2026· The Innovation Drug Discovery· Vol 1, pp. 100009· 2 citations· 114 references
TL;DR
A strategic roadmap for seamlessly integrating generative AI with physics-based validation with physics-based validation is provided, thereby accelerating the transition of computationally designed peptides from in silico blueprints to viable clinical candidates.
Abstract
Targeted peptide therapeutics offer a potent solution for undruggable intracellular targets yet their clinical translation remains hampered by poor membrane permeability and metabolic instability. The integration of high-performance computing and artificial intelligence is currently driving a fundamental transition from empirical screening to rational de novo design. This review moves beyond a conventional enumeration of tools to construct a strategic framework that integrates physics-based validation with generative deep learning. We critically analyze the synergistic application of molecular dynamics and docking for thermodynamic verification while simultaneously evaluating how diffusion models and protein language models accelerate the exploration of vast chemical spaces. By delineating a closed-loop workflow that incorporates pharmacokinetic constraints into generative algorithms this review not only synthesizes current advancements but also provides a strategic roadmap for seamlessly integrating generative AI with physics-based validation, thereby accelerating the transition of computationally designed peptides from in silico blueprints to viable clinical candidates.
PROTACs are revolutionary therapeutics that eliminate pathogenic proteins via catalytic event-driven degradation. Conventional development suffers from unpredictable ternary complexes, empirical linker modification and blind ligand screening, yielding clinical success below 10% and requiring 3-4 years to obtain preclinical candidates. Generative artificial intelligence (AI) offers a promising avenue for data-driven rational design. This perspective explores how multimodal deep learning enhances ternary complex prediction accuracy and boosts molecular design hit rates from 5-8% to over 35%. Closed-loop research and development (R&D) ecosystems supported by databases accelerate PROTAC development. The landmark case of Insilico Medicine’s PKMYT1-PROTAC, developed via its AI platform Chemistry 42, achieves a DC50 of 0.5 nM and exhibits a dual degradation-inhibition mechanism, and has advanced to the preclinical candidate (PCC) validation stage within approximately 12 months. We further discuss how to integrate AI design with clinical translation. Future efforts focus on advanced computational strategies, establishing standardized evaluation metrics and expanding the E3 ligase toolbox. This AI-powered strategy will expedite PROTAC research and expand the application of targeted protein degradation therapy.
Pengyun Li, Shiyang Sun, Ting Wei et al.· The Innovation Drug Discover...· 0 citations
The evolving role of AI in modern drug discovery is discussed while highlighting the importance of explainable algorithms, high-quality biomedical data, real-world evidence, and interdisciplinary collaboration.
Mohsen Zabihi· Advances in Pharmacology and...· 0 citations
Artificial intelligence (AI) is evolving from a predictive tool into a foundational computational infrastructure for mechanism-driven pharmacology, fundamentally reshaping drug discovery. This review examines how this transformation addresses persistent challenges in target validation, including data biases and the need for model interpretability, by integrating network pharmacology with advanced deep learning architectures. Specifically, graph neural networks decipher the complex topology of biological systems and transformer models facilitate the fusion of multimodal data, from genomics to real-world clinical records. Coupled with physics-informed neural networks, this integrated framework operates as a predictive computational microscope. It enables comprehensive in silico simulations that span multiple biological scales, encompassing atomic-level molecular interactions and longitudinal patient trajectories. We demonstrate that this AI-driven paradigm is essential for advancing precision medicine, as it systematically translates vast and heterogeneous datasets into testable mechanistic hypotheses. Consequently, this approach accelerates the development of safer, more effective and patient-specific therapies, by de-risking target validation and elucidating novel therapeutic mechanisms. It directly addresses some of the most pressing inefficiencies in contemporary drug discovery and development, offering a pathway towards more rational and efficient therapeutic innovation.
Xuerui Song, Zhi Chen, Y. An et al.· British Journal of Pharmacol...· 0 citations
This review examines how machine learning, deep learning, natural language processing (NLP), and generative modeling are being applied across medicinal chemistry and drug development, and highlights how multimodal data fusion, predictive modeling, and human-AI collaborative frameworks are supporting more informed decisions in rational drug design.
Kaicheng U, Sophia Meixuan Zhang, Ziyu Yu et al.· Chemical Society Reviews· 0 citations
It is proposed that the translational potential of AI in oncology is substantially shaped by the rigor of the experimental feedback loops that constrain and refine it, thereby accelerating the delivery of more effective, personalized therapies validated through the complete hierarchy of in vitro assays, in vivo PDX models, and prospective clinical trials to patients.
Tuğba Ören Varol, M. Varol· Cancer Medicine· 0 citations
An operational, end-to-end workflow that explicitly connects computational predictions to medicinal chemistry decision points is provided, addressing a critical gap between computational prediction and clinical translation.
Antonio Lavecchia· Medicinal research reviews (...· 0 citations