AI Based Advanced Drug Delivery System

Öz

The integration of Artificial Intelligence (AI) into pharmaceutical research has accelerated drug discovery by streamlining target identification, compound screening, and candidate optimization. Yet, developing effective AI-driven systems remains challenging due to high- dimensional data and the need for expert-driven model tuning. Automated Machine Learning (AutoML) mitigates these issues by automating key stages of the ML pipeline data preprocessing, model selection, hyperparameter tuning, and evaluation thereby enhancing scalability and reducing dependence on domain expertise. AutoML's ability to handle diverse datasets, from omics to lipid nanoparticle (LNP) optimization enabling faster translation of candidates into clinically viable therapeutics. Techniques such as transfer learning, graph neural networks, and transformer-based models enrich molecular representations and improve predictive performance. Advances like DNN-VS further bolster tasks such as virtual screening and bioactivity prediction. Nonetheless, challenges persist in achieving model interpretability and integrating multimodal data. Future efforts should focus on adaptive, domain-aware AutoML strategies to overcome these limitations.

Anahtar Kelimeler

• AutoML
• Materials Science
• Artificial Intelligence
• Drug Delivery

Yapay Zeka Destekli Gelişmiş İlaç Dağıtım Sistemleri

Öz

Yapay Zeka’nın (AI) ilaç araştırmalarına entegrasyonu, hedef tanımlama, bileşik taraması ve aday optimizasyon süreçlerini kolaylaştırarak ilaç keşfini hızlandırmıştır. Bununla birlikte, yüksek boyutlu veriler ve uzmanlar tarafından gerçekleştirilen model ayarlamasına duyulan ihtiyaç nedeniyle, etkili AI tabanlı sistemler geliştirmek hâlâ zorlu bir görev olmaya devam etmektedir. Otomatik Makine Öğrenimi (AutoML), ML Veri Önleme Süreci, model seçimi, hiperparametre ayarlaması ve değerlendirme gibi kilit aşamalarını otomatikleştirerek bu sorunları hafifletir, böylece ölçeklenebilirliği artırır ve alan uzmanlığına olan bağımlılığı azaltır. AutoML'nin omiklerden lipit nanopartikül (LNP) optimizasyonuna kadar çeşitli veri kümelerini işleme yeteneği, adayların klinik olarak uygulanabilir terapötiklere daha hızlı dönüştürülmesini sağlar. Transfer öğrenimi, grafik sinir ağları ve dönüştürücü tabanlı modeller gibi teknikler, moleküler temsilleri zenginleştirir ve tahmin performansını iyileştirir. DNN-VS gibi gelişmeler, sanal tarama ve biyoaktivite tahmini gibi görevleri daha da güçlendirir. Bununla birlikte, modelin yorumlanabilirliğini sağlamak ve çok modlu verileri entegre etmek konusunda zorluklar devam etmektedir. Gelecekteki çabalar, bu sınırlamaları aşmak için uyarlanabilir, alan farkındalığına sahip AutoML stratejilerine odaklanmalıdır.

Anahtar Kelimeler

• AutoML
• Malzeme Bilimi
• Yapay Zeka
• İlaç İletimi

Kaynakça

1. [1] Kapoor, D. U., et al. (2024). AI-driven design and optimization of nanoparticle-based drug delivery systems. Science, Engineering and Health Studies, 24010003–24010003.
2. [2] Kolluri, S., Lin, J., Liu, R., & others. (2022). Machine learning and artificial intelligence in pharmaceutical research and development: A review. AAPS Journal, 24, 19. https://doi.org/10.1208/s12248-022-00681-5
3. [3] Yang, H., & Novick, S. (2019). Bayesian analysis with R for drug development: Concepts, algorithms, and case studies (1st ed.). Chapman and Hall/CRC. https://doi.org/10.1201/9781315100388
4. [4] Wang Q, Sun B, Yi Y, Velkov T, Shen J, Dai C, Jiang H. Progress of AI-Driven Drug-Target Interaction Prediction and Lead Optimization. Int J Mol Sci. 2025 Oct 15;26(20):10037. doi: 10.3390/ijms262010037. PMID: 41155330; PMCID: PMC12563295.
5. [5] Réda, C., Kaufmann, E., & Delahaye-Duriez, A. (2020). Machine learning applications in drug development. Computational and Structural Biotechnology Journal, 18, 241–252. https://doi.org/10.1016/j.csbj.2019.12.005
6. [6] Patel, L., Shukla, T., Huang, X., Ussery, D. W., & Wang, S. (2020). Machine learning methods in drug discovery. Molecules, 25(22), 5277. https://doi.org/10.3390/molecules25225277
7. [7] Bahi, M., & Batouche, M. (2018). Deep learning for ligand-based virtual screening in drug discovery. In 2018 3rd International Conference on Pattern Analysis and Intelligent Systems (PAIS) (pp. 1–5). IEEE. https://doi.org/10.1109/PAIS.2018.8598488
8. [8] Wang, B., Zhang, T., Liu, Q., Sutcharitchan, C., Zhou, Z., Zhang, D., & Li, S. (2025). Elucidating the role of artificial intelligence in drug development from the perspective of drug-target interactions. Journal of Pharmaceutical Analysis, 15, 101144. https://doi.org/10.1016/j.jpha.2024.101144

9. [9] Che, M., Yao, K., Che, C., Cao, Z., & Kong, F. (2021). Knowledge-Graph-Based Drug Repositioning against COVID-19 by Graph Convolutional Network with Attention Mechanism. Future Internet, 13(1), 13. https://doi.org/10.3390/fi13010013
10. [10] Grechishnikova D. Transformer neural network for protein-specific de novo drug generation as a machine translation problem. Sci Rep. 2021 Jan 11;11(1):321. doi: 10.1038/s41598-020-79682-4. PMID: 33432013; PMCID: PMC7801439.
11. [11] Kong W, Hu Y, Zhang J, Tan Q. Application of SMILES-based molecular generative model in new drug design. Front Pharmacol. 2022 Oct 13;13:1046524. doi: 10.3389/fphar.2022.1046524. PMID: 36313306; PMCID: PMC9606214.
12. [12] Arús-Pous, J., Johansson, S., Prykhodko, O., Bjerrum, E., Tyrchan, C., Reymond, J.-L., Chen, H., & Engkvist, O. (2019). Randomized SMILES strings improve the quality of molecular generative models. Journal of Cheminformatics, 11, Article 71. https://doi.org/10.1186/s13321-019-0393-0
13. [13] Bhogal, N. (2009). 21st century drug development: Advances, opportunities and challenges. Alternatives to Laboratory Animals,37(4),335–339. https://doi.org/10.1177/026119290903700401
14. [14] Chen, T. (2024). Artificial intelligence and drug design: Future prospects and ethical considerations. Computational Molecular Biology, 14(1), 9–19. https://doi.org/10.5376/cmb.2024.14.0002