DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra

2025-02-13

AI Summary

To address mass-spectrometry (MS)-driven unknown small-molecule structure elucidation, this paper proposes the first MS-conditioned graph diffusion molecular generation framework. Methodologically, it introduces a formula-constrained encoder–decoder architecture: the encoder integrates MS priors—including elemental peak formulas and neutral losses—while the decoder employs a discrete graph diffusion model restricted to heavy-atom composition. Crucially, we propose large-scale pretraining on fingerprint–structure pairs to mitigate the scarcity of structure–MS paired data and explicitly incorporate MS physical principles to enhance chemical validity and generalization. Our approach achieves state-of-the-art performance across multiple benchmarks. Ablation studies validate the efficacy of both the diffusion mechanism and pretraining strategy. Moreover, performance consistently improves with increasing pretraining data scale. The code is publicly available.

Technology Category

• Machine Learning: Structured Learning
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Mass spectrometry plays a fundamental role in elucidating the structures of unknown molecules and subsequent scientific discoveries. One formulation of the structure elucidation task is the conditional $ extit{de novo}$ generation of molecular structure given a mass spectrum. Toward a more accurate and efficient scientific discovery pipeline for small molecules, we present DiffMS, a formula-restricted encoder-decoder generative network that achieves state-of-the-art performance on this task. The encoder utilizes a transformer architecture and models mass spectra domain knowledge such as peak formulae and neutral losses, and the decoder is a discrete graph diffusion model restricted by the heavy-atom composition of a known chemical formula. To develop a robust decoder that bridges latent embeddings and molecular structures, we pretrain the diffusion decoder with fingerprint-structure pairs, which are available in virtually infinite quantities, compared to structure-spectrum pairs that number in the tens of thousands. Extensive experiments on established benchmarks show that DiffMS outperforms existing models on $ extit{de novo}$ molecule generation. We provide several ablations to demonstrate the effectiveness of our diffusion and pretraining approaches and show consistent performance scaling with increasing pretraining dataset size. DiffMS code is publicly available at https://github.com/coleygroup/DiffMS.

Problem

• Generate molecular structures from mass spectra
• Improve accuracy in small molecule discovery
• Utilize transformer and diffusion models

Innovation

• Transformer-based encoder for mass spectra
• Graph diffusion model for molecular structures
• Pretraining with fingerprint-structure pairs