Jul 2026· ITU Journal of Metallurgy and Materials Engineering· 0 citations· 13 references
TL;DR
AutoML mitigates 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.
Abstract
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.
This review highlights the synergy between AI and HTS, emphasizing DL techniques such as convolutional neural networks for bioactivity prediction, recurrent neural networks for de novo design, and reinforcement learning for property optimization.
K. Herbetko, Katarzyna Herbetko, Magdalena Mikołajek et al.· Future Medicinal Chemistry· 0 citations
This review emphasizes the influence of new AI platforms like AlphaFold3, molecular interactions are structurally optimized (MISATO), and ZairaChem on the discovery of oncology drugs and examines how AI reconciles chemical design with pharmacological feasibility.
Mohsin Ali, Muhammad Ali Tajwar, Farid Ahmed et al.· Medicinal research reviews (...· 0 citations
Artificial Intelligence (AI) is transforming drug discovery by making the process faster, more cost-effective, and more accurate than traditional methods, which often require 10–15 years and billions of dollars to develop a new drug. AI techniques such as machine learning, deep learning, natural language processing, reinforcement learning, and generative AI are widely used for drug target identification, biomarker discovery, molecular screening, toxicity prediction, lead optimization, and clinical trial support. Advanced models including Support Vector Machines (SVM), Random Forests (RF), Convolutional Neural Networks (CNN), Graph Neural Networks (GNN), and Transformers improve the prediction of molecular properties and drug-target interactions, while generative AI enables the design of novel therapeutic molecules. This study reviews AI-driven drug discovery methods, presents a structured AI pipeline from data collection to candidate selection, and evaluates performance using metrics such as prediction accuracy, screening efficiency, lead optimization success, and toxicity reduction. Despite its advantages, AI faces challenges including limited high-quality datasets, model bias, interpretability, regulatory uncertainty, computational complexity, and integration with conventional laboratory workflows. The findings indicate that AI significantly improves drug discovery efficiency, reduces research costs, and accelerates pharmaceutical innovation. Future advancements will rely on explainable AI, multimodal biological data integration, federated learning, and stronger regulatory frameworks.
Joseph Robin· International Journal of Mod...· 0 citations
Drug delivery, serving as a pivotal link between pharmaceutical innovation and clinical implementation, faces numerous challenges in achieving optimal therapeutic outcomes. With the advancement of computational methodologies and technological tools, artificial intelligence (AI) has been increasingly applied in pharmaceutical sciences, ranging from target discovery to product management. In recent years, AI has been extensively used in drug delivery to tailor formulation design, enhance therapeutic efficacy, and reduce side effects. However, limitations in data quality and model interpretability frequently restrict AI's predictive performance and hinder its clinical applicability. This overview highlights the applications of AI in drug delivery, focusing on AI-designed drug formulations, AI-driven prediction of ADMET properties, and AI-assisted drug delivery devices, which support the development of precision medicine. Additionally, the translation challenges and future perspectives in this field are discussed.
Xinmin Yu, Xinyun Jiang, Tao Sheng et al.· ACS Nano· 0 citations
Artificial intelligence (AI) has emerged as a major technological development influencing modern
pharmaceutical research and development. Machine learning, computational biology, and large-scale
biological data analysis have the potential to improve target identification, molecular optimization, and
clinical development. However, despite growing enthusiasm, significant uncertainty remains regarding
the ability of AI systems to overcome the biological, regulatory, and translational challenges that have
historically limited pharmaceutical innovation. This review examines AI-driven drug discovery from
a biomedical engineering and translational perspective. It evaluates the scientific foundations of AIenabled
pharmaceutical development, including target identification, molecular design, and multimodal
biological modeling, while analyzing key barriers involving biological complexity, clinical translation,
regulatory oversight, and commercialization. Case studies of Recursion Pharmaceuticals and Schrödinger
demonstrate both the opportunities and limitations associated with integrating computational approaches
into therapeutic development. The analysis suggests that AI will become an increasingly important
component of pharmaceutical workflows; however, long-term impact will depend less on algorithmic
advancement alone and more on effective integration with biological validation, experimental rigor,
clinical evidence, and scalable translational infrastructure. AI should therefore be viewed as an enabling
technology that enhances decision-making and prioritization rather than a replacement for traditional
biomedical research processes.
Andrew Matelis· American Journal of Student...· 0 citations
Artificial intelligence (AI) has rapidly evolved from a computational research tool into a major driver of innovation across the pharmaceutical development pipeline. Advances in deep learning, foundation models, protein structure prediction, and generative molecular design have accelerated target identification, compound optimization, toxicity prediction, and biomarker discovery. These developments have substantially reduced the time required to generate and prioritize therapeutic hypotheses.
Despite this remarkable progress, the translation of computational predictions into clinically effective medicines remains challenging. Drug development continues to be limited by biological complexity, patient heterogeneity, incomplete datasets, and the need for rigorous experimental and clinical validation. AI can improve decision-making, but it cannot replace the biological evidence required for regulatory approval or patient care.
This editorial discusses the evolving role of AI in modern drug discovery while highlighting the importance of explainable algorithms, high-quality biomedical data, real-world evidence, and interdisciplinary collaboration. Rather than viewing AI as a replacement for scientists, clinicians, or pharmacologists, it should be considered a powerful partner that enhances scientific reasoning and accelerates translational research.
The future of pharmaceutical innovation will depend on integrating computational intelligence with experimental pharmacology, clinical medicine, and regulatory science. Responsible implementation—not computational sophistication alone—will determine whether AI ultimately delivers safer, more effective, and more personalized therapies for patients.
Mohsen Zabihi· Advances in Pharmacology and...· 0 citations