发表机构
Nanyang Technological University; Zhejiang University（南洋理工大学; 浙江大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出ScentGen分层多模态框架，融合一维、二维和三维分子信息生成自然语言气味描述，并构建配对数据集，实验证明其生成连贯且富有表现力的气味描述。
AI 中文摘要
本文提出了一项分子气味描述生成任务，旨在从分子结构生成自然语言的气味描述。与使用离散标签描述分子气味的传统方法不同，该任务生成具有表现力和人类可解释性的感官描述。为解决该任务，我们提出了一种名为ScentGen的分层多模态嗅觉语义建模框架。ScentGen由三个关键组件组成：气味语义规划器、语义适配器和描述生成器。气味语义规划器整合来自一维SMILES序列、二维分子图和三维分子构象的互补分子信息，以学习具有判别性和结构化的嗅觉语义。语义适配器进一步将学习到的嗅觉表示映射到大语言模型的隐藏空间，将分子气味语义转化为与语言兼容的连续提示。基于这些提示，描述生成器生成连贯的气味描述，反映输入分子的合理感官特征。考虑到缺乏带有自然语言气味描述的分子数据集，我们进一步构建了一个分子气味描述数据集，其中包含配对的多模态分子表示和人类可解释的气味描述。大量实验表明，ScentGen能够生成连贯且富有表现力的气味描述，为超越离散气味标签预测的分子气味理解提供了更灵活的解决方案。
英文摘要
In this paper, we introduce a molecular odor description generation task, which aims to generate natural language odor descriptions from molecular structures. Unlike conventional methods that describe molecular odor using discrete labels, this task generates expressive and human-interpretable sensory descriptions. To address this task, we propose a hierarchical multimodal olfactory semantic modeling framework, named ScentGen. ScentGen consists of three key components: an odor semantic planner, a semantic adapter, and a description generator. The odor semantic planner integrates complementary molecular information from 1D SMILES sequences, 2D molecular graphs, and 3D molecular conformations to learn discriminative and structured olfactory semantics. The semantic adapter further maps the learned olfactory representation into the hidden space of a large language model, transforming molecular odor semantics into language-compatible continuous prompts. Conditioned on these prompts, the description generator produces coherent odor descriptions that reflect plausible sensory characteristics of the input molecule. Considering the lack of molecular datasets with natural language odor descriptions, we further construct a molecular odor description dataset containing paired multimodal molecular representations and human-interpretable odor descriptions. Extensive experiments demonstrate that ScentGen generates coherent and expressive odor descriptions, providing a more flexible solution for molecular odor understanding beyond discrete odor label prediction.
