Abstract
Mass spectrometry data is one of the key sources of information in many workflows in medicine and across the life sciences. Mass fragmentation spectra are generally considered to be characteristic signatures of the chemical compound they originate from, yet the chemical structure itself usually cannot be easily deduced from the spectrum. Often, spectral similarity measures are used as a proxy for structural similarity but this approach is strongly limited by a generally poor correlation between both metrics. Here, we propose MS2DeepScore: a novel Siamese neural network to predict the structural similarity between two chemical structures solely based on their MS/MS fragmentation spectra. Using a cleaned dataset of > 100,000 mass spectra of about 15,000 unique known compounds, we trained MS2DeepScore to predict structural similarity scores for spectrum pairs with high accuracy. In addition, sampling different model varieties through Monte-Carlo Dropout is used to further improve the predictions and assess the model’s prediction uncertainty. On 3600 spectra of 500 unseen compounds, MS2DeepScore is able to identify highly-reliable structural matches and to predict Tanimoto scores for pairs of molecules based on their fragment spectra with a root mean squared error of about 0.15. Furthermore, the prediction uncertainty estimate can be used to select a subset of predictions with a root mean squared error of about 0.1. Furthermore, we demonstrate that MS2DeepScore outperforms classical spectral similarity measures in retrieving chemically related compound pairs from large mass spectral datasets, thereby illustrating its potential for spectral library matching. Finally, MS2DeepScore can also be used to create chemically meaningful mass spectral embeddings that could be used to cluster large numbers of spectra. Added to the recently introduced unsupervised Spec2Vec metric, we believe that machine learning-supported mass spectral similarity measures have great potential for a range of metabolomics data processing pipelines.
Highlights
In the rapidly growing field of metabolomics, mass spectrometry fragmentation approaches are a key source of information to chemically characterize large numbers of detected molecules
With current open spectral libraries growing to such sizes that machine learning approaches have sufficient data for training, validation, and testing; we recognize that there is an opportunity for the development of alternative mass spectral similarity scores
With MS2DeepScore, we show for the first time that neural networks can be used to predict structural similarity scores, i.e., to obtain a chemical-driven measure, from MS/MS spectra without requiring a known molecular formula or other metadata
Summary
In the rapidly growing field of metabolomics, mass spectrometry fragmentation approaches are a key source of information to chemically characterize large numbers of detected molecules. With current open spectral libraries growing to such sizes that machine learning approaches have sufficient data for training, validation, and testing; we recognize that there is an opportunity for the development of alternative mass spectral similarity scores. This is in line with a recent review article sketching the current and future role of deep learning for metabolite annotation [13]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
