Spec2Vec: Improved mass spectral similarity scoring through learning of structural relationships

PLoS Comput Biol. 2021 Feb 16;17(2):e1008724. doi: 10.1371/journal.pcbi.1008724. eCollection 2021 Feb.

Abstract

Spectral similarity is used as a proxy for structural similarity in many tandem mass spectrometry (MS/MS) based metabolomics analyses such as library matching and molecular networking. Although weaknesses in the relationship between spectral similarity scores and the true structural similarities have been described, little development of alternative scores has been undertaken. Here, we introduce Spec2Vec, a novel spectral similarity score inspired by a natural language processing algorithm-Word2Vec. Spec2Vec learns fragmental relationships within a large set of spectral data to derive abstract spectral embeddings that can be used to assess spectral similarities. Using data derived from GNPS MS/MS libraries including spectra for nearly 13,000 unique molecules, we show how Spec2Vec scores correlate better with structural similarity than cosine-based scores. We demonstrate the advantages of Spec2Vec in library matching and molecular networking. Spec2Vec is computationally more scalable allowing structural analogue searches in large databases within seconds.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms*
  • Computational Biology / methods*
  • Computer Simulation
  • Databases, Factual
  • False Positive Reactions
  • Gene Library*
  • Machine Learning
  • Metabolomics / methods*
  • Natural Language Processing
  • Reproducibility of Results
  • Tandem Mass Spectrometry / methods*

Grants and funding

J.J.J.v.d.H. acknowledges funding from an ASDI eScience grant, ASDI.2017.030, from the Netherlands eScience Center—NLeSC, www.esciencecenter.nl, The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.