Generative AI and Large-Language Models in Genomics: From Sequence to Function, Prediction and Interpretation

The explosion of genomic data has created a need for powerful computational tools. Generative AI and large-language-model (LLM) approaches are now entering genomics: treating DNA/RNA/protein sequences as “language”, generating hypotheses, predicting variant effects, automating annotation, and integrating multimodal data. For example, LLMs are being applied to genomic sequence modelling, single-cell analysis, and structure/function prediction.

To gather further insights in generative AI and language modeling in genomics, we welcome articles addressing, but not limited to, the following themes:

• Foundations of sequence modeling for DNA, RNA, and protein using generative and language models
• In-silico generation and design of variants, regulatory elements, and synthetic genes
• AI-driven prediction of variant effects, functional annotation, and disease risk assessment
• Translational and clinical applications, including diagnostics, biomarker discovery, and genomic pipelines
• Fusion and integration of multimodal data sources (genomics, imaging, spatial omics, clinical data)
• Interpretability, reproducibility, and robustness in AI models
• Human–AI collaboration and the future of generative design in synthetic biology