Simulating Tandem Mass Spectra for Small Molecules using a General-Purpose Large-Language Model

We show a practical application of the Google Gemini large-language-model for simulating tandem mass spectra for compounds from the Blood Exposome Database. This approach bypasses the need for domain-specific model training, suggesting that the chemical fragmentation knowledge could be latently encoded within the Gemini model. General-purpose LLMs represent a useful and accessible tool for expanding in-silico spectral libraries and may accelerate the compound annotation in mass spectrometry-based metabolomics and exposomics.

• Publication year

  2025

• Venue

  bioRxiv

• Publication date

  2025-11-11

• Fields of study

  Biology, Medicine, Chemistry, Computer Science

• Identifiers
  DOI 10.1101/2025.11.10.687298PMID 41292869PMCID 12642542
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Generative artificial intelligence in medicine

  2025cited by this paper
• Large language models to accelerate organic chemistry synthesis

  2025cited by this paper
• Toward expert-level medical question answering with large language models

  2025cited by this paper
• Prediction of Fragmentation Pathway of Natural Products, Antibiotics, and Pesticides by ChemFrag

  2025cited by this paper
• Application of large language models in medicine

  2025cited by this paper
• Simulating Collision-Induced Dissociation Tandem Mass Spectrometry (CID-MS/MS) for the Blood Exposome Database Using Quantum Chemistry Methods - A Pilot Study.

  2025cited by this paper
• Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS.

  2025cited by this paper
• FIORA: Local neighborhood-based prediction of compound mass spectra from single fragmentation events

  2024cited by this paper
• Adapted large language models can outperform medical experts in clinical text summarization

  2023cited by this paper
• IDSL.CSA: Composite Spectra Analysis for Chemical Annotation of Untargeted Metabolomics Datasets

  2023cited by this paper
• Augmenting large language models with chemistry tools

  2023cited by this paper
• Generating Molecular Fragmentation Graphs with Autoregressive Neural Networks.

  2023cited by this paper
• IDSL.CSA: Composite Spectra Analysis for Chemical Annotation of Untargeted Metabolomics Datasets.

  2023cited by this paper
• A transformer-based model to predict peptide–HLA class I binding and optimize mutated peptides for vaccine design

  2022cited by this paper
• Highly accurate protein structure prediction with AlphaFold

  2021cited by this paper
• Predicting in silico electron ionization mass spectra using quantum chemistry

  2020cited by this paper
• Generating the Blood Exposome Database Using a Comprehensive Text Mining and Database Fusion Approach

  2019cited by this paper

• No citing papers are available for this paper.