# MSAlign: Aligning Molecule and Mass Spectra representations for Metabolite Identification

arXiv: https://arxiv.org/abs/2605.19752 · HTML: https://mlsanity.com/paper/2605.19752/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 69 references that are in the map.
- First posted on arXiv 19 May 2026.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [A Brief Review of Domain Adaptation](https://mlsanity.com/paper/2010.03978/) (2020)
- [ChemBERTa-2: Towards Chemical Foundation Models](https://mlsanity.com/paper/2209.01712/) (2022)
- [Assessing and Learning Alignment of Unimodal Vision and Language Models](https://mlsanity.com/paper/2412.04616/) (2024)
- [DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra](https://mlsanity.com/paper/2502.09571/) (2025)
- [Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining](https://mlsanity.com/paper/2505.11293/) (2025)
- [Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenters](https://mlsanity.com/paper/2202.03813/) (2022)
- [MADGEN: Mass-Spec attends to De Novo Molecular generation](https://mlsanity.com/paper/2501.01950/) (2025)
- [MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation](https://mlsanity.com/paper/2510.20615/) (2025)
- [Ensemble Spectral Prediction (ESP) Model for Metabolite Annotation](https://mlsanity.com/paper/2203.13783/) (2022)
- [JESTR: Joint Embedding Space Technique for Ranking Candidate Molecules for the Annotation of Untargeted Metabolomics Data](https://mlsanity.com/paper/2411.14464/) (2024)
- [Sketch In, Sketch Out: Accelerating both Learning and Inference for Structured Prediction with Kernels](https://mlsanity.com/paper/2302.10128/) (2023)
- [MHG-GNN: Combination of Molecular Hypergraph Grammar with Graph Neural Network](https://mlsanity.com/paper/2309.16374/) (2023)
- [Small molecule retrieval from tandem mass spectrometry: what are we optimizing for?](https://mlsanity.com/paper/2602.16507/) (2026)
- [SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport](https://mlsanity.com/paper/2602.23353/) (2026)
- [To Bin or not to Bin: Alternative Representations of Mass Spectra](https://mlsanity.com/paper/2502.10851/) (2025)

## Built on by (most cited first, 1 of 1)

- [Graph Matching Relaxations and Amortization for Supervised Graph Prediction](https://mlsanity.com/paper/2609.15437/) (2026)

## Abstract (arXiv)

Accurately identifying metabolites i.e. small molecules from mass spectrometry data remains a core challenge in metabolomics, with broad applications in drug discovery, environmental analysis, and clinical research. We address the Molecule Retrieval task, which consists in recovering the chemical structure of a metabolite from its MS/MS spectrum given a set of candidate molecules. We make three contributions. First, we propose a unified framework encompassing recent approaches based on representation alignment and contrastive learning. Second, we introduce MSAlign, a lightweight model that achieves state-of-the art performances by aligning two frozen foundation models (DreaMS for mass spectra and MolDeBERTa for molecules) and demonstrate that a score fusion strategy further improves the performance for a very small computational cost. Third, we investigate a long-standing evaluation problem: data splitting strategies in molecule retrieval implicitly trade off data leakage against domain shift. We formalize this tension by introducing a quantitative measure of distribution shift, and use it to evaluate splitting strategies in existing benchmarks. All datasets, splits, candidate sets, and a unified implementation of MSAlign and baselines are publicly released to support reproducible research.