The evolution of computation-driven paradigms in targeted peptide drug design: From predictive modeling to generative AI and clinical translation
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.