# MADGEN: Mass-Spec attends to De Novo Molecular generation

arXiv: https://arxiv.org/abs/2501.01950 · HTML: https://mlsanity.com/paper/2501.01950/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 3 Jan 2025.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [CLIP2Video: Mastering Video-Text Retrieval via Image CLIP](https://mlsanity.com/paper/2106.11097/) (2021)
- [Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling](https://mlsanity.com/paper/2305.04111/) (2023)
- [A Survey on Deep Graph Generation: Methods and Applications](https://mlsanity.com/paper/2203.06714/) (2022)
- [A CLIP-Hitchhiker's Guide to Long Video Retrieval](https://mlsanity.com/paper/2205.08508/) (2022)
- [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)
- [Rapid Prediction of Electron-Ionization Mass Spectrometry using Neural Networks](https://mlsanity.com/paper/1811.08545/) (2018)
- [A Deep Generative Model for Fragment-Based Molecule Generation](https://mlsanity.com/paper/2002.12826/) (2020)
- [Extending CLIP for Category-to-image Retrieval in E-commerce](https://mlsanity.com/paper/2112.11294/) (2021)
- [Using Graph Neural Networks for Mass Spectrometry Prediction](https://mlsanity.com/paper/2010.04661/) (2020)
- [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)
- [React-OT: Optimal Transport for Generating Transition State in Chemical Reactions](https://mlsanity.com/paper/2404.13430/) (2024)

## Built on by (most cited first, 16 of 16)

- [DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra](https://mlsanity.com/paper/2502.09571/) (2025)
- [MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation](https://mlsanity.com/paper/2510.20615/) (2025)
- [DiffNMR: Diffusion Models for Nuclear Magnetic Resonance Spectra Elucidation](https://mlsanity.com/paper/2507.08854/) (2025)
- [Breaking the Modality Barrier: Generative Modeling for Accurate Molecule Retrieval from Mass Spectra](https://mlsanity.com/paper/2511.06259/) (2025)
- [FRIGID: Scaling Diffusion-Based Molecular Generation from Mass Spectra at Training and Inference Time](https://mlsanity.com/paper/2604.16648/) (2026)
- [Comparative Analysis of Formula and Structure Prediction from Tandem Mass Spectra](https://mlsanity.com/paper/2601.00941/) (2026)
- [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)
- [NMIRacle: Multi-modal Generative Molecular Elucidation from IR and NMR Spectra](https://mlsanity.com/paper/2512.19733/) (2025)
- [SpecBridge: Bridging Mass Spectrometry and Molecular Representations via Cross-Modal Alignment](https://mlsanity.com/paper/2601.17204/) (2026)
- [MSAlign: Aligning Molecule and Mass Spectra representations for Metabolite Identification](https://mlsanity.com/paper/2605.19752/) (2026)
- [How well can off-the-shelf LLMs elucidate molecular structures from mass spectra using chain-of-thought reasoning?](https://mlsanity.com/paper/2601.06289/) (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)
- [MS-GPT: Rethinking MS/MS De Novo Structure Elucidation as Spectrum-Induced Posterior Querying of a Molecule-Language Model](https://mlsanity.com/paper/2607.23607/) (2026)

## Abstract (arXiv)

The annotation (assigning structural chemical identities) of MS/MS spectra remains a significant challenge due to the enormous molecular diversity in biological samples and the limited scope of reference databases. Currently, the vast majority of spectral measurements remain in the "dark chemical space" without structural annotations. To improve annotation, we propose MADGEN (Mass-spec Attends to De Novo Molecular GENeration), a scaffold-based method for de novo molecular structure generation guided by mass spectrometry data. MADGEN operates in two stages: scaffold retrieval and spectra-conditioned molecular generation starting with the scaffold. In the first stage, given an MS/MS spectrum, we formulate scaffold retrieval as a ranking problem and employ contrastive learning to align mass spectra with candidate molecular scaffolds. In the second stage, starting from the retrieved scaffold, we employ the MS/MS spectrum to guide an attention-based generative model to generate the final molecule. Our approach constrains the molecular generation search space, reducing its complexity and improving generation accuracy. We evaluate MADGEN on three datasets (NIST23, CANOPUS, and MassSpecGym) and evaluate MADGEN's performance with a predictive scaffold retriever and with an oracle retriever. We demonstrate the effectiveness of using attention to integrate spectral information throughout the generation process to achieve strong results with the oracle retriever.