Scholarlink

<p>Chemical language models are powerful tools for navigating chemical space, but their reliance on linear representations such as molecular strings creates a semantic gap, hindering their ability to bridge natural language with the full complexity of molecular structures. Here we show that chemical language models can gain a comprehensive, multi-modal understanding of molecules through heterogeneous molecular encoding, which integrates one-dimensional sequences, two-dimensional topology, three-dimensional geometry, and statistically derived molecular fragments. We further introduce a query-based module that converts heterogeneous structural information into a unified representation compatible with language models, together with a chain-of-fragment mechanism that guides molecular generation through a hierarchical chemical blueprinting process. To support research in this area, we constructed a million-scale dataset for multi-objective molecular design. Experimentally, the framework enables bidirectional navigation of the chemical-linguistic space, achieving consistent improvements across molecular comprehension and design tasks over strong baselines.</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

Navigating chemical-linguistic sharing space with heterogeneous molecular encoding

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月10日

查看全文
  • Liuzhenghao Lv,
  • Hao Li,
  • Yu Wang,
  • Zijun Chen,
  • Zhiyuan Yan,
  • Zongying Lin,
  • Yuyang Liu,
  • Li Yuan,
  • Yonghong Tian

摘要

Chemical language models are powerful tools for navigating chemical space, but their reliance on linear representations such as molecular strings creates a semantic gap, hindering their ability to bridge natural language with the full complexity of molecular structures. Here we show that chemical language models can gain a comprehensive, multi-modal understanding of molecules through heterogeneous molecular encoding, which integrates one-dimensional sequences, two-dimensional topology, three-dimensional geometry, and statistically derived molecular fragments. We further introduce a query-based module that converts heterogeneous structural information into a unified representation compatible with language models, together with a chain-of-fragment mechanism that guides molecular generation through a hierarchical chemical blueprinting process. To support research in this area, we constructed a million-scale dataset for multi-objective molecular design. Experimentally, the framework enables bidirectional navigation of the chemical-linguistic space, achieving consistent improvements across molecular comprehension and design tasks over strong baselines.