Generative AI in Biomedicine and Systems Biology - Models, Methods & Applications 

Generative Artificial Intelligence (Generative AI) has emerged as a transformative approach across life sciences, capable of designing molecules, generating synthetic omics data, constructing biological networks, and simulating disease mechanisms. The convergence of deep generative models with biomedical data and systems biology frameworks holds the potential to unlock new understanding and applications in personalized medicine, therapeutics, and mechanistic modeling. Generative AI is revolutionizing biomedical research and systems biology, enabling more accurate disease modeling, personalized treatment, integrative omics analyses, and improved healthcare delivery. This workshop will explore state-of-the-art generative models—such as VAEs, GANs,Diffusion Models, and autoregressive transformers—and how they are applied to critical challenges in biomedical research and systems-level biology. It fosters interdisciplinary collaboration between AI researchers, computational biologists, and biomedical scientists to present and discuss cutting- edge Generative AI methodologies applied to biomedicine and systems biology.

We invite submissions that address (but are not limited to) the following areas:

•  Variational Autoencoders (VAEs) for biological data

•  Diffusion models in molecular and protein generation

•  Generative Adversarial Networks (GANs) for omics data synthesis

•  Transformer-based and autoregressive models for genomics

•  Multi-modal and multi-task generative architectures

•  Use generative models (e.g., GANs, diffusion models) to design novel molecules.

•  AI-driven protein folding and structure prediction

•  Reinforcement learning for molecular optimization

•  Fine-tuning large language models (LLMs) like GPT, Med-PaLM, or BioBERT for clinical use.

•  Multimodal foundation models combining text, imaging, and genomics.