SpecBridge: Bridging Mass Spectrometry and Molecular Representations via Cross-Modal Alignment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yinkai, Chen, Yan Zhou, Chen, Xiaohui, Liu, Li-Ping, Hassoun, Soha
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911483391115264
author Wang, Yinkai
Chen, Yan Zhou
Chen, Xiaohui
Liu, Li-Ping
Hassoun, Soha
author_facet Wang, Yinkai
Chen, Yan Zhou
Chen, Xiaohui
Liu, Li-Ping
Hassoun, Soha
contents Small-molecule identification from tandem mass spectrometry (MS/MS) remains a bottleneck in untargeted settings where spectral libraries are incomplete. While deep learning offers a solution, current approaches typically fall into two extremes: explicit generative models that construct molecular graphs atom-by-atom, or joint contrastive models that learn cross-modal subspaces from scratch. We introduce SpecBridge, a novel implicit alignment framework that treats structure identification as a geometric alignment problem. SpecBridge fine-tunes a self-supervised spectral encoder (DreaMS) to project directly into the latent space of a frozen molecular foundation model (ChemBERTa), and then performs retrieval by cosine similarity to a fixed bank of precomputed molecular embeddings. Across MassSpecGym, Spectraverse, and MSnLib benchmarks, SpecBridge improves top-1 retrieval accuracy by roughly 20-25% relative to strong neural baselines, while keeping the number of trainable parameters small. These results suggest that aligning to frozen foundation models is a practical, stable alternative to designing new architectures from scratch. The code for SpecBridge is released at https://github.com/HassounLab/SpecBridge.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17204
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SpecBridge: Bridging Mass Spectrometry and Molecular Representations via Cross-Modal Alignment
Wang, Yinkai
Chen, Yan Zhou
Chen, Xiaohui
Liu, Li-Ping
Hassoun, Soha
Machine Learning
Computational Engineering, Finance, and Science
Small-molecule identification from tandem mass spectrometry (MS/MS) remains a bottleneck in untargeted settings where spectral libraries are incomplete. While deep learning offers a solution, current approaches typically fall into two extremes: explicit generative models that construct molecular graphs atom-by-atom, or joint contrastive models that learn cross-modal subspaces from scratch. We introduce SpecBridge, a novel implicit alignment framework that treats structure identification as a geometric alignment problem. SpecBridge fine-tunes a self-supervised spectral encoder (DreaMS) to project directly into the latent space of a frozen molecular foundation model (ChemBERTa), and then performs retrieval by cosine similarity to a fixed bank of precomputed molecular embeddings. Across MassSpecGym, Spectraverse, and MSnLib benchmarks, SpecBridge improves top-1 retrieval accuracy by roughly 20-25% relative to strong neural baselines, while keeping the number of trainable parameters small. These results suggest that aligning to frozen foundation models is a practical, stable alternative to designing new architectures from scratch. The code for SpecBridge is released at https://github.com/HassounLab/SpecBridge.
title SpecBridge: Bridging Mass Spectrometry and Molecular Representations via Cross-Modal Alignment
topic Machine Learning
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2601.17204