FlowMS: Flow Matching for De Novo Structure Elucidation from Mass Spectra

TL;DR

FlowMS introduces a novel discrete flow matching framework for de novo molecular structure elucidation from mass spectra, achieving state-of-the-art results and producing chemically plausible candidate molecules.

Contribution

This work pioneers the application of discrete flow matching to spectrum-conditioned molecular generation, improving accuracy and efficiency over existing deep learning methods.

Findings

Achieves 9.15% top-1 accuracy on NPLIB1 benchmark.

Outperforms previous models in top-10 MCES by 4.2%.

Generates structurally plausible molecules closely resembling ground truth.

Abstract

Mass spectrometry (MS) stands as a cornerstone analytical technique for molecular identification, yet de novo structure elucidation from spectra remains challenging due to the combinatorial complexity of chemical space and the inherent ambiguity of spectral fragmentation patterns. Recent deep learning approaches, including autoregressive sequence models, scaffold-based methods, and graph diffusion models, have made progress. However, diffusion-based generation for this task remains computationally demanding. Meanwhile, discrete flow matching, which has shown strong performance for graph generation, has not yet been explored for spectrum-conditioned structure elucidation. In this work, we introduce FlowMS, the first discrete flow matching framework for spectrum-conditioned de novo molecular generation. FlowMS generates molecular graphs through iterative refinement in probability space, enforcing chemical formula constraints while conditioning on spectral embeddings from a pretrained formula transformer encoder. Notably, it achieves state-of-the-art performance on 5 out of 6 metrics on the NPLIB1 benchmark: 9.15% top-1 accuracy (9.7% relative improvement over DiffMS) and 7.96 top-10 MCES (4.2% improvement over MS-BART). We also visualize the generated molecules, which further demonstrate that FlowMS produces structurally plausible candidates closely resembling ground truth structures. These results establish discrete flow matching as a promising paradigm for mass spectrometry-based structure elucidation in metabolomics and natural product discovery.