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

arXiv: https://arxiv.org/abs/2510.20615 · HTML: https://mlsanity.com/paper/2510.20615/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 50 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [A Generalization of Transformer Networks to Graphs](https://mlsanity.com/paper/2012.09699/) (2020)
- [BRIO: Bringing Order to Abstractive Summarization](https://mlsanity.com/paper/2203.16804/) (2022)
- [Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference](https://mlsanity.com/paper/2303.04673/) (2023)
- [Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models](https://mlsanity.com/paper/2309.02772/) (2023)
- [MassSpecGym: A benchmark for the discovery and identification of molecules](https://mlsanity.com/paper/2410.23326/) (2024)
- [RetroBridge: Modeling Retrosynthesis with Markov Bridges](https://mlsanity.com/paper/2308.16212/) (2023)
- [DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra](https://mlsanity.com/paper/2502.09571/) (2025)
- [Domain-Agnostic Molecular Generation with Chemical Feedback](https://mlsanity.com/paper/2301.11259/) (2023)
- [Prefix-Tree Decoding for Predicting Mass Spectra from Molecules](https://mlsanity.com/paper/2303.06470/) (2023)
- [MADGEN: Mass-Spec attends to De Novo Molecular generation](https://mlsanity.com/paper/2501.01950/) (2025)
- [Efficiently predicting high resolution mass spectra with graph neural networks](https://mlsanity.com/paper/2301.11419/) (2023)
- [AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference](https://mlsanity.com/paper/2410.00409/) (2024)

## Built on by (most cited first, 9 of 9)

- [MassSpecGym in the Wild: Uncovering and Correcting Evaluation Pitfalls in AI-Driven Molecule Discovery](https://mlsanity.com/paper/2606.19624/) (2026)
- [FlowMS: Flow Matching for De Novo Structure Elucidation from Mass Spectra](https://mlsanity.com/paper/2603.18397/) (2026)
- [SpecBridge: Bridging Mass Spectrometry and Molecular Representations via Cross-Modal Alignment](https://mlsanity.com/paper/2601.17204/) (2026)
- [De novo molecular structure elucidation from mass spectra via flow matching](https://mlsanity.com/paper/2602.19912/) (2026)
- [MSAlign: Aligning Molecule and Mass Spectra representations for Metabolite Identification](https://mlsanity.com/paper/2605.19752/) (2026)
- [When should we trust the annotation? Selective prediction for molecular structure retrieval from mass spectra](https://mlsanity.com/paper/2603.10950/) (2026)
- [Unlocking High-Fidelity Molecular Generation from Mass Spectra via Dual-Stream Line Graph Diffusion](https://mlsanity.com/paper/2605.07048/) (2026)
- [CoRe-Gen: Robust Spectrum-to-Structure Generation under Imperfect Fingerprint Conditions](https://mlsanity.com/paper/2605.12980/) (2026)
- [MARLIN: De Novo Molecular Structure Elucidation from Tandem Mass Spectra without a Ground-Truth Formula](https://mlsanity.com/paper/2607.04774/) (2026)

## Abstract (arXiv)

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.