM, Varona P. Artificial intelligence in nanotechnology. Nanotechnology. 2013;24(45):452002.
63. Malik S, Muhammad K, Waheed Y. Nanotechnology: A Revolution in Modern Industry. Molecules. 2023;28(2):661.
64. Wahl B, Cossy-Gantner A, Germann S, Schwalbe NR. Artificial intelligence (AI) and global health: how can AI contribute to health in resource-poor settings? BMJ Global Health. 2018;3(4):e000798.
65. Hong L, Li W, Li Y, Yin S. Nanoparticle-based drug delivery systems targeting cancer cell surfaces. RSC Advances. 2023;13(31):21365-21382.
66. Vidhya KS, Sultana A, M NK, Rangareddy H. Artificial Intelligence’s Impact on Drug Discovery and Development From Bench to Bedside. Cureus. 2023.
67. Soori M, Arezoo B, Dastres R. Artificial intelligence, machine learning and deep learning in advanced robotics, a review. Cognitive Robotics. 2023;3:54-70.
68. He S, Leanse LG, Feng Y. Artificial intelligence and machine learning assisted drug delivery for effective treatment of infectious diseases. Adv Drug Del Rev. 2021;178:113922.
69. Singh AV, Varma M, Laux P, Choudhary S, Datusalia AK, Gupta N, et al. Artificial intelligence and machine learning disciplines with the potential to improve the nanotoxicology and nanomedicine fields: a comprehensive review. Arch Toxicol. 2023;97(4):963-979.
70. Li Y. Teaching mode of oral English in the age of artificial intelligence. Front Psychol. 2022;13.
71. Kop M. Abundance and Equality. Frontiers in Research Metrics and Analytics. 2022;7.
72. Anil Kumar Y, Koyyada G, Ramachandran T, Kim JH, Sajid S, Moniruzzaman M, et al. Carbon Materials as a Conductive Skeleton for Supercapacitor Electrode Applications: A Review. Nanomaterials. 2023;13(6):1049.
73. Darwish MA, Abd-Elaziem W, Elsheikh A, Zayed AA. Advancements in nanomaterials for nanosensors: a comprehensive review. Nanoscale Advances. 2024.
74. Daneshkhah A, Prabhala S, Viswanathan P, Subramanian H, Lin J, Chang AS, et al. Early detection of lung cancer using artificial intelligence-enhanced optical nanosensing of chromatin alterations in field carcinogenesis. Sci Rep. 2023;13(1).
75. Chang A, Prabhala S, Daneshkhah A, Lin J, Subramanian H, Roy HK, Backman V. Early screening of colorectal cancer using feature engineering with artificial intelligence- enhanced analysis of nanoscale chromatin modifications. Sci Rep. 2024;14(1).
76. Valenzuela-Amaro HM, Aguayo-Acosta A, Meléndez- Sánchez ER, de la Rosa O, Vázquez-Ortega PG, Oyervides- Muñoz MA, et al. Emerging Applications of Nanobiosensors in Pathogen Detection in Water and Food. Biosensors. 2023;13(10):922.
77. Alhalaili B, Popescu IN, Kamoun O, Alzubi F, Alawadhia S, Vidu R. Nanobiosensors for the Detection of Novel Coronavirus 2019-nCoV and Other Pandemic/Epidemic Respiratory Viruses: A Review. Sensors. 2020;20(22):6591.
78. Jin X, Cai A, Xu T, Zhang X. Artificial intelligence biosensors for continuous glucose monitoring. Interdisciplinary Materials. 2023;2(2):290-307.