The rapid evolution of computational methodologies, encompassing machine learning, generative modeling, and large-scale biomedical data integration, is fundamentally reshaping the paradigm of modern drug design and discovery. Traditional drug discovery pipelines are inherently constrained by prolonged development cycles, high attrition rates, and limited capacity for systematic exploration of the vast chemical space. With the exponential growth of genomic and multi-omics profiles, high-resolution structural data, and complex pharmacological networks, advanced computational architectures now offer unprecedented opportunities to accelerate target identification, molecular generation, and precision therapeutics.
Recent breakthroughs—such as deep learning-driven molecular generation, high-throughput virtual screening, and multimodal representation learning—have demonstrated transformative potential across the preclinical and clinical drug development continuum. However, critical bottlenecks remain in cross-modal data integration, model interpretability, mechanism-aware validation, and the robust translation of in silico candidates into clinical efficacy. This track aims to highlight cutting-edge research that advances computationally-driven drug discovery, bridging the gap between theoretical algorithmic innovations and practical implementation in real-world pharmacological applications. By consolidating emerging methodologies, this track will advance a strategically critical research frontier and contribute to the development of intelligent, data-driven, and translational therapeutics.
We are pleased to announce the important dates for PDCAT 2026.
Please mark your calendars!
All deadlines are based on Anywhere on Earth (AoE), at midnight on the specified date.