GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problem

2026-06-27

AI Summary

This work addresses the challenge of fragmentation modeling in predicting tandem mass spectrometry (MS/MS) spectra from molecular structures by reframing the task as a target detection problem on molecular graphs. The authors propose a single-stage Transformer-based graph neural network framework that directly detects fragment subgraphs and their spectral contributions, circumventing the need for candidate enumeration inherent in traditional two-stage approaches. This enables globally consistent and scalable fragmentation modeling. Combined with a contrastive fine-tuning strategy, the model achieves top-1 retrieval accuracies of 70.0% on MassSpecGym and 52.5% on NIST'20, substantially outperforming existing methods while delivering nearly an 8× speedup in inference time.

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

Problem

• mass spectrometry prediction
• molecular fragmentation
• MS/MS
• object detection
• molecular graphs

Innovation

• mass spectrometry prediction
• molecular graph
• object detection
• transformer
• fragment detection