GEMS 用图编辑搜索从小分子质谱推断分子结构
GEMS: Molecular Structure Elucidation as Learned Search over Isomer Graphs
质谱解分子结构向来慢，GEMS 把它变成图上的搜索问题，几分钟跑完过去一天多的活，做代谢组学的可以看看。
GEMS（Guided Editing of Molecular Structures）将分子结构解析建模为在同分异构体图上的学习搜索，通过保持分子式和原子化合价的 2-switch 键编辑逐步修正候选结构。模型先用 MIST 将质谱预测为分子指纹，再由神经策略网络把候选指纹与预测比对，一次前向传播给所有有效编辑打分。策略网络在最短编辑路径上训练，因此可先在 PubChem 同分异构体上预训练，再用谱图预测指纹微调。在 NPLIB1 和 MassSpecGym 上，排除目标结构初始化的设定下，3 轮编辑达到 Hit@1 29.64%/30.22%，NPLIB1 端到端约 3.3 分钟完成鉴定，而对比方法 FRIGID 需 26.2 小时。实验还发现指纹预测误差是目标恢复和最终排序的瓶颈。
GEMS: Molecular Structure Elucidation as Learned Search over Isomer Graphs
Identifying small-molecule structures from molecular formulas and tandem mass spectra remains a bottleneck in untargeted metabolomics and natural-product discovery. Even when database retrieval or de novo prediction misses the exact structure, the resulting candidates can provide starting points for exploring nearby structures through a few bond edits. We introduce GEMS (Guided Editing of Molecular Structures), which refines candidates through learned 2-switch bond edits that preserve the molecular formula and each atom's total valence. GEMS uses MIST, a pretrained spectrum-to-fingerprint model, to predict fingerprint probabilities once per spectrum. A neural policy compares each candidate's fingerprint with these predictions, links present features to the atoms and bonds that generate them, and scores all valid edits in one forward pass. The policy is trained on shortest edit paths between structures, so it can be pretrained on PubChem isomers without spectra and then fine-tuned with spectrum-predicted fingerprints. At inference, GEMS searches from multiple initial candidates matching the supplied molecular formula and ranks candidates by fingerprint agreement and multi-start consensus. With the target structure excluded from PubChem initialization, three edit rounds achieve Hit@1/Hit@10 of 29.64%/50.81% on NPLIB1 and 30.22%/41.33% on MassSpecGym, exceeding published baselines under comparable settings. On NPLIB1, GEMS achieves higher identification accuracy in about 3.3 minutes end to end, compared with 26.2 hours for our FRIGID run. GEMS also improves identification from generated candidates, including those refined by FRIGID. Experiments with exact target fingerprints identify fingerprint prediction error as a bottleneck in target recovery and final ranking. Deeper search recovers additional targets without retraining, with larger gains from weaker initial candidates.
