大規模言語モデルを用いた条件付きDNA調節配列生成のためのマルチモーダル細胞コンテキスト命令チューニング

Designing biologically plausible regulatory sequences, such as enhancers, is a key challenge in synthetic biology. Current approaches either classify active enhancers or generate synthetic sequences independently but often fail to address the need for cell-type-specific recruitment of multiple transcription factors (TFs) for effective transcription activation. This oversight leads to suboptimal designs. To overcome these limitations, we propose Leonine, a novel framework redefining enhancer sequence design as a multimodal question-answering task within a cellular context. Leonine utilizes large language models (LLMs) trained on DNA sequences and integrates multimodal cellular data-including promoter sequences, gene expression profiles, and cell type information-to optimize enhancer sequences for specific regulatory environments. A large-scale dataset of over 1.5 million cell-type-specific promoter-enhancer pairs and a robust evaluation benchmark were developed to support this effort. Extensive evaluations across seven cell types demonstrate that Leonine outperforms state-of-the-art LLMs, generating biologically and functionally coherent sequences. This work introduces a new paradigm for context-aware DNA sequence design, advancing research in synthetic biology and gene regulation.