用AI从核磁谱图自动推断有机分子结构，突破传统方法极限。
Pushing the limits of one-dimensional NMR spectroscopy for automated structure elucidation using artificial intelligence
- 基于Transformer架构，将核磁谱图转为分子生成序列
- 40个非氢原子内正确结构前15名命中率达60.4%
- 适用于含多种元素的药物分子空间，可微调适配实验数据
一维核磁共振波谱是有机化合物和天然产物表征中最常用的技术之一。对于含36个以下非氢原子的分子，可能的结构数量估计在10²⁰至10⁶⁰之间。仅凭¹H和/或¹³C NMR谱图完全确定此类分子的结构（分子式与连接关系）——即从头生成结构——看似不可行。本文展示，通过深度学习框架，可在涵盖典型有机化学中所有元素（C、N、O、H、P、S、Si、B及卤素）的情况下，实现对最多含40个非氢原子体系的准确结构推断，覆盖了大部分药物分子化学空间。借鉴自然语言处理思想，我们提出的基于Transformer的架构仅使用¹H和¹³C NMR谱图，就能在前15次预测中以60.4%的准确率给出正确分子，克服了化学空间的组合爆炸问题，且可通过微调扩展到实际实验数据。
原文摘要 · Abstract (English)
One-dimensional NMR spectroscopy is one of the most widely used techniques for the characterization of organic compounds and natural products. For molecules with up to 36 non-hydrogen atoms, the number of possible structures has been estimated to range from $10^{20} - 10^{60}$. The task of determining the structure (formula and connectivity) of a molecule of this size using only its one-dimensional $^1$H and/or $^{13}$C NMR spectrum, i.e. de novo structure generation, thus appears completely intractable. Here we show how it is possible to achieve this task for systems with up to 40 non-hydrogen atoms across the full elemental coverage typically encountered in organic chemistry (C, N, O, H, P, S, Si, B, and the halogens) using a deep learning framework, thus covering a vast portion of the drug-like chemical space. Leveraging insights from natural language processing, we show that our transformer-based architecture predicts the correct molecule with 60.4% accuracy within the first 15 predictions using only the $^1$H and $^{13}$C NMR spectra, thus overcoming the combinatorial growth of the chemical space while also being extensible to experimental data via fine-tuning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。