Abstract
The identification and property prediction of chemical molecules is of central importance in the advancement of drug discovery and material science, where the tandem mass spectrometry technology gives valuable fragmentation cues in the form of mass-to-charge ratio peaks. However, the lack of experimental spectra hinders the attachment of each molecular identification, and thus urges the establishment of prediction approaches for computational models. Deep learning models appear promising for predicting molecular structure spectra, but overall assessment remains challenging as a result of the heterogeneity in methods and the lack of well-defined benchmarks. To address this, our contribution is the creation of benchmark framework FlexMS for constructing and evaluating diverse model architectures in mass spectrum prediction. With its easy-to-use flexibility, FlexMS supports the dynamic construction of numerous distinct combinations of model architectures, while assessing their performance on preprocessed public datasets using different metrics. In this paper, we provide insights into factors influencing performance, including the structural diversity of datasets, hyperparameters like learning rate and data sparsity, pretraining effects, metadata ablation settings and cross-domain transfer learning analysis. This provides practical guidance in choosing suitable models. Moreover, retrieval benchmarks simulate practical identification scenarios and score potential matches based on predicted spectra.
Abstract (translated)
化学分子的识别和性质预测在药物发现和材料科学的进步中至关重要。其中，串联质谱技术通过提供质量与电荷比（m/z）峰的形式提供了有价值的碎片线索。然而，由于缺乏实验光谱数据，每种分子的识别都受到了限制，并因此迫切需要建立用于计算模型的预测方法。深度学习模型在预测分子结构光谱方面显示出前景，但由于方法上的异质性和缺乏明确定义的标准，全面评估仍然具有挑战性。为了解决这个问题，我们的贡献是创建了基准框架FlexMS，该框架旨在构建和评估多种不同的架构以进行质量光谱预测。通过其易于使用的灵活性，FlexMS支持动态构建众多不同组合的模型架构，并在预处理后的公共数据集上使用不同的指标对其性能进行评估。 本文中，我们探讨了一些影响表现的因素，包括数据集中的结构多样性、超参数（如学习率和数据稀疏性）、预训练效果、元数据消融设置以及跨领域迁移学习分析。这为选择合适的模型提供了实用的指导。此外，检索基准模拟了实际识别场景，并根据预测光谱来评分潜在匹配项。 这个框架及其研究成果有助于促进更精确且高效的分子识别技术的发展，在药物研发和材料科学等领域具有重要意义。
URL
https://arxiv.org/abs/2602.22822
