MADGEN: Mass-Spec attends to De Novo Molecular generation

TL;DR

MADGEN is a novel scaffold-based method that uses mass spectrometry data to guide de novo molecular structure generation, significantly improving annotation accuracy in complex biological samples.

Contribution

It introduces a two-stage approach combining contrastive learning for scaffold retrieval and an attention-based generative model guided by spectra, enhancing molecular annotation.

Findings

MADGEN outperforms existing methods on multiple datasets.

Attention integration improves molecular generation accuracy.

Using an oracle retriever yields the best results.

Abstract

The annotation (assigning structural chemical identities) of MS/MS spectra remains a significant challenge due to the enormous molecular diversity in biological samples and the limited scope of reference databases. Currently, the vast majority of spectral measurements remain in the "dark chemical space" without structural annotations. To improve annotation, we propose MADGEN (Mass-spec Attends to De Novo Molecular GENeration), a scaffold-based method for de novo molecular structure generation guided by mass spectrometry data. MADGEN operates in two stages: scaffold retrieval and spectra-conditioned molecular generation starting with the scaffold. In the first stage, given an MS/MS spectrum, we formulate scaffold retrieval as a ranking problem and employ contrastive learning to align mass spectra with candidate molecular scaffolds. In the second stage, starting from the retrieved scaffold, we employ the MS/MS spectrum to guide an attention-based generative model to generate the final molecule. Our approach constrains the molecular generation search space, reducing its complexity and improving generation accuracy. We evaluate MADGEN on three datasets (NIST23, CANOPUS, and MassSpecGym) and evaluate MADGEN's performance with a predictive scaffold retriever and with an oracle retriever. We demonstrate the effectiveness of using attention to integrate spectral information throughout the generation process to achieve strong results with the oracle retriever.