用指纹编码质谱，生成分子结构准确率提升十倍。
One Small Step with Fingerprints, One Giant Leap for De Novo Molecule Generation from Mass Spectra
- 将质谱转为分子指纹，再解码生成分子结构。
- 在MassSpecGym数据集上，Top-1准确率达31%，Top-10达40%。
- 方法简洁高效，适合作为新研究的基准参考。
从质谱进行从头分子生成的常见方法采用两阶段流程：(1) 将质谱编码为分子指纹，(2) 解码这些指纹生成分子结构。本文采用MIST作为编码器，MolForge作为解码器，并引入额外训练数据以提升性能。通过阈值化每个指纹位的概率，聚焦关键亚结构的存在。该方法在MassSpecGym（Bushuiev et. al., 2024）数据集上实现相比先前最先进方法十倍的提升，生成分子结构的Top-1准确率为31%，Top-10准确率为40%。本工作可作为未来质谱驱动的从头分子解析研究的强基线。
原文摘要 · Abstract (English)
A common approach to the de novo molecular generation problem from mass spectra involves a two-stage pipeline: (1) encoding mass spectra into molecular fingerprints, followed by (2) decoding these fingerprints into molecular structures. In our work, we adopt MIST (Goldman et. al., 2023) as the encoder and MolForge (Ucak et. al., 2023) as the decoder, leveraging additional training data to enhance performance. We also threshold the probabilities of each fingerprint bit to focus on the presence of substructures. This results in a tenfold improvement over previous state-of-the-art methods, generating top-1 31% / top-10 40% of molecular structures correctly from mass spectra in MassSpecGym (Bushuiev et. al., 2024). We position this as a strong baseline for future research in de novo molecule elucidation from mass spectra.
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。