# One Small Step with Fingerprints, One Giant Leap for De Novo Molecule Generation from Mass Spectra

arXiv: https://arxiv.org/abs/2508.04180 · HTML: https://mlsanity.com/paper/2508.04180/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Builds on (most cited first, 6 of 6)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models](https://mlsanity.com/paper/1811.12823/) (2018)
- [MassSpecGym: A benchmark for the discovery and identification of molecules](https://mlsanity.com/paper/2410.23326/) (2024)
- [DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra](https://mlsanity.com/paper/2502.09571/) (2025)
- [Rapid Prediction of Electron-Ionization Mass Spectrometry using Neural Networks](https://mlsanity.com/paper/1811.08545/) (2018)
- [Chemical Structure Elucidation from Mass Spectrometry by Matching Substructures](https://mlsanity.com/paper/1811.07886/) (2018)

## Built on by (most cited first, 2 of 2)

- [MassSpecGym in the Wild: Uncovering and Correcting Evaluation Pitfalls in AI-Driven Molecule Discovery](https://mlsanity.com/paper/2606.19624/) (2026)
- [Critical Mass: Structure-Disjoint Splits Drift With the Libraries They Are Built On](https://mlsanity.com/paper/2610.12694/) (2026)

## Abstract (arXiv)

A common approach to the de novo molecular generation problem from mass spectra involves a two-stage pipeline: (1) encoding mass spectra into molecular fingerprints, followed by (2) decoding these fingerprints into molecular structures. In our work, we adopt MIST (Goldman et. al., 2023) as the encoder and MolForge (Ucak et. al., 2023) as the decoder, leveraging additional training data to enhance performance. We also threshold the probabilities of each fingerprint bit to focus on the presence of substructures. This results in a tenfold improvement over previous state-of-the-art methods, generating top-1 31% / top-10 40% of molecular structures correctly from mass spectra in MassSpecGym (Bushuiev et. al., 2024). We position this as a strong baseline for future research in de novo molecule elucidation from mass spectra.