arXiv：cs.LG· Changlin Liu, Tianyu Yi, Chengchun Liu, Boxuan Zhao, Fanyang Mo·· 3 小时前AI 评分32
DiffGCMS：用扩散模型与 LLM 重排序实现 GC-MS 可解释分子结构推断
Explainable Molecular Structure Inference from GC--MS with Diffusion Models and LLM Reranking
AI 导读
DiffGCMS 是一个基于谱图条件的离散图扩散模型，可从 GC-EI-MS 数据直接推断分子结构，并联合 LLM 进行第二阶段推理。在 NIST 20 的 13,696 条谱图测试集上，生成模型 Acc@1 和 Acc@10 分别为 6.01% 和 15.76%。
正文
Abstract:GC--EI--MS is an important technique for analyzing volatile and semivolatile compounds in complex samples. However, conventional methods rely heavily on reference spectral library matching, limiting their ability to identify compounds absent from these libraries and to infer complete molecular structures directly from fragmentation information. Here, we present DiffGCMS, a spectrum-conditioned discrete graph diffusion model for de novo structure elucidation from GC--EI--MS, and further develop a framework that integrates DiffGCMS with second-stage reasoning by a large language model (LLM). In the first stage, DiffGCMS generates candidate molecular structures from input spectra; in the second stage, the LLM uses mass spectral information to validate, repair, and rerank the candidates and provides interpretable analysis of fragment-ion peaks. This framework can generate plausible molecular structures for compounds absent from reference spectral libraries and provide traceable evidence supporting its decisions. On a test set comprising 13,696 spectra from NIST 20, the generative model achieved Acc@1 and Acc@10 of 6.01\% and 15.76\%, respectively. On the test subset containing molecules with no more than 10 heavy atoms, LLM-assisted molecular graph repair and reranking increased Acc@1 from 21.28\% to 21.95\%, Acc@10 from 46.91\% to 47.99\%, and candidate validity from 91.04\% to 100\%. These results demonstrate that spectrum-aware postprocessing can correct errors produced by the generative model while providing auditable and traceable explanations for the final ranking.
| Comments: | 4 figures |
| Subjects: | Chemical Physics (physics.chem-ph); Machine Learning (cs.LG); Computational Physics (physics.comp-ph); Data Analysis, Statistics and Probability (physics.data-an) |
| Cite as: | arXiv:2610.03066 [physics.chem-ph] |
| (or arXiv:2610.03066v1 [physics.chem-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2610.03066 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Fanyang Mo [view email]
[v1]
Fri, 2 Oct 2026 09:48:55 UTC (792 KB)
来源：arXiv：cs.LG · arxiv.org