GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problem
Abstract
Predicting tandem mass spectra (MS/MS) from molecular structures represents a central task in analytical chemistry with direct relevance to clinical metabolomics, systems biology, and adjacent disciplines. In this work, we revisit the problem through the lens of object detection on molecular graphs. Molecular fragmentation, a central step in MS/MS prediction, can be approximated as detecting a set of subgraphs (i.e., fragments) and their associated spectral contributions. Existing fragment-based models follow a two-stage paradigm -- first generating candidate fragments and then scoring them -- analogous to two-stage R-CNNs in computer vision. Towards higher accuracy and faster inference, we introduce GLACIER, a single-stage transformer-based fragment detection neural network for molecular graphs. This unified formulation eliminates the need for candidate enumeration, enabling scalable and globally consistent modeling of molecular fragmentation. GLACIER is faster and more accurate than existing state-of-the-art by a significant margin, achieving 70.0% and 69.7% Top-1 retrieval accuracy with and without contrastive finetuning on the MassSpecGym dataset (from the previous SOTA of 64.0%) and 52.5% and 38.5% respectively on the NIST'20 dataset (from 33.2%). Furthermore, GLACIER provides nearly 8-fold inference speedup over our prior two-stage model. Code is available at https://github.com/coleygroup/ms-pred
Related
- Beyond Behavioral Signs: Toward a Multidomain Risk Architecture for Early Detection of Autism Spectrum Disorder
- Cortical circuit implementation of signed deviant detection with positive and negative prediction error neurons
- A method for brain tumor detection and localization by means of deep learning and reliable prediction explainability
- Predicting climate-change impacts on the global glacier-fed stream microbiome
- Taxonomic and functional patterns of arthropod succession after glacier retreat in the Dolomite Alps
BibTeX
@misc{wang2026glacier,
title = {{GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problem}},
author = {Rui-Xi Wang and Runzhong Wang and Connor W. Coley},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.29161},
eprint = {2606.29161},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.29161},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problem
AU - Rui-Xi Wang
AU - Runzhong Wang
AU - Connor W. Coley
PY - 2026
DA - 2026/10/05
PB - arXiv
DO - 10.48550/arxiv.2606.29161
UR - https://arxiv.org/abs/2606.29161
AB - Predicting tandem mass spectra (MS/MS) from molecular structures represents a central task in analytical chemistry with direct relevance to clinical metabolomics, systems biology, and adjacent disciplines. In this work, we revisit the problem through the lens of object detection on molecular graphs. Molecular fragmentation, a central step in MS/MS prediction, can be approximated as detecting a set of subgraphs (i.e., fragments) and their associated spectral contributions. Existing fragment-based models follow a two-stage paradigm -- first generating candidate fragments and then scoring them -- analogous to two-stage R-CNNs in computer vision. Towards higher accuracy and faster inference, we introduce GLACIER, a single-stage transformer-based fragment detection neural network for molecular graphs. This unified formulation eliminates the need for candidate enumeration, enabling scalable and globally consistent modeling of molecular fragmentation. GLACIER is faster and more accurate than existing state-of-the-art by a significant margin, achieving 70.0% and 69.7% Top-1 retrieval accuracy with and without contrastive finetuning on the MassSpecGym dataset (from the previous SOTA of 64.0%) and 52.5% and 38.5% respectively on the NIST'20 dataset (from 33.2%). Furthermore, GLACIER provides nearly 8-fold inference speedup over our prior two-stage model. Code is available at https://github.com/coleygroup/ms-pred
ER -