MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation

TL;DR

MS-BART is a unified deep learning framework that improves molecular structure elucidation from mass spectrometry data by leveraging cross-modal pretraining, multi-task learning, and chemical feedback mechanisms, achieving state-of-the-art results.

Contribution

The paper introduces MS-BART, a novel model that unifies spectral and molecular data into a shared space, enabling effective pretraining and transfer learning for structure elucidation.

Findings

Achieves state-of-the-art performance on key metrics.

Faster inference compared to diffusion-based methods.

Robustness to real-world spectral variability.

Abstract

Mass spectrometry (MS) plays a critical role in molecular identification, significantly advancing scientific discovery. However, structure elucidation from MS data remains challenging due to the scarcity of annotated spectra. While large-scale pretraining has proven effective in addressing data scarcity in other domains, applying this paradigm to mass spectrometry is hindered by the complexity and heterogeneity of raw spectral signals. To address this, we propose MS-BART, a unified modeling framework that maps mass spectra and molecular structures into a shared token vocabulary, enabling cross-modal learning through large-scale pretraining on reliably computed fingerprint-molecule datasets. Multi-task pretraining objectives further enhance MS-BART's generalization by jointly optimizing denoising and translation task. The pretrained model is subsequently transferred to experimental spectra through finetuning on fingerprint predictions generated with MIST, a pre-trained spectral inference model, thereby enhancing robustness to real-world spectral variability. While finetuning alleviates the distributional difference, MS-BART still suffers molecular hallucination and requires further alignment. We therefore introduce a chemical feedback mechanism that guides the model toward generating molecules closer to the reference structure. Extensive evaluations demonstrate that MS-BART achieves SOTA performance across 5/12 key metrics on MassSpecGym and NPLIB1 and is faster by one order of magnitude than competing diffusion-based methods, while comprehensive ablation studies systematically validate the model's effectiveness and robustness.