DeepMoLM: 利用视觉和几何结构信息进行分子-文本建模
DeepMoLM: Leveraging Visual and Geometric Structural Information for Molecule-Text Modeling
AI总结：
DeepMoLM通过双视角框架结合视觉和几何信息，提升分子-文本建模的准确性与物理合理性。
摘要：
在药物发现和化学文献挖掘中，AI模型必须解读分子图像并生成与3D几何和立体化学一致的输出。大多数分子语言模型依赖字符串或图结构，而视觉-语言模型常忽视立体化学细节，并难以将连续的3D结构映射为离散的标记。我们提出了DeepMoLM：深度分子语言建模，一种双视角框架，通过从分子构象中提取的几何不变量将高分辨率分子图像锚定下来。DeepMoLM保留了1024×1024输入的高频证据，将构态邻居编码为离散的扩展三维指纹，并通过交叉注意力融合视觉和几何流，实现物理基础的生成，而无需原子坐标。DeepMoLM在PubChem描述生成中比最强的通用基线模型提高了12.3%的相对METEOR分数，同时在专业方法中保持竞争力。它为所有属性查询生成有效的数值输出，并在专业设置中达到分子量MAE 13.64 g/mol和复杂度MAE 37.89。在从图像生成ChEBI-20描述时，它超越了通用基线模型并匹配了最先进的视觉-语言模型。代码可在https://github.com/1anj/DeepMoLM上获取。
英文摘要：
AI models for drug discovery and chemical literature mining must interpret molecular images and generate outputs consistent with 3D geometry and stereochemistry. Most molecular language models rely on strings or graphs, while vision-language models often miss stereochemical details and struggle to map continuous 3D structures into discrete tokens. We propose DeepMoLM: Deep Molecular Language M odeling, a dual-view framework that grounds high-resolution molecular images in geometric invariants derived from molecular conformations. DeepMoLM preserves high-frequency evidence from 1024 $\times$ 1024 inputs, encodes conformer neighborhoods as discrete Extended 3-Dimensional Fingerprints, and fuses visual and geometric streams with cross-attention, enabling physically grounded generation without atom coordinates. DeepMoLM improves PubChem captioning with a 12.3% relative METEOR gain over the strongest generalist baseline while staying competitive with specialist methods. It produces valid numeric outputs for all property queries and attains MAE 13.64 g/mol on Molecular Weight and 37.89 on Complexity in the specialist setting. On ChEBI-20 description generation from images, it exceeds generalist baselines and matches state-of-the-art vision-language models. Code is available at https://github.com/1anj/DeepMoLM.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
