BMDMS-NP: A comprehensive ESI-MS/MS spectral library of natural compounds

Lee, Sang‐Won; Hwang, Sungbo; Seo, Myungwon; Shin, Ki Beom; Kim, Kwang Hoe; Park, Gun Wook; Kim, Jin Young; Yoo, Jong Shin; No, Kyoung Tai

doi:10.1016/j.phytochem.2020.112427

Cited by 16 publications

(16 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We construct a set of labeled MS/MS spectra by combining a number of publicly available datasets [29, 3, 14, 17, 22, 24, 25, 27, 31, 33, 35, 39, 41] with our internal proprietary dataset. We allow spectra collected in both positive and negative ion mode, and across a variety of instrument types, collision energies, and other important instrument parameters.…”

Section: Methodsmentioning

confidence: 99%

“…Unlike many machine learning methods on MS data, which may require minutes or more for a single inference call and scale poorly with molecular weight, MS2Prop can carry out inference even for very complex spectra with many peaks in a few milliseconds. Exploiting this computational efficiency, we predict properties for 500 million unlabeled spectra from a range of repositories of metabolomics experiments [29, 3, 14, 17, 22, 24, 25, 27, 31, 33, 35, 39, 41]. A first look at natural products space using these predictions suggests there exist portions of natural products space that are significantly drug-like, relatively synthetically accessible, and largely un-mined by current FDA approved drugs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MS2Prop: A machine learning model that directly generatesde novopredictions of drug-likeness of natural products from unannotated MS/MS spectra

Voronov

Frandsen

Bargh

et al. 2022

Preprint

View full text Add to dashboard Cite

Mass spectrometry is a key analytical tool for the study of complex small molecule mixtures. The contents of these mixtures are the subject of untargeted metabolomics applications ranging from understanding metabolism, disease, biomarkers, and environmental contaminants to natural products based drug discovery. Yet identifying from mixtures the compounds or their properties from mass spectrometry data remains very challenging for most small molecules. For most compounds there will not be an annotation, and nearly all annotation techniques rely on partial matches to spectral and structural databases with limited coverage. However, property prediction of unknowns in untargeted metabolomics relies heavily on those annotations. Here we introduce MS2Prop, a complement to compound identification, that directly predicts chemically relevant properties of compounds for drug discovery and other applications from mass spectrometry data for any mass spectrometry feature, regardless of whether the corresponding compound is in an existing database. On compounds excluded from the training set MS2Prop has an average R^2 = 0.73 across ten properties, including synthetic accessibility and quantitative drug likeness properties, and R^2 = 0.96 for compounds in the training set, but with disjoint spectra. For compounds excluded from the training set, MS2Prop outperforms predictions based on compound identification by over a factor of three, setting the stage for future use of computational prioritization of compounds for diagnostic and drug discovery applications.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

MS2Prop: A machine learning model that directly generatesde novopredictions of drug-likeness of natural products from unannotated MS/MS spectra

Voronov

Frandsen

Bargh

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The exact experimental setup and gradients used for chromatographic separation remain unclear. The results suggest that RT prediction with Fiora is possible, but requires extensive retraining with a larger Retention time values for the test sets were retrieved from the BMDMS-NP library [39] and CCS values from the whole MS-Dial library [34]. The diagonal lines describe perfect prediction.…”

Section: Fiora Generalizes Well Across Compound Classes and To Unknow...mentioning

confidence: 99%

Fiora: Local neighborhood-based prediction of compound mass spectra from single fragmentation events

Nowatzky,

Russo,

Lisec

et al. 2024

Preprint

View full text Add to dashboard Cite

Non-targeted metabolomics holds great promise for advancing precision medicine and facilitating the discovery of novel biomarkers. However, the identification of compounds from tandem mass spectra remains a non-trivial task due to the incomplete nature of spectral reference libraries. Augmenting these libraries with simulated mass spectra can provide the necessary reference to resolve unmatched mass spectra, but remains a difficult undertaking to this day. In this study, we introduce Fiora, an innovative open-source algorithm using graph neural networks to simulate tandem mass spectra in silico. Our objective is to improve fragment intensity prediction with an intricate graph model architecture that facilitates edge prediction, thereby modeling fragment ions as the result of singular bond breaks and their local molecular neighborhood. We evaluate the performance on test data from NIST (2017) and the curated MS-Dial spectral library, as well as compounds from the 2016 and 2022 CASMI challenges. Fiora not only surpasses state-of-the-art fragmentation algorithms, ICEBERG and CFM-ID, in terms of prediction quality, but also predicts additional features, such as retention time and collision cross section. In addition, Fiora emonstrates significant speed improvements through the use of GPUs. This enables rapid (re)scoring of putative compound identifications in non-targeted experiments and facilitates large-scale expansion of spectral reference libraries with accurate spectral predictions.

show abstract

“…26 Moreover, mass spectral database searching has become a well-accepted approach for the identification of unknown chemicals. 27 Rapid analysis of pentacyclic triterpenoids from medicinal plant sources using various analytical techniques including ESI-MS/MS also has been reported. [28][29][30] Nonetheless, there is only one report indicating the fragmentation behavior of certain unsaturated pentacyclic triterpenes of αand β-amyrin group 31…”

Section: Introductionmentioning

confidence: 99%

“…The product ions possess rich information regarding bond energies and the structures of the precursor and product ions can be used to infer structural information about new and/or similar analytes 26 . Moreover, mass spectral database searching has become a well‐accepted approach for the identification of unknown chemicals 27 …”

Section: Introductionmentioning

confidence: 99%

Structure–fragmentation study of pentacyclic triterpenoids using electrospray ionization quadrupole time‐of‐flight tandem mass spectrometry (ESI‐QTOFMS/MS)

Uddin¹,

Muhsinah²,

Imran³

et al. 2022

Rapid Comm Mass Spectrometry

View full text Add to dashboard Cite

Pentacyclic triterpenoids are secondary plant metabolites widespread in fruit peel, leaves, and stem bark. Due to their important biological activities, these compounds are widely screened using advance analytical techniques like electrospray ionization (ESI) mass spectrometry. Over the past few decades, the practice of ESI has been refined into a versatile ionization technique for a wide variety of analytes differing in their chemical makeup, size, complexity, and bimolecular stability. Methods: The structure-fragmentation relationships (SFRs) of 16 pentacyclic triterpenoids were studied using a positive ion ESI quadrupole time-of-flight mass spectrometry (ESI-QqTOFMS/MS) hybrid instrument. Results: ESI-QqTOFMS (positive ion mode) showed the presence of the protonated molecules [M + H] + of most of analyzed compounds. Low-energy collision-induced dissociation MS/MS analysis of these molecules indicated multiple losses of water molecules and the loss of the formic acid moiety [M + H À HCOOH] + and other substituents as the predominant pathway for further fragmentation. Key product ions were identified which resulted from the retro-Diels-Alder cleavage of the ring system. SFRs of all the compounds analyzed were also developed. Conclusions: We developed a fragmentation pattern of pentacyclic triterpenoids using the ESI-QqTOFMS/MS technique. It was concluded that the formation of key product ions and loss of characteristic neutrals can give detailed insight into structural information about the basic structure and attached substituents.

show abstract

BMDMS-NP: A comprehensive ESI-MS/MS spectral library of natural compounds

Cited by 16 publications

References 30 publications

MS2Prop: A machine learning model that directly generatesde novopredictions of drug-likeness of natural products from unannotated MS/MS spectra

MS2Prop: A machine learning model that directly generatesde novopredictions of drug-likeness of natural products from unannotated MS/MS spectra

Fiora: Local neighborhood-based prediction of compound mass spectra from single fragmentation events

Structure–fragmentation study of pentacyclic triterpenoids using electrospray ionization quadrupole time‐of‐flight tandem mass spectrometry (ESI‐QTOFMS/MS)

Contact Info

Product

Resources

About