Scholarlink

<p>Molecular design operates through fragment-based reasoning, yet many widely used molecular encodings rely on atom-level representations. This misalignment makes fragment-by-fragment construction and scaffold-centered designs hard to realize, especially for fused-ring systems. We present MOLCANO, a molecular language that represents molecules as chemically interpretable fragments linked by explicit junction tags, supporting single-bond, face-to-face, and even substructure-level connections for versatile scaffold assembly. It facilitates the construction of chemically complex structures while maintaining interpretability throughout the generation process. We validate MOLCANO across three open datasets spanning small-molecule drugs and organic electronic materials, covering de novo generation, superstructure growth/decoration, and medicinal-chemistry scaffolding. This also integrates with reinforcement learning for goal-oriented optimization of properties and with large language models for interactive, text-guided editing. By aligning computational representations with chemists’ modular reasoning, MOLCANO broadens the accessible chemical design space and accelerates molecular innovation in drug discovery, materials science, and beyond.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Molcano: Molecular Language for Chemical Assembly Notation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月7日

查看全文
  • Hwidong Na,
  • Eun Hyun Cho,
  • MiYoung Jang,
  • Joon Heo,
  • Changjin Oh,
  • Sang Ha Park,
  • Joonghee Won,
  • Sanghyun Yoo,
  • Hasup Lee,
  • Hyun Koo,
  • Ji Whan Kim,
  • Joonghyuk Kim,
  • Sun-Jae Lee,
  • Kisoo Kwon

摘要

Molecular design operates through fragment-based reasoning, yet many widely used molecular encodings rely on atom-level representations. This misalignment makes fragment-by-fragment construction and scaffold-centered designs hard to realize, especially for fused-ring systems. We present MOLCANO, a molecular language that represents molecules as chemically interpretable fragments linked by explicit junction tags, supporting single-bond, face-to-face, and even substructure-level connections for versatile scaffold assembly. It facilitates the construction of chemically complex structures while maintaining interpretability throughout the generation process. We validate MOLCANO across three open datasets spanning small-molecule drugs and organic electronic materials, covering de novo generation, superstructure growth/decoration, and medicinal-chemistry scaffolding. This also integrates with reinforcement learning for goal-oriented optimization of properties and with large language models for interactive, text-guided editing. By aligning computational representations with chemists’ modular reasoning, MOLCANO broadens the accessible chemical design space and accelerates molecular innovation in drug discovery, materials science, and beyond.